eaddario/Watt-Tool-8B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: eaddario/Watt-Tool-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 16:00:13 +08:00
commit f9723b838e
110 changed files with 14825 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.gitattributes vendored Normal file
View File

@@ -0,0 +1,38 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.gguf filter=lfs diff=lfs merge=lfs -text
*.logits filter=lfs diff=lfs merge=lfs -text
*.dat filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

584
.gitignore vendored Normal file
View File

@@ -0,0 +1,584 @@
# https://github.com/github/gitignore
# -------------
# General Linux
# -------------
.directory
.fuse_hidden*
.nfs*
.Trash-*
*~
# -----------
# General OSX
# -----------
._*
.apdisk
.AppleDB
.AppleDesktop
.AppleDouble
.com.apple.timemachine.donotpresent
.DocumentRevisions-V100
.DS_Store
.fseventsd
.LSOverride
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
Network Trash Folder
Temporary Items
# ---------------
# General Windows
# ---------------
[Dd]esktop.ini
*.cab
*.lnk
*.msi
*.msix
*.msm
*.msp
*.stackdump
$RECYCLE.BIN/
ehthumbs_vista.db
ehthumbs.db
Thumbs.db
Thumbs.db:encryptable
# -----------------
# General JetBrains
# -----------------
.idea_modules/
.idea/
*.iml
*.ipr
*.iws
# ---------------
# General VS Code
# ---------------
!.vscode/*.code-snippets
!.vscode/extensions.json
!.vscode/launch.json
!.vscode/settings.json
!.vscode/tasks.json
.history/
.vscode/
*.vsix
# ---------------------
# General Visual Studio
# ---------------------
__pycache__/
_NCrunch_*
_pkginfo.txt
_Pvt_Extensions
_ReSharper*/
_TeamCity*
_UpgradeReport_Files/
!?*.[Cc]ache/
!.vscode/extensions.json
!**/[Pp]ackages/build/
.*crunch*.local.xml
.builds
.cr/personal
.fake/
.ionide/
.localhistory/
.mfractor/
.ntvs_analysis.dat
.paket/paket.exe
.sass-cache/
.vs/
.vscode/*
.vshistory/
[Aa][Rr][Mm]/
[Aa][Rr][Mm]64/
[Bb]in/
[Bb]uild[Ll]og.*
[Dd]ebug/
[Dd]ebugPS/
[Dd]ebugPublic/
[Ee]xpress/
[Ll]og/
[Ll]ogs/
[Oo]bj/
[Rr]elease/
[Rr]eleasePS/
[Rr]eleases/
[Tt]est[Rr]esult*/
[Ww][Ii][Nn]32/
*_h.h
*_i.c
*_p.c
*_wpftmp.csproj
*- [Bb]ackup ([0-9]).rdl
*- [Bb]ackup ([0-9][0-9]).rdl
*- [Bb]ackup.rdl
*.[Cc]ache
*.[Pp]ublish.xml
*.[Rr]e[Ss]harper
*.appx
*.appxbundle
*.appxupload
*.aps
*.azurePubxml
*.bim_*.settings
*.bim.layout
*.binlog
*.btm.cs
*.btp.cs
*.build.csdef
*.cachefile
*.code-workspace
*.coverage
*.coveragexml
*.dbmdl
*.dbproj.schemaview
*.dotCover
*.DotSettings.user
*.dsp
*.dsw
*.e2e
*.GhostDoc.xml
*.gpState
*.ilk
*.iobj
*.ipdb
*.jfm
*.jmconfig
*.ldf
*.mdf
*.meta
*.mm.*
*.ncb
*.ndf
*.nuget.props
*.nuget.targets
*.nupkg
*.nvuser
*.obj
*.odx.cs
*.opendb
*.opensdf
*.opt
*.pch
*.pdb
*.pfx
*.pgc
*.pgd
*.pidb
*.plg
*.psess
*.publishproj
*.publishsettings
*.pubxml
*.pyc
*.rdl.data
*.rptproj.bak
*.rptproj.rsuser
*.rsp
*.rsuser
*.sap
*.sbr
*.scc
*.sdf
*.sln.docstates
*.sln.iml
*.snupkg
*.suo
*.svclog
*.tlb
*.tlh
*.tli
*.tlog
*.tmp
*.tmp_proj
*.tss
*.user
*.userosscache
*.userprefs
*.vbp
*.vbw
*.VC.db
*.VC.VC.opendb
*.VisualState.xml
*.vsp
*.vspscc
*.vspx
*.vssscc
*.xsd.cs
**/[Pp]ackages/*
**/*.DesktopClient/GeneratedArtifacts
**/*.DesktopClient/ModelManifest.xml
**/*.HTMLClient/GeneratedArtifacts
**/*.Server/GeneratedArtifacts
**/*.Server/ModelManifest.xml
~$*
$tf/
AppPackages/
artifacts/
ASALocalRun/
AutoTest.Net/
Backup*/
BenchmarkDotNet.Artifacts/
bld/
BundleArtifacts/
ClientBin/
coverage*.info
coverage*.json
coverage*.xml
csx/
dlldata.c
DocProject/buildhelp/
DocProject/Help/*.hhc
DocProject/Help/*.hhk
DocProject/Help/*.hhp
DocProject/Help/*.HxC
DocProject/Help/*.HxT
DocProject/Help/html
DocProject/Help/Html2
ecf/
FakesAssemblies/
FodyWeavers.xsd
Generated_Code/
healthchecksdb
ipch/
MigrationBackup/
mono_crash.*
nCrunchTemp_*
node_modules/
nunit-*.xml
OpenCover/
orleans.codegen.cs
Package.StoreAssociation.xml
paket-files/
project.fragment.lock.json
project.lock.json
publish/
PublishScripts/
rcf/
ScaffoldingReadMe.txt
ServiceFabricBackup/
StyleCopReport.xml
TestResult.xml
UpgradeLog*.htm
UpgradeLog*.XML
x64/
x86/
# ----------------------
# General Archived Files
# ----------------------
*.7z
*.bz2
*.bzip
*.bzip2
*.deb
*.dmg
*.egg
*.gem
*.gz
*.gzip
*.iso
*.jar
*.lzma
*.rar
*.rpm
*.tar
*.tgz
*.txz
*.tzst
*.xar
*.xpi
*.xz
*.zip
*.zst
# -----
# C/C++
# -----
.tmp_versions/
*.a
*.app
*.cmd
*.d
*.dll
*.dSYM/
*.dylib
*.elf
*.exe
*.exp
*.gch
*.hex
*.i*86
*.idb
*.ko
*.la
*.lai
*.lib
*.lo
*.map
*.mod*
*.o
*.out
*.slo
*.so
*.so.*
*.su
*.x86_64
dkms.conf
Mkfile.old
Module.symvers
modules.order
# ----
# CUDA
# ----
*.cubin
*.fatbin
*.gpu
*.i
*.ii
*.ptx
# --
# Go
# --
.env
*.exe~
*.test
go.work
go.work.sum
# ----
# Java
# ----
*.class
*.ctxt
*.ear
*.hprof
*.nar
*.tar.gz
*.war
hs_err_pid*
replay_pid*
# -----
# Julia
# -----
*.jl.*.cov
*.jl.cov
*.jl.mem
deps/build.log
deps/deps.jl
deps/downloads/
deps/src/
deps/usr/
docs/build/
docs/site/
Manifest.toml
# ------------------------------
# JavaScript / Node / TypeScript
# ------------------------------
.cache
.cache/
.docusaurus
.dynamodb/
.env.development.local
.env.local
.env.production.local
.env.test.local
.eslintcache
.fusebox/
.grunt
.lock-wscript
.next
.node_repl_history
.npm
.nuxt
.nyc_output
.parcel-cache
.pnp.*
.pnpm-debug.log*
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
.serverless/
.stylelintcache
.temp
.tern-port
.vscode-test
.vuepress/dist
.yarn-integrity
.yarn/build-state.yml
.yarn/cache
.yarn/install-state.gz
.yarn/unplugged
*.lcov
*.pid
*.pid.lock
*.seed
*.tsbuildinfo
bower_components
dist
jspm_packages/
lerna-debug.log*
lib-cov
logs
npm-debug.log*
out
pids
report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
web_modules/
yarn-debug.log*
yarn-error.log*
# ------
# Python
# ------
__pypackages__/
.coverage
.coverage.*
.dmypy.json
.eggs/
.hypothesis/
.installed.cfg
.ipynb_checkpoints
.mypy_cache/
.nox/
.pdm-build/
.pdm-python
.pdm.toml
.pybuilder/
.pyre/
.pytest_cache/
.Python
.python-version
.pytype/
.ropeproject
.scrapy
.spyderproject
.spyproject
.tox/
.venv
.webassets-cache
*.cover
*.egg-info/
*.manifest
*.mo
*.pot
*.py,cover
*.py[cod]
*.sage.py
*.spec
*$py.class
/site
build/
celerybeat-schedule
celerybeat.pid
cover/
coverage.xml
cython_debug/
db.sqlite3
db.sqlite3-journal
develop-eggs/
dist/
dmypy.json
docs/_build/
downloads/
eggs/
env.bak/
env/
htmlcov/
instance/
ipython_config.py
lib/
lib64/
local_settings.py
MANIFEST
nosetests.xml
parts/
pip-delete-this-directory.txt
pip-log.txt
profile_default/
sdist/
share/python-wheels/
target/
var/
venv.bak/
venv/
wheels/
# ----
# Rust
# ----
**/*.rs.bk
Cargo.lock
debug/
# -----
# Scala
# -----
# -----
# CMake
# -----
_deps
cmake_install.cmake
CMakeCache.txt
CMakeFiles
CMakeLists.txt.user
CMakeScripts
CMakeUserPresets.json
compile_commands.json
CTestTestfile.cmake
install_manifest.txt
Makefile
Testing
# ------
# Gradle
# ------
!gradle-wrapper.jar
!gradle-wrapper.properties
!src/**/build/
.classpath
.gradle
.gradletasknamecache
.project
**/build/
gradle-app.setting
# -----
# Maven
# -----
.mvn/
buildNumber.properties
dependency-reduced-pom.xml
pom.xml.next
pom.xml.releaseBackup
pom.xml.tag
pom.xml.versionsBackup
release.properties
# ---------
# Terraform
# ---------
.terraform.tfstate.lock.info
.terraform/
.terraformrc
*_override.tf
*_override.tf.json
*.tfstate
*.tfstate.*
*.tfvars
*.tfvars.json
crash.*.log
crash.log
override.tf
override.tf.json
terraform.rc

140
README.md Normal file
View File

@@ -0,0 +1,140 @@
---
base_model:
- watt-ai/watt-tool-8B
datasets:
- eaddario/imatrix-calibration
language:
- en
license:
- apache-2.0
pipeline_tag: text-generation
tags:
- gguf
- quant
- experimental
---
# Experimental layer-wise quantization of watt-ai/watt-tool-8B
Using [LLaMA C++](<https://github.com/ggerganov/llama.cpp>) release [b5150](<https://github.com/ggerganov/llama.cpp/releases/tag/b5150>) for quantization.
Original model: [watt-ai/watt-tool-8B](https://huggingface.co/watt-ai/watt-tool-8B)
From the original model creators:
> watt-tool-8B is a fine-tuned language model based on LLaMa-3.1-8B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the [Berkeley Function-Calling Leaderboard (BFCL)](<https://gorilla.cs.berkeley.edu/leaderboard.html>)
>
> The model is specifically designed to excel at complex tool usage scenarios that require multi-turn interactions, making it ideal for empowering platforms like [Lupan](<https://lupan.watt.chat/>), an AI-powered workflow building tool. By leveraging a carefully curated and optimized dataset, watt-tool-8B demonstrates superior capabilities in understanding user requests, selecting appropriate tools, and effectively utilizing them across multiple turns of conversation.
# PLEASE READ THIS BEFORE USING THESE EXPERIMENTAL VERSIONS!
An area of personal interest is finding ways to optimize the inference performance of LLMs when deployed in resource-constrained environments like commodity hardware, desktops, laptops, mobiles, edge devices, etc. There are many approaches to accomplish this, including architecture simplification and knowledge distillation, but my focus has been primarily on quantization and pruning.
The method used to produce these experimental versions is covered in [Squeezing Tensor Bits: the quest for smaller LLMs](<https://medium.com/@eaddario/squeezing-tensor-bits-the-quest-for-smaller-llms-86b23bd052ca>), but at a high level it involves using custom versions of `llama-imatrix` and `llama-quantize` to identify the influential tensors, and quantize the most important layers to higher bit precision and the less important to lower bits. This process was partly inspired by Dumitru's et al [Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels](<https://arxiv.org/abs/2406.17415>).
There’re two pull requests ([imatrix](<https://github.com/ggml-org/llama.cpp/pull/12718>) & [quantize](<https://github.com/ggml-org/llama.cpp/pull/12511>)) to merge these changes back into the core llama.cpp project. This may or may not ever happen so, until then, the modified versions will be available on [GitHub](<https://github.com/EAddario/llama.cpp>).
For testing and comparison I'd normally use models produced by [Unsloth](<https://huggingface.co/unsloth>) ([Daniel and Michael Han](<https://unsloth.ai/>) do some really advanced level stuff!) and [Bartowski](<https://huggingface.co/bartowski>) (see credits below), but they don't provide GGUF versions of this model, so all tests and comparisons are done against naive quantizations obtained by simply running `llama-quantize` with no further optimization.
All experimental versions were generated using an appropriate imatrix created from calibration datasets available at [eaddario/imatrix-calibration](<https://huggingface.co/datasets/eaddario/imatrix-calibration>). At its core, an Importance Matrix (imatrix) is a table or, more broadly, a structured representation that scores the relative importance of different features or parameters in a machine learning model. It essentially quantifies the "impact" each feature has on a specific outcome, prediction, or relationship being modeled, and it helps to counterbalance the negative effects of quantization and pruning.
The process to generate these models is roughly as follows:
1. Convert the the original model's tensors to [GGUF](<https://huggingface.co/docs/hub/en/gguf>) F16*
2. Estimate the Perplexity score for the F16 model (baseline) using the [wikitext-2-raw-v1](<https://huggingface.co/datasets/Salesforce/wikitext/tree/main/wikitext-2-raw-v1>) dataset, and save the [logits](<https://huggingface.co/eaddario/Watt-Tool-8B-GGUF/tree/main/logits>)
3. Generate an [imatrix](<https://huggingface.co/eaddario/Watt-Tool-8B-GGUF/tree/main/imatrix>) from selected calibration datasets
4. Determine tensor and layer Importance Score contribution using a modified version of `llama-imatrix`
5. Select an appropiate quant level for each tensor using a modified version of `llama-quantize`
6. Calculate Perplexity, KL Divergence, ARC (Easy+Challenge), HellaSwag, MMLU, Truthful QA and WinoGrande scores for each quantized model
7. Keep versions with the best scores
8. Repeat until all desired quants are created. I find that quantizations below Q3/IQ3 are not fit for my purposes and therefore do not usually generate them, but happy to provide other quants on request.
*[BF16](<https://en.wikipedia.org/wiki/Bfloat16_floating-point_format>) would be preferred, but Apple's GPUs don't support it yet, and therefore any operations are executed in the CPU, making it unacceptably slow. This is expected to change in the near term but until then, if you are using Apple kit avoid using any models tagged BF16
# Models
### Sizes (in GB)
| Model | Naive | Repo | Shrinkage |
| ------------------------------------------------- | ----: | ---: | --------: |
| [Watt-Tool-8B-IQ3_M](./Watt-Tool-8B-IQ3_M.gguf) | 3.78 | 3.69 | 2.4% |
| [Watt-Tool-8B-IQ3_S](./Watt-Tool-8B-IQ3_S.gguf) | 3.68 | 3.43 | 6.8% |
| [Watt-Tool-8B-IQ4_NL](./Watt-Tool-8B-IQ4_NL.gguf) | 4.68 | 4.39 | 6.2% |
| [Watt-Tool-8B-Q3_K_L](./Watt-Tool-8B-Q3_K_L.gguf) | 4.32 | 3.76 | 13.0% |
| [Watt-Tool-8B-Q3_K_M](./Watt-Tool-8B-Q3_K_M.gguf) | 4.02 | 3.56 | 11.4% |
| [Watt-Tool-8B-Q3_K_S](./Watt-Tool-8B-Q3_K_S.gguf) | 3.66 | 3.31 | 9.6% |
| [Watt-Tool-8B-Q4_K_M](./Watt-Tool-8B-Q4_K_M.gguf) | 4.92 | 4.41 | 10.4% |
| [Watt-Tool-8B-Q4_K_S](./Watt-Tool-8B-Q4_K_S.gguf) | 4.69 | 4.28 | 8.7% |
| [Watt-Tool-8B-Q5_K_M](./Watt-Tool-8B-Q5_K_M.gguf) | 5.73 | 5.38 | 6.1% |
| [Watt-Tool-8B-Q5_K_S](./Watt-Tool-8B-Q5_K_S.gguf) | 5.60 | 5.24 | 6.4% |
| [Watt-Tool-8B-Q6_K](./Watt-Tool-8B-Q6_K.gguf) | 6.60 | 6.57 | 0.5% |
| [Watt-Tool-8B-Q8_0](./Watt-Tool-8B-Q8_0.gguf) | 8.54 | 7.73 | 9.5% |
### Perplexity and KL Divergence scores
| Model | μPPL | 𝜌PPL | μKLD | RMS Δp |
| ------------------------------------------------- | -----------------: | -----: | -----------------: | ------------: |
| [Watt-Tool-8B-IQ3_M](./Watt-Tool-8B-IQ3_M.gguf) | 7.841948 ±0.049502 | 98.36% | 0.081774 ±0.000354 | 8.316 ±0.043 |
| [Watt-Tool-8B-IQ3_S](./Watt-Tool-8B-IQ3_S.gguf) | 8.253598 ±0.051864 | 97.71% | 0.117565 ±0.000433 | 10.385 ±0.045 |
| [Watt-Tool-8B-IQ4_NL](./Watt-Tool-8B-IQ4_NL.gguf) | 7.516430 ±0.047275 | 99.30% | 0.034545 ±0.000172 | 5.270 ±0.035 |
| [Watt-Tool-8B-Q3_K_L](./Watt-Tool-8B-Q3_K_L.gguf) | 8.274172 ±0.052402 | 97.60% | 0.114738 ±0.000483 | 10.050 ±0.048 |
| [Watt-Tool-8B-Q3_K_M](./Watt-Tool-8B-Q3_K_M.gguf) | 8.459379 ±0.053550 | 97.26% | 0.131196 ±0.000539 | 10.892 ±0.050 |
| [Watt-Tool-8B-Q3_K_S](./Watt-Tool-8B-Q3_K_S.gguf) | 8.869361 ±0.056188 | 96.40% | 0.171689 ±0.000675 | 12.587 ±0.055 |
| [Watt-Tool-8B-Q4_K_M](./Watt-Tool-8B-Q4_K_M.gguf) | 7.553687 ±0.047468 | 99.32% | 0.033370 ±0.000164 | 5.188 ±0.033 |
| Watt-Tool-8B-Q4_K_M (naive) | 7.409510 ±0.046740 | 99.65% | 0.017663 ±0.000107 | 3.658 ±0.032 |
| [Watt-Tool-8B-Q4_K_S](./Watt-Tool-8B-Q4_K_S.gguf) | 7.570386 ±0.047455 | 99.27% | 0.036155 ±0.000172 | 5.421 ±0.034 |
| [Watt-Tool-8B-Q5_K_M](./Watt-Tool-8B-Q5_K_M.gguf) | 7.337057 ±0.046220 | 99.81% | 0.009155 ±0.000052 | 2.680 ±0.024 |
| [Watt-Tool-8B-Q5_K_S](./Watt-Tool-8B-Q5_K_S.gguf) | 7.347298 ±0.046298 | 99.80% | 0.009763 ±0.000056 | 2.763 ±0.024 |
| [Watt-Tool-8B-Q6_K](./Watt-Tool-8B-Q6_K.gguf) | 7.275772 ±0.045822 | 99.93% | 0.003219 ±0.000027 | 1.585 ±0.020 |
| [Watt-Tool-8B-Q8_0](./Watt-Tool-8B-Q8_0.gguf) | 7.262551 ±0.045671 | 99.96% | 0.001873 ±0.000019 | 1.209 ±0.015 |
| [Watt-Tool-8B-F16](./Watt-Tool-8B-F16.gguf) | 7.237090 ±0.045539 | 100% | N/A | N/A |
### ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
Scores generated using [llama-perplexity](<https://github.com/ggml-org/llama.cpp/tree/master/examples/perplexity>) with 750 tasks per test, and a context size of 768 tokens.
For the test data used in the generation of these scores, follow the appropiate links: [HellaSwag](<https://github.com/klosax/hellaswag_text_data>), [ARC, MMLU, Truthful QA](<https://huggingface.co/datasets/ikawrakow/validation-datasets-for-llama.cpp/tree/main>) and [WinoGrande](<https://huggingface.co/datasets/ikawrakow/winogrande-eval-for-llama.cpp/tree/main>)
| Model | ARC | HellaSwag | MMLU | Truthful QA | WinoGrande | Avg Score |
| ------------------------------------------------- | --------------: | --------: | --------------: | --------------: | --------------: | --------: |
| [Watt-Tool-8B-IQ3_M](./Watt-Tool-8B-IQ3_M.gguf) | 62.8000 ±1.7661 | 78.00 | 37.7333 ±1.7711 | 32.1333 ±1.7063 | 73.6000 ±1.6106 | 56.85 |
| [Watt-Tool-8B-IQ3_S](./Watt-Tool-8B-IQ3_S.gguf) | 62.0000 ±1.7736 | 76.26 | 37.3333 ±1.7674 | 30.4000 ±1.6807 | 72.9333 ±1.6235 | 55.79 |
| [Watt-Tool-8B-IQ4_NL](./Watt-Tool-8B-IQ4_NL.gguf) | 63.4667 ±1.7594 | 77.73 | 39.6000 ±1.7870 | 31.4667 ±1.6968 | 75.4667 ±1.5722 | 57.55 |
| [Watt-Tool-8B-Q3_K_L](./Watt-Tool-8B-Q3_K_L.gguf) | 61.7333 ±1.7759 | 77.20 | 38.5333 ±1.7783 | 32.4000 ±1.7100 | 71.8667 ±1.6430 | 56.35 |
| [Watt-Tool-8B-Q3_K_M](./Watt-Tool-8B-Q3_K_M.gguf) | 61.0667 ±1.7816 | 77.20 | 38.5333 ±1.7783 | 33.3333 ±1.7225 | 73.0667 ±1.6209 | 56.64 |
| [Watt-Tool-8B-Q3_K_S](./Watt-Tool-8B-Q3_K_S.gguf) | 58.2667 ±1.8018 | 75.60 | 38.1333 ±1.7748 | 33.2000 ±1.7207 | 73.6000 ±1.6106 | 55.76 |
| [Watt-Tool-8B-Q4_K_M](./Watt-Tool-8B-Q4_K_M.gguf) | 65.7333 ±1.7342 | 77.73 | 39.4667 ±1.7860 | 30.9333 ±1.6889 | 74.0000 ±1.6027 | 57.57 |
| Watt-Tool-8B-Q4_K_M (naive) | 62.5668 ±1.7707 | 77.73 | 42.0000 ±1.8034 | 36.8098 ±2.6753 | 73.6000 ±1.6106 | 58.54 |
| [Watt-Tool-8B-Q4_K_S](./Watt-Tool-8B-Q4_K_S.gguf) | 65.8667 ±1.7325 | 78.00 | 39.4667 ±1.7860 | 30.5333 ±1.6828 | 73.2000 ±1.6184 | 57.41 |
| [Watt-Tool-8B-Q5_K_M](./Watt-Tool-8B-Q5_K_M.gguf) | 65.7333 ±1.7342 | 78.66 | 40.9333 ±1.7967 | 33.7333 ±1.7276 | 75.0667 ±1.5808 | 58.83 |
| [Watt-Tool-8B-Q5_K_S](./Watt-Tool-8B-Q5_K_S.gguf) | 65.7333 ±1.7342 | 78.66 | 41.6000 ±1.8010 | 33.6000 ±1.7259 | 74.5333 ±1.5919 | 58.83 |
| [Watt-Tool-8B-Q6_K](./Watt-Tool-8B-Q6_K.gguf) | 66.1333 ±1.7292 | 79.33 | 40.1333 ±1.7910 | 33.0667 ±1.7190 | 74.5333 ±1.5919 | 58.64 |
| [Watt-Tool-8B-Q8_0](./Watt-Tool-8B-Q8_0.gguf) | 65.8667 ±1.7325 | 78.67 | 41.0667 ±1.7976 | 32.9333 ±1.7172 | 74.5333 ±1.5919 | 58.61 |
| [Watt-Tool-8B-F16](./Watt-Tool-8B-F16.gguf) | 65.8667 ±1.7325 | 78.67 | 40.9333 ±1.7967 | 32.9333 ±1.7172 | 74.8000 ±1.5864 | 58.64 |
### Tokens per Second - Benchmarks
Scores generated using [llama-bench](https://github.com/ggml-org/llama.cpp/tree/master/examples/llama-bench). Naive Q4_K_M quantization included for comparison.
| model | size | params | backend | threads | test | t/s |
| ------------------------------------------------- | -------: | -----: | ---------- | ------: | ------------: | ------------: |
| [Watt-Tool-8B-Q4_K_M](./Watt-Tool-8B-Q4_K_M.gguf) | 4.10 GiB | 8.03 B | Metal,BLAS | 6 | pp512 | 313.03 ± 1.17 |
| [Watt-Tool-8B-Q4_K_M](./Watt-Tool-8B-Q4_K_M.gguf) | 4.10 GiB | 8.03 B | Metal,BLAS | 6 | tg128 | 27.97 ± 0.08 |
| [Watt-Tool-8B-Q4_K_M](./Watt-Tool-8B-Q4_K_M.gguf) | 4.10 GiB | 8.03 B | Metal,BLAS | 6 | pp1024+tg1024 | 44.64 ± 0.22 |
| Watt-Tool-8B-Q4_K_M (naive) | 4.58 GiB | 8.03 B | Metal,BLAS | 6 | pp512 | 327.42 ± 0.47 |
| Watt-Tool-8B-Q4_K_M (naive) | 4.58 GiB | 8.03 B | Metal,BLAS | 6 | tg128 | 26.18 ± 0.08 |
| Watt-Tool-8B-Q4_K_M (naive) | 4.58 GiB | 8.03 B | Metal,BLAS | 6 | pp1024+tg1024 | 42.69 ± 0.09 |
# Metrics used
**[Perplexity](<https://huggingface.co/docs/transformers/en/perplexity>):** one of the key metrics used in NLP evaluation. It measures the quality of a language model by evaluating how well it predicts the next token given a particular sequence of words. A PPL of **1** indicates an exact match between predicted and actual, whereas values greater than one indicate a degree of "surprise" the generated token differs from the expected.
**[Kullback–Leibler (KL) Divergence](<https://en.wikipedia.org/wiki/Kullback–Leibler_divergence>):** a statistical measure of how much a probability distribution differs from another. When quantizing models (or altering the original tensors in any way for that matter), the closest we can preserve the weights' probability distribution to the original model the better, thus the closest to **0** the better.
**[AI2 Reasoning Challenge (ARC)](<https://leaderboard.allenai.org/arc/submissions/get-started>):** a benchmark to evaluate the ability of AI models to answer complex science questions that require logical reasoning beyond pattern matching.
**[HellaSwag](<https://rowanzellers.com/hellaswag/>):** the Harder Endings, Longer contexts, and Low-shot Activities for Situations With Adversarial Generations (bit of a mouthful!) is a benchmark designed to test commonsense natural language inference. It requires the model to predict the most likely ending of a sentence.
**[MMLU](<https://github.com/hendrycks/test>):** the Massive Multitask Language Understanding evaluates LLMs’ general knowledge and problem-solving abilities across 57 subjects, including elementary mathematics, US history, computer science, and law.
**[Truthful QA](<https://github.com/sylinrl/TruthfulQA>):** evaluates how well LLMs generate truthful responses to questions. It identifies whether AI models can avoid generating false or misleading information, particularly in areas where human knowledge is prone to misconceptions.
**[Winogrande](<https://winogrande.allenai.org/>):** based on the [Winograd Schema Challenge](<https://cdn.aaai.org/ocs/4492/4492-21843-1-PB.pdf>), is a natural language understanding task requiring models to resolve ambiguities in sentences involving pronoun references.
## Credits
A big **Thank You!** to [Colin Kealty](<https://huggingface.co/bartowski>) for the many contributions and for being one of the best sources of high quality quantized models available in Hugginface, and a really big ***Thank You!*** to [Georgi Gerganov](<https://github.com/ggerganov>) for his amazing work with **llama.cpp** and the **ggml/gguf** libraries.

3
Watt-Tool-8B-F16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3180113741ba97ed0037a0461cea6a8df298423398411b13974538c8687ca659
size 16068892192

3
Watt-Tool-8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f540894975327cbd19efa3b59756634affd17c74208f87cad1abf6d38c20e65
size 3685259040

3
Watt-Tool-8B-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7bbed2bd502eeaf4c35a3c2b226fd11fcd80b195dc651f8960845f80f753cffd
size 3431012128

3
Watt-Tool-8B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d7cb0515ea6fcf8b1972efcfcdde440f75b64767a0439752ce98ec18433bccf
size 4394661664

3
Watt-Tool-8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40c9a48865f3bdc20e9d6e2e2af059f13d00b4b40ef3c32e841462a06457c32b
size 3757610784

3
Watt-Tool-8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5447a240e72006cf523b61388c6718cd18acb9bee66b51e913eb22611b0949b8
size 3564148512

3
Watt-Tool-8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3723ae295218e143e69b7205fc1f55b352e67e3c10b79deca4f3c5177c37e8c5
size 3305797408

3
Watt-Tool-8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:040db4c4a874e1654d02d1b9fdc81875a58ddbabe36bae915a4d72912ea71fcc
size 4405147424

3
Watt-Tool-8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6244ebc0a241d912682b687bff3e9f554e4eff69a9492b34cb37f4538f9affdc
size 4279318304

3
Watt-Tool-8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:70bb104cb1d2a4ca3aac8651c0f96ce8d265b466e4c9e3be2e51425551e83f47
size 5375735584

3
Watt-Tool-8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9102f2c7dee391e31d1fb5d9d706e18da0d3e7cf0b2a56112f78c8a3bcbdf741
size 5242042144

3
Watt-Tool-8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:749746e38f80775460a8aeed9e10341509149bbb9630c6592ec77c494f41b113
size 6568007456

3
Watt-Tool-8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5a5ae5c0853e2b7324211a3eafd5cf7f69f5fa942b1852230b531b10f68ee93
size 7734900512

3
imatrix/imatrix-Watt-Tool-8B-micro.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a1d2c07594bc90b0c5628b9abe601c7cd709ad621479fd55429f6934ac2e33d
size 5004591

3
imatrix/imatrix-Watt-Tool-8B-small.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2060cea90dd0130292a753f7500892bed97ebb7aaa92e2272b706d8740a54eb4
size 5004591

3
imatrix/imatrix-Watt-Tool-8B-tiny.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c3b83b652c7cbb810803c9e994ded2a899486b8585c2efcae600809f07829ab3
size 5004590

3
logits/Watt-Tool-8B-F16.logits Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92d3afca5550f046dd0e278530e4740638093f9398a34c8173856d1225ef2e95
size 36942087252

13
scores/Watt-Tool-8B-F16.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 292 tensors from ./Watt-Tool-8B-F16.gguf (version GGUF V3 (latest))
Final result: 65.8667 +/- 1.7325
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 7049.26 ms
llama_perf_context_print: prompt eval time = 109446.86 ms / 36600 tokens ( 2.99 ms per token, 334.41 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 110483.23 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-F16.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 292 tensors from ./Watt-Tool-8B-F16.gguf (version GGUF V3 (latest))
750 78.66666667% [75.5926%, 81.4486%]
llama_perf_context_print: load time = 580.08 ms
llama_perf_context_print: prompt eval time = 381945.70 ms / 126448 tokens ( 3.02 ms per token, 331.06 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 386591.06 ms / 126449 tokens
ggml_metal_free: deallocating

978
scores/Watt-Tool-8B-F16.md Normal file
View File

@@ -0,0 +1,978 @@
# Watt-Tool-8B-F16.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 39 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 36 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | general.file_type | 1 |
| 28 | UINT32 | 1 | llama.vocab_size | 128256 |
| 29 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 30 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 31 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 32 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 33 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 34 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 35 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 36 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 37 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 38 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 39 | UINT32 | 1 | general.quantization_version | 2 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-F16.gguf - GGUF Internal File Dump](#watt-tool-8b-f16gguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | rope_freqs.weight | 0x779520 | 0x100 |
| 1 | output.weight | 0x779620 | 0x3ea00000 |
| 2 | token_embd.weight | 0x3f179620 | 0x3ea00000 |
| 3 | blk.0.attn_norm.weight | 0x7db79620 | 0x4000 |
| 4 | blk.0.ffn_down.weight | 0x7db7d620 | 0x7000000 |
| 5 | blk.0.ffn_gate.weight | 0x84b7d620 | 0x7000000 |
| 6 | blk.0.ffn_up.weight | 0x8bb7d620 | 0x7000000 |
| 7 | blk.0.ffn_norm.weight | 0x92b7d620 | 0x4000 |
| 8 | blk.0.attn_k.weight | 0x92b81620 | 0x800000 |
| 9 | blk.0.attn_output.weight | 0x93381620 | 0x2000000 |
| 10 | blk.0.attn_q.weight | 0x95381620 | 0x2000000 |
| 11 | blk.0.attn_v.weight | 0x97381620 | 0x800000 |
| 12 | blk.1.attn_norm.weight | 0x97b81620 | 0x4000 |
| 13 | blk.1.ffn_down.weight | 0x97b85620 | 0x7000000 |
| 14 | blk.1.ffn_gate.weight | 0x9eb85620 | 0x7000000 |
| 15 | blk.1.ffn_up.weight | 0xa5b85620 | 0x7000000 |
| 16 | blk.1.ffn_norm.weight | 0xacb85620 | 0x4000 |
| 17 | blk.1.attn_k.weight | 0xacb89620 | 0x800000 |
| 18 | blk.1.attn_output.weight | 0xad389620 | 0x2000000 |
| 19 | blk.1.attn_q.weight | 0xaf389620 | 0x2000000 |
| 20 | blk.1.attn_v.weight | 0xb1389620 | 0x800000 |
| 21 | blk.10.attn_norm.weight | 0xb1b89620 | 0x4000 |
| 22 | blk.10.ffn_down.weight | 0xb1b8d620 | 0x7000000 |
| 23 | blk.10.ffn_gate.weight | 0xb8b8d620 | 0x7000000 |
| 24 | blk.10.ffn_up.weight | 0xbfb8d620 | 0x7000000 |
| 25 | blk.10.ffn_norm.weight | 0xc6b8d620 | 0x4000 |
| 26 | blk.10.attn_k.weight | 0xc6b91620 | 0x800000 |
| 27 | blk.10.attn_output.weight | 0xc7391620 | 0x2000000 |
| 28 | blk.10.attn_q.weight | 0xc9391620 | 0x2000000 |
| 29 | blk.10.attn_v.weight | 0xcb391620 | 0x800000 |
| 30 | blk.11.attn_norm.weight | 0xcbb91620 | 0x4000 |
| 31 | blk.11.ffn_down.weight | 0xcbb95620 | 0x7000000 |
| 32 | blk.11.ffn_gate.weight | 0xd2b95620 | 0x7000000 |
| 33 | blk.11.ffn_up.weight | 0xd9b95620 | 0x7000000 |
| 34 | blk.11.ffn_norm.weight | 0xe0b95620 | 0x4000 |
| 35 | blk.11.attn_k.weight | 0xe0b99620 | 0x800000 |
| 36 | blk.11.attn_output.weight | 0xe1399620 | 0x2000000 |
| 37 | blk.11.attn_q.weight | 0xe3399620 | 0x2000000 |
| 38 | blk.11.attn_v.weight | 0xe5399620 | 0x800000 |
| 39 | blk.12.attn_norm.weight | 0xe5b99620 | 0x4000 |
| 40 | blk.12.ffn_down.weight | 0xe5b9d620 | 0x7000000 |
| 41 | blk.12.ffn_gate.weight | 0xecb9d620 | 0x7000000 |
| 42 | blk.12.ffn_up.weight | 0xf3b9d620 | 0x7000000 |
| 43 | blk.12.ffn_norm.weight | 0xfab9d620 | 0x4000 |
| 44 | blk.12.attn_k.weight | 0xfaba1620 | 0x800000 |
| 45 | blk.12.attn_output.weight | 0xfb3a1620 | 0x2000000 |
| 46 | blk.12.attn_q.weight | 0xfd3a1620 | 0x2000000 |
| 47 | blk.12.attn_v.weight | 0xff3a1620 | 0x800000 |
| 48 | blk.13.attn_norm.weight | 0xffba1620 | 0x4000 |
| 49 | blk.13.ffn_down.weight | 0xffba5620 | 0x7000000 |
| 50 | blk.13.ffn_gate.weight | 0x106ba5620 | 0x7000000 |
| 51 | blk.13.ffn_up.weight | 0x10dba5620 | 0x7000000 |
| 52 | blk.13.ffn_norm.weight | 0x114ba5620 | 0x4000 |
| 53 | blk.13.attn_k.weight | 0x114ba9620 | 0x800000 |
| 54 | blk.13.attn_output.weight | 0x1153a9620 | 0x2000000 |
| 55 | blk.13.attn_q.weight | 0x1173a9620 | 0x2000000 |
| 56 | blk.13.attn_v.weight | 0x1193a9620 | 0x800000 |
| 57 | blk.14.attn_norm.weight | 0x119ba9620 | 0x4000 |
| 58 | blk.14.ffn_down.weight | 0x119bad620 | 0x7000000 |
| 59 | blk.14.ffn_gate.weight | 0x120bad620 | 0x7000000 |
| 60 | blk.14.ffn_up.weight | 0x127bad620 | 0x7000000 |
| 61 | blk.14.ffn_norm.weight | 0x12ebad620 | 0x4000 |
| 62 | blk.14.attn_k.weight | 0x12ebb1620 | 0x800000 |
| 63 | blk.14.attn_output.weight | 0x12f3b1620 | 0x2000000 |
| 64 | blk.14.attn_q.weight | 0x1313b1620 | 0x2000000 |
| 65 | blk.14.attn_v.weight | 0x1333b1620 | 0x800000 |
| 66 | blk.15.attn_norm.weight | 0x133bb1620 | 0x4000 |
| 67 | blk.15.ffn_down.weight | 0x133bb5620 | 0x7000000 |
| 68 | blk.15.ffn_gate.weight | 0x13abb5620 | 0x7000000 |
| 69 | blk.15.ffn_up.weight | 0x141bb5620 | 0x7000000 |
| 70 | blk.15.ffn_norm.weight | 0x148bb5620 | 0x4000 |
| 71 | blk.15.attn_k.weight | 0x148bb9620 | 0x800000 |
| 72 | blk.15.attn_output.weight | 0x1493b9620 | 0x2000000 |
| 73 | blk.15.attn_q.weight | 0x14b3b9620 | 0x2000000 |
| 74 | blk.15.attn_v.weight | 0x14d3b9620 | 0x800000 |
| 75 | blk.16.attn_norm.weight | 0x14dbb9620 | 0x4000 |
| 76 | blk.16.ffn_down.weight | 0x14dbbd620 | 0x7000000 |
| 77 | blk.16.ffn_gate.weight | 0x154bbd620 | 0x7000000 |
| 78 | blk.16.ffn_up.weight | 0x15bbbd620 | 0x7000000 |
| 79 | blk.16.ffn_norm.weight | 0x162bbd620 | 0x4000 |
| 80 | blk.16.attn_k.weight | 0x162bc1620 | 0x800000 |
| 81 | blk.16.attn_output.weight | 0x1633c1620 | 0x2000000 |
| 82 | blk.16.attn_q.weight | 0x1653c1620 | 0x2000000 |
| 83 | blk.16.attn_v.weight | 0x1673c1620 | 0x800000 |
| 84 | blk.17.attn_norm.weight | 0x167bc1620 | 0x4000 |
| 85 | blk.17.ffn_down.weight | 0x167bc5620 | 0x7000000 |
| 86 | blk.17.ffn_gate.weight | 0x16ebc5620 | 0x7000000 |
| 87 | blk.17.ffn_up.weight | 0x175bc5620 | 0x7000000 |
| 88 | blk.17.ffn_norm.weight | 0x17cbc5620 | 0x4000 |
| 89 | blk.17.attn_k.weight | 0x17cbc9620 | 0x800000 |
| 90 | blk.17.attn_output.weight | 0x17d3c9620 | 0x2000000 |
| 91 | blk.17.attn_q.weight | 0x17f3c9620 | 0x2000000 |
| 92 | blk.17.attn_v.weight | 0x1813c9620 | 0x800000 |
| 93 | blk.18.attn_norm.weight | 0x181bc9620 | 0x4000 |
| 94 | blk.18.ffn_down.weight | 0x181bcd620 | 0x7000000 |
| 95 | blk.18.ffn_gate.weight | 0x188bcd620 | 0x7000000 |
| 96 | blk.18.ffn_up.weight | 0x18fbcd620 | 0x7000000 |
| 97 | blk.18.ffn_norm.weight | 0x196bcd620 | 0x4000 |
| 98 | blk.18.attn_k.weight | 0x196bd1620 | 0x800000 |
| 99 | blk.18.attn_output.weight | 0x1973d1620 | 0x2000000 |
| 100 | blk.18.attn_q.weight | 0x1993d1620 | 0x2000000 |
| 101 | blk.18.attn_v.weight | 0x19b3d1620 | 0x800000 |
| 102 | blk.19.attn_norm.weight | 0x19bbd1620 | 0x4000 |
| 103 | blk.19.ffn_down.weight | 0x19bbd5620 | 0x7000000 |
| 104 | blk.19.ffn_gate.weight | 0x1a2bd5620 | 0x7000000 |
| 105 | blk.19.ffn_up.weight | 0x1a9bd5620 | 0x7000000 |
| 106 | blk.19.ffn_norm.weight | 0x1b0bd5620 | 0x4000 |
| 107 | blk.19.attn_k.weight | 0x1b0bd9620 | 0x800000 |
| 108 | blk.19.attn_output.weight | 0x1b13d9620 | 0x2000000 |
| 109 | blk.19.attn_q.weight | 0x1b33d9620 | 0x2000000 |
| 110 | blk.19.attn_v.weight | 0x1b53d9620 | 0x800000 |
| 111 | blk.2.attn_norm.weight | 0x1b5bd9620 | 0x4000 |
| 112 | blk.2.ffn_down.weight | 0x1b5bdd620 | 0x7000000 |
| 113 | blk.2.ffn_gate.weight | 0x1bcbdd620 | 0x7000000 |
| 114 | blk.2.ffn_up.weight | 0x1c3bdd620 | 0x7000000 |
| 115 | blk.2.ffn_norm.weight | 0x1cabdd620 | 0x4000 |
| 116 | blk.2.attn_k.weight | 0x1cabe1620 | 0x800000 |
| 117 | blk.2.attn_output.weight | 0x1cb3e1620 | 0x2000000 |
| 118 | blk.2.attn_q.weight | 0x1cd3e1620 | 0x2000000 |
| 119 | blk.2.attn_v.weight | 0x1cf3e1620 | 0x800000 |
| 120 | blk.20.attn_norm.weight | 0x1cfbe1620 | 0x4000 |
| 121 | blk.20.ffn_down.weight | 0x1cfbe5620 | 0x7000000 |
| 122 | blk.20.ffn_gate.weight | 0x1d6be5620 | 0x7000000 |
| 123 | blk.20.ffn_up.weight | 0x1ddbe5620 | 0x7000000 |
| 124 | blk.20.ffn_norm.weight | 0x1e4be5620 | 0x4000 |
| 125 | blk.20.attn_k.weight | 0x1e4be9620 | 0x800000 |
| 126 | blk.20.attn_output.weight | 0x1e53e9620 | 0x2000000 |
| 127 | blk.20.attn_q.weight | 0x1e73e9620 | 0x2000000 |
| 128 | blk.20.attn_v.weight | 0x1e93e9620 | 0x800000 |
| 129 | blk.21.attn_norm.weight | 0x1e9be9620 | 0x4000 |
| 130 | blk.21.ffn_down.weight | 0x1e9bed620 | 0x7000000 |
| 131 | blk.21.ffn_gate.weight | 0x1f0bed620 | 0x7000000 |
| 132 | blk.21.ffn_up.weight | 0x1f7bed620 | 0x7000000 |
| 133 | blk.21.ffn_norm.weight | 0x1febed620 | 0x4000 |
| 134 | blk.21.attn_k.weight | 0x1febf1620 | 0x800000 |
| 135 | blk.21.attn_output.weight | 0x1ff3f1620 | 0x2000000 |
| 136 | blk.21.attn_q.weight | 0x2013f1620 | 0x2000000 |
| 137 | blk.21.attn_v.weight | 0x2033f1620 | 0x800000 |
| 138 | blk.22.attn_norm.weight | 0x203bf1620 | 0x4000 |
| 139 | blk.22.ffn_down.weight | 0x203bf5620 | 0x7000000 |
| 140 | blk.22.ffn_gate.weight | 0x20abf5620 | 0x7000000 |
| 141 | blk.22.ffn_up.weight | 0x211bf5620 | 0x7000000 |
| 142 | blk.22.ffn_norm.weight | 0x218bf5620 | 0x4000 |
| 143 | blk.22.attn_k.weight | 0x218bf9620 | 0x800000 |
| 144 | blk.22.attn_output.weight | 0x2193f9620 | 0x2000000 |
| 145 | blk.22.attn_q.weight | 0x21b3f9620 | 0x2000000 |
| 146 | blk.22.attn_v.weight | 0x21d3f9620 | 0x800000 |
| 147 | blk.23.attn_norm.weight | 0x21dbf9620 | 0x4000 |
| 148 | blk.23.ffn_down.weight | 0x21dbfd620 | 0x7000000 |
| 149 | blk.23.ffn_gate.weight | 0x224bfd620 | 0x7000000 |
| 150 | blk.23.ffn_up.weight | 0x22bbfd620 | 0x7000000 |
| 151 | blk.23.ffn_norm.weight | 0x232bfd620 | 0x4000 |
| 152 | blk.23.attn_k.weight | 0x232c01620 | 0x800000 |
| 153 | blk.23.attn_output.weight | 0x233401620 | 0x2000000 |
| 154 | blk.23.attn_q.weight | 0x235401620 | 0x2000000 |
| 155 | blk.23.attn_v.weight | 0x237401620 | 0x800000 |
| 156 | blk.24.attn_norm.weight | 0x237c01620 | 0x4000 |
| 157 | blk.24.ffn_down.weight | 0x237c05620 | 0x7000000 |
| 158 | blk.24.ffn_gate.weight | 0x23ec05620 | 0x7000000 |
| 159 | blk.24.ffn_up.weight | 0x245c05620 | 0x7000000 |
| 160 | blk.24.ffn_norm.weight | 0x24cc05620 | 0x4000 |
| 161 | blk.24.attn_k.weight | 0x24cc09620 | 0x800000 |
| 162 | blk.24.attn_output.weight | 0x24d409620 | 0x2000000 |
| 163 | blk.24.attn_q.weight | 0x24f409620 | 0x2000000 |
| 164 | blk.24.attn_v.weight | 0x251409620 | 0x800000 |
| 165 | blk.25.attn_norm.weight | 0x251c09620 | 0x4000 |
| 166 | blk.25.ffn_down.weight | 0x251c0d620 | 0x7000000 |
| 167 | blk.25.ffn_gate.weight | 0x258c0d620 | 0x7000000 |
| 168 | blk.25.ffn_up.weight | 0x25fc0d620 | 0x7000000 |
| 169 | blk.25.ffn_norm.weight | 0x266c0d620 | 0x4000 |
| 170 | blk.25.attn_k.weight | 0x266c11620 | 0x800000 |
| 171 | blk.25.attn_output.weight | 0x267411620 | 0x2000000 |
| 172 | blk.25.attn_q.weight | 0x269411620 | 0x2000000 |
| 173 | blk.25.attn_v.weight | 0x26b411620 | 0x800000 |
| 174 | blk.26.attn_norm.weight | 0x26bc11620 | 0x4000 |
| 175 | blk.26.ffn_down.weight | 0x26bc15620 | 0x7000000 |
| 176 | blk.26.ffn_gate.weight | 0x272c15620 | 0x7000000 |
| 177 | blk.26.ffn_up.weight | 0x279c15620 | 0x7000000 |
| 178 | blk.26.ffn_norm.weight | 0x280c15620 | 0x4000 |
| 179 | blk.26.attn_k.weight | 0x280c19620 | 0x800000 |
| 180 | blk.26.attn_output.weight | 0x281419620 | 0x2000000 |
| 181 | blk.26.attn_q.weight | 0x283419620 | 0x2000000 |
| 182 | blk.26.attn_v.weight | 0x285419620 | 0x800000 |
| 183 | blk.27.attn_norm.weight | 0x285c19620 | 0x4000 |
| 184 | blk.27.ffn_down.weight | 0x285c1d620 | 0x7000000 |
| 185 | blk.27.ffn_gate.weight | 0x28cc1d620 | 0x7000000 |
| 186 | blk.27.ffn_up.weight | 0x293c1d620 | 0x7000000 |
| 187 | blk.27.ffn_norm.weight | 0x29ac1d620 | 0x4000 |
| 188 | blk.27.attn_k.weight | 0x29ac21620 | 0x800000 |
| 189 | blk.27.attn_output.weight | 0x29b421620 | 0x2000000 |
| 190 | blk.27.attn_q.weight | 0x29d421620 | 0x2000000 |
| 191 | blk.27.attn_v.weight | 0x29f421620 | 0x800000 |
| 192 | blk.28.attn_norm.weight | 0x29fc21620 | 0x4000 |
| 193 | blk.28.ffn_down.weight | 0x29fc25620 | 0x7000000 |
| 194 | blk.28.ffn_gate.weight | 0x2a6c25620 | 0x7000000 |
| 195 | blk.28.ffn_up.weight | 0x2adc25620 | 0x7000000 |
| 196 | blk.28.ffn_norm.weight | 0x2b4c25620 | 0x4000 |
| 197 | blk.28.attn_k.weight | 0x2b4c29620 | 0x800000 |
| 198 | blk.28.attn_output.weight | 0x2b5429620 | 0x2000000 |
| 199 | blk.28.attn_q.weight | 0x2b7429620 | 0x2000000 |
| 200 | blk.28.attn_v.weight | 0x2b9429620 | 0x800000 |
| 201 | blk.29.attn_norm.weight | 0x2b9c29620 | 0x4000 |
| 202 | blk.29.ffn_down.weight | 0x2b9c2d620 | 0x7000000 |
| 203 | blk.29.ffn_gate.weight | 0x2c0c2d620 | 0x7000000 |
| 204 | blk.29.ffn_up.weight | 0x2c7c2d620 | 0x7000000 |
| 205 | blk.29.ffn_norm.weight | 0x2cec2d620 | 0x4000 |
| 206 | blk.29.attn_k.weight | 0x2cec31620 | 0x800000 |
| 207 | blk.29.attn_output.weight | 0x2cf431620 | 0x2000000 |
| 208 | blk.29.attn_q.weight | 0x2d1431620 | 0x2000000 |
| 209 | blk.29.attn_v.weight | 0x2d3431620 | 0x800000 |
| 210 | blk.3.attn_norm.weight | 0x2d3c31620 | 0x4000 |
| 211 | blk.3.ffn_down.weight | 0x2d3c35620 | 0x7000000 |
| 212 | blk.3.ffn_gate.weight | 0x2dac35620 | 0x7000000 |
| 213 | blk.3.ffn_up.weight | 0x2e1c35620 | 0x7000000 |
| 214 | blk.3.ffn_norm.weight | 0x2e8c35620 | 0x4000 |
| 215 | blk.3.attn_k.weight | 0x2e8c39620 | 0x800000 |
| 216 | blk.3.attn_output.weight | 0x2e9439620 | 0x2000000 |
| 217 | blk.3.attn_q.weight | 0x2eb439620 | 0x2000000 |
| 218 | blk.3.attn_v.weight | 0x2ed439620 | 0x800000 |
| 219 | blk.30.attn_norm.weight | 0x2edc39620 | 0x4000 |
| 220 | blk.30.ffn_down.weight | 0x2edc3d620 | 0x7000000 |
| 221 | blk.30.ffn_gate.weight | 0x2f4c3d620 | 0x7000000 |
| 222 | blk.30.ffn_up.weight | 0x2fbc3d620 | 0x7000000 |
| 223 | blk.30.ffn_norm.weight | 0x302c3d620 | 0x4000 |
| 224 | blk.30.attn_k.weight | 0x302c41620 | 0x800000 |
| 225 | blk.30.attn_output.weight | 0x303441620 | 0x2000000 |
| 226 | blk.30.attn_q.weight | 0x305441620 | 0x2000000 |
| 227 | blk.30.attn_v.weight | 0x307441620 | 0x800000 |
| 228 | blk.31.attn_norm.weight | 0x307c41620 | 0x4000 |
| 229 | blk.31.ffn_down.weight | 0x307c45620 | 0x7000000 |
| 230 | blk.31.ffn_gate.weight | 0x30ec45620 | 0x7000000 |
| 231 | blk.31.ffn_up.weight | 0x315c45620 | 0x7000000 |
| 232 | blk.31.ffn_norm.weight | 0x31cc45620 | 0x4000 |
| 233 | blk.31.attn_k.weight | 0x31cc49620 | 0x800000 |
| 234 | blk.31.attn_output.weight | 0x31d449620 | 0x2000000 |
| 235 | blk.31.attn_q.weight | 0x31f449620 | 0x2000000 |
| 236 | blk.31.attn_v.weight | 0x321449620 | 0x800000 |
| 237 | blk.4.attn_norm.weight | 0x321c49620 | 0x4000 |
| 238 | blk.4.ffn_down.weight | 0x321c4d620 | 0x7000000 |
| 239 | blk.4.ffn_gate.weight | 0x328c4d620 | 0x7000000 |
| 240 | blk.4.ffn_up.weight | 0x32fc4d620 | 0x7000000 |
| 241 | blk.4.ffn_norm.weight | 0x336c4d620 | 0x4000 |
| 242 | blk.4.attn_k.weight | 0x336c51620 | 0x800000 |
| 243 | blk.4.attn_output.weight | 0x337451620 | 0x2000000 |
| 244 | blk.4.attn_q.weight | 0x339451620 | 0x2000000 |
| 245 | blk.4.attn_v.weight | 0x33b451620 | 0x800000 |
| 246 | blk.5.attn_norm.weight | 0x33bc51620 | 0x4000 |
| 247 | blk.5.ffn_down.weight | 0x33bc55620 | 0x7000000 |
| 248 | blk.5.ffn_gate.weight | 0x342c55620 | 0x7000000 |
| 249 | blk.5.ffn_up.weight | 0x349c55620 | 0x7000000 |
| 250 | blk.5.ffn_norm.weight | 0x350c55620 | 0x4000 |
| 251 | blk.5.attn_k.weight | 0x350c59620 | 0x800000 |
| 252 | blk.5.attn_output.weight | 0x351459620 | 0x2000000 |
| 253 | blk.5.attn_q.weight | 0x353459620 | 0x2000000 |
| 254 | blk.5.attn_v.weight | 0x355459620 | 0x800000 |
| 255 | blk.6.attn_norm.weight | 0x355c59620 | 0x4000 |
| 256 | blk.6.ffn_down.weight | 0x355c5d620 | 0x7000000 |
| 257 | blk.6.ffn_gate.weight | 0x35cc5d620 | 0x7000000 |
| 258 | blk.6.ffn_up.weight | 0x363c5d620 | 0x7000000 |
| 259 | blk.6.ffn_norm.weight | 0x36ac5d620 | 0x4000 |
| 260 | blk.6.attn_k.weight | 0x36ac61620 | 0x800000 |
| 261 | blk.6.attn_output.weight | 0x36b461620 | 0x2000000 |
| 262 | blk.6.attn_q.weight | 0x36d461620 | 0x2000000 |
| 263 | blk.6.attn_v.weight | 0x36f461620 | 0x800000 |
| 264 | blk.7.attn_norm.weight | 0x36fc61620 | 0x4000 |
| 265 | blk.7.ffn_down.weight | 0x36fc65620 | 0x7000000 |
| 266 | blk.7.ffn_gate.weight | 0x376c65620 | 0x7000000 |
| 267 | blk.7.ffn_up.weight | 0x37dc65620 | 0x7000000 |
| 268 | blk.7.ffn_norm.weight | 0x384c65620 | 0x4000 |
| 269 | blk.7.attn_k.weight | 0x384c69620 | 0x800000 |
| 270 | blk.7.attn_output.weight | 0x385469620 | 0x2000000 |
| 271 | blk.7.attn_q.weight | 0x387469620 | 0x2000000 |
| 272 | blk.7.attn_v.weight | 0x389469620 | 0x800000 |
| 273 | blk.8.attn_norm.weight | 0x389c69620 | 0x4000 |
| 274 | blk.8.ffn_down.weight | 0x389c6d620 | 0x7000000 |
| 275 | blk.8.ffn_gate.weight | 0x390c6d620 | 0x7000000 |
| 276 | blk.8.ffn_up.weight | 0x397c6d620 | 0x7000000 |
| 277 | blk.8.ffn_norm.weight | 0x39ec6d620 | 0x4000 |
| 278 | blk.8.attn_k.weight | 0x39ec71620 | 0x800000 |
| 279 | blk.8.attn_output.weight | 0x39f471620 | 0x2000000 |
| 280 | blk.8.attn_q.weight | 0x3a1471620 | 0x2000000 |
| 281 | blk.8.attn_v.weight | 0x3a3471620 | 0x800000 |
| 282 | blk.9.attn_norm.weight | 0x3a3c71620 | 0x4000 |
| 283 | blk.9.ffn_down.weight | 0x3a3c75620 | 0x7000000 |
| 284 | blk.9.ffn_gate.weight | 0x3aac75620 | 0x7000000 |
| 285 | blk.9.ffn_up.weight | 0x3b1c75620 | 0x7000000 |
| 286 | blk.9.ffn_norm.weight | 0x3b8c75620 | 0x4000 |
| 287 | blk.9.attn_k.weight | 0x3b8c79620 | 0x800000 |
| 288 | blk.9.attn_output.weight | 0x3b9479620 | 0x2000000 |
| 289 | blk.9.attn_q.weight | 0x3bb479620 | 0x2000000 |
| 290 | blk.9.attn_v.weight | 0x3bd479620 | 0x800000 |
| 291 | output_norm.weight | 0x3bdc79620 | 0x4000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 1 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | F16 |
| 2 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | F16 |
| 291 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 3 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 4 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 5 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 6 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 7 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 8 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 9 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 10 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 11 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 12 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 13 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 14 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 15 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 16 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 17 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 18 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 19 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 20 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 21 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 22 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 23 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 24 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 25 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 26 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 27 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 28 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 29 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 30 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 31 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 32 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 33 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 34 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 35 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 36 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 37 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 38 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 39 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 40 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 41 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 42 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 43 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 44 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 45 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 46 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 47 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 48 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 49 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 50 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 51 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 52 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 53 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 54 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 55 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 56 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 57 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 58 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 59 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 60 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 61 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 62 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 63 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 64 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 65 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 66 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 67 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 68 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 69 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 70 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 71 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 72 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 73 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 74 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 75 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 76 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 77 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 78 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 79 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 80 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 81 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 82 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 83 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 84 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 85 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 86 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 87 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 88 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 89 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 90 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 91 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 92 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 93 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 94 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 95 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 96 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 97 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 98 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 99 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 100 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 101 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 102 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 103 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 104 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 105 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 106 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 107 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 108 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 109 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 110 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 111 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 112 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 113 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 114 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 115 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 116 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 117 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 118 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 119 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 120 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 121 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 122 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 123 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 124 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 125 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 126 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 127 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 128 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 129 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 130 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 131 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 132 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 133 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 134 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 135 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 136 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 137 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 138 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 139 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 140 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 141 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 142 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 143 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 144 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 145 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 146 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 147 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 148 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 149 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 150 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 151 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 152 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 153 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 154 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 155 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 156 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 157 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 158 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 159 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 160 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 161 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 162 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 163 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 164 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 165 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 166 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 167 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 168 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 169 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 170 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 171 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 172 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 173 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 174 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 175 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 176 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 177 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 178 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 179 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 180 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 181 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 182 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 183 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 184 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 185 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 186 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 187 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 188 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 189 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 190 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 191 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 192 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 193 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 194 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 195 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 196 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 197 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 198 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 199 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 200 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 201 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 202 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 203 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 204 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 205 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 206 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 207 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 208 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 209 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 210 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 211 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 212 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 213 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 214 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 215 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 216 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 217 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 218 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 219 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 220 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 221 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 222 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 223 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 224 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 225 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 226 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 227 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 228 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 229 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 230 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 231 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 232 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 233 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 234 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 235 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 236 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 237 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 238 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 239 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 240 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 241 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 242 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 243 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 244 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 245 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 246 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 247 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 248 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 249 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 250 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 251 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 252 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 253 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 254 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 255 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 256 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 257 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 258 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 259 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 260 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 261 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 262 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 263 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 264 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 265 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 266 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 267 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 268 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 269 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 270 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 271 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 272 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 273 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 274 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 275 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 276 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 277 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 278 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 279 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 280 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 281 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 282 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 283 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | F16 |
| 284 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 285 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | F16 |
| 286 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 287 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 288 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 289 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | F16 |
| 290 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%

13
scores/Watt-Tool-8B-F16.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 292 tensors from ./Watt-Tool-8B-F16.gguf (version GGUF V3 (latest))
Final result: 40.9333 +/- 1.7967
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 596.70 ms
llama_perf_context_print: prompt eval time = 197375.99 ms / 67195 tokens ( 2.94 ms per token, 340.44 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 198932.74 ms / 67196 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-F16.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 292 tensors from ./Watt-Tool-8B-F16.gguf (version GGUF V3 (latest))
Final result: 32.9333 +/- 1.7172
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 624.82 ms
llama_perf_context_print: prompt eval time = 153527.41 ms / 50072 tokens ( 3.07 ms per token, 326.14 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 155568.93 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-F16.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 292 tensors from ./Watt-Tool-8B-F16.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 74.8000 +/- 1.5864
llama_perf_context_print: load time = 624.64 ms
llama_perf_context_print: prompt eval time = 66689.29 ms / 22192 tokens ( 3.01 ms per token, 332.77 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 67279.36 ms / 22193 tokens
ggml_metal_free: deallocating

982
scores/Watt-Tool-8B-IQ3_M.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-IQ3_M.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 27 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-IQ3\_M.gguf - GGUF Internal File Dump](#watt-tool-8b-iq3_mgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0xd746000 |
| 1 | output_norm.weight | 0xdebf620 | 0x4000 |
| 2 | rope_freqs.weight | 0xdec3620 | 0x100 |
| 3 | token_embd.weight | 0xdec3720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x1b609720 | 0x188000 |
| 5 | blk.0.attn_norm.weight | 0x1b791720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1b795720 | 0x900000 |
| 7 | blk.0.attn_q.weight | 0x1c095720 | 0x620000 |
| 8 | blk.0.attn_v.weight | 0x1c6b5720 | 0x1b8000 |
| 9 | blk.0.ffn_down.weight | 0x1c86d720 | 0x1f80000 |
| 10 | blk.0.ffn_gate.weight | 0x1e7ed720 | 0x1570000 |
| 11 | blk.0.ffn_norm.weight | 0x1fd5d720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x1fd61720 | 0x1570000 |
| 13 | blk.1.attn_k.weight | 0x212d1720 | 0x188000 |
| 14 | blk.1.attn_norm.weight | 0x21459720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x2145d720 | 0x900000 |
| 16 | blk.1.attn_q.weight | 0x21d5d720 | 0x620000 |
| 17 | blk.1.attn_v.weight | 0x2237d720 | 0x1b8000 |
| 18 | blk.1.ffn_down.weight | 0x22535720 | 0x1f80000 |
| 19 | blk.1.ffn_gate.weight | 0x244b5720 | 0x1570000 |
| 20 | blk.1.ffn_norm.weight | 0x25a25720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x25a29720 | 0x1570000 |
| 22 | blk.2.attn_k.weight | 0x26f99720 | 0x188000 |
| 23 | blk.2.attn_norm.weight | 0x27121720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x27125720 | 0x900000 |
| 25 | blk.2.attn_q.weight | 0x27a25720 | 0x620000 |
| 26 | blk.2.attn_v.weight | 0x28045720 | 0x1b8000 |
| 27 | blk.2.ffn_down.weight | 0x281fd720 | 0x1f80000 |
| 28 | blk.2.ffn_gate.weight | 0x2a17d720 | 0x1570000 |
| 29 | blk.2.ffn_norm.weight | 0x2b6ed720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x2b6f1720 | 0x1570000 |
| 31 | blk.3.attn_k.weight | 0x2cc61720 | 0x188000 |
| 32 | blk.3.attn_norm.weight | 0x2cde9720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x2cded720 | 0x900000 |
| 34 | blk.3.attn_q.weight | 0x2d6ed720 | 0x620000 |
| 35 | blk.3.attn_v.weight | 0x2dd0d720 | 0x1b8000 |
| 36 | blk.3.ffn_down.weight | 0x2dec5720 | 0x1f80000 |
| 37 | blk.3.ffn_gate.weight | 0x2fe45720 | 0x1570000 |
| 38 | blk.3.ffn_norm.weight | 0x313b5720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x313b9720 | 0x1570000 |
| 40 | blk.4.attn_k.weight | 0x32929720 | 0x188000 |
| 41 | blk.4.attn_norm.weight | 0x32ab1720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x32ab5720 | 0x900000 |
| 43 | blk.4.attn_q.weight | 0x333b5720 | 0x620000 |
| 44 | blk.4.attn_v.weight | 0x339d5720 | 0x1b8000 |
| 45 | blk.4.ffn_down.weight | 0x33b8d720 | 0x1f80000 |
| 46 | blk.4.ffn_gate.weight | 0x35b0d720 | 0x1570000 |
| 47 | blk.4.ffn_norm.weight | 0x3707d720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x37081720 | 0x1570000 |
| 49 | blk.5.attn_k.weight | 0x385f1720 | 0x188000 |
| 50 | blk.5.attn_norm.weight | 0x38779720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x3877d720 | 0x900000 |
| 52 | blk.5.attn_q.weight | 0x3907d720 | 0x620000 |
| 53 | blk.5.attn_v.weight | 0x3969d720 | 0x1b8000 |
| 54 | blk.5.ffn_down.weight | 0x39855720 | 0x1f80000 |
| 55 | blk.5.ffn_gate.weight | 0x3b7d5720 | 0x1570000 |
| 56 | blk.5.ffn_norm.weight | 0x3cd45720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x3cd49720 | 0x1570000 |
| 58 | blk.6.attn_k.weight | 0x3e2b9720 | 0x188000 |
| 59 | blk.6.attn_norm.weight | 0x3e441720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x3e445720 | 0x900000 |
| 61 | blk.6.attn_q.weight | 0x3ed45720 | 0x620000 |
| 62 | blk.6.attn_v.weight | 0x3f365720 | 0x1b8000 |
| 63 | blk.6.ffn_down.weight | 0x3f51d720 | 0x1f80000 |
| 64 | blk.6.ffn_gate.weight | 0x4149d720 | 0x1570000 |
| 65 | blk.6.ffn_norm.weight | 0x42a0d720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x42a11720 | 0x1570000 |
| 67 | blk.7.attn_k.weight | 0x43f81720 | 0x188000 |
| 68 | blk.7.attn_norm.weight | 0x44109720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x4410d720 | 0x900000 |
| 70 | blk.7.attn_q.weight | 0x44a0d720 | 0x620000 |
| 71 | blk.7.attn_v.weight | 0x4502d720 | 0x1b8000 |
| 72 | blk.7.ffn_down.weight | 0x451e5720 | 0x1f80000 |
| 73 | blk.7.ffn_gate.weight | 0x47165720 | 0x1570000 |
| 74 | blk.7.ffn_norm.weight | 0x486d5720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x486d9720 | 0x1570000 |
| 76 | blk.8.attn_k.weight | 0x49c49720 | 0x188000 |
| 77 | blk.8.attn_norm.weight | 0x49dd1720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x49dd5720 | 0x900000 |
| 79 | blk.8.attn_q.weight | 0x4a6d5720 | 0x620000 |
| 80 | blk.8.attn_v.weight | 0x4acf5720 | 0x1b8000 |
| 81 | blk.8.ffn_down.weight | 0x4aead720 | 0x1f80000 |
| 82 | blk.8.ffn_gate.weight | 0x4ce2d720 | 0x1570000 |
| 83 | blk.8.ffn_norm.weight | 0x4e39d720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x4e3a1720 | 0x1570000 |
| 85 | blk.9.attn_k.weight | 0x4f911720 | 0x188000 |
| 86 | blk.9.attn_norm.weight | 0x4fa99720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x4fa9d720 | 0x900000 |
| 88 | blk.9.attn_q.weight | 0x5039d720 | 0x620000 |
| 89 | blk.9.attn_v.weight | 0x509bd720 | 0x1b8000 |
| 90 | blk.9.ffn_down.weight | 0x50b75720 | 0x1f80000 |
| 91 | blk.9.ffn_gate.weight | 0x52af5720 | 0x1570000 |
| 92 | blk.9.ffn_norm.weight | 0x54065720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x54069720 | 0x1570000 |
| 94 | blk.10.attn_k.weight | 0x555d9720 | 0x188000 |
| 95 | blk.10.attn_norm.weight | 0x55761720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x55765720 | 0x900000 |
| 97 | blk.10.attn_q.weight | 0x56065720 | 0x620000 |
| 98 | blk.10.attn_v.weight | 0x56685720 | 0x1b8000 |
| 99 | blk.10.ffn_down.weight | 0x5683d720 | 0x1f80000 |
| 100 | blk.10.ffn_gate.weight | 0x587bd720 | 0x1570000 |
| 101 | blk.10.ffn_norm.weight | 0x59d2d720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x59d31720 | 0x1570000 |
| 103 | blk.11.attn_k.weight | 0x5b2a1720 | 0x188000 |
| 104 | blk.11.attn_norm.weight | 0x5b429720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x5b42d720 | 0x900000 |
| 106 | blk.11.attn_q.weight | 0x5bd2d720 | 0x620000 |
| 107 | blk.11.attn_v.weight | 0x5c34d720 | 0x1b8000 |
| 108 | blk.11.ffn_down.weight | 0x5c505720 | 0x1f80000 |
| 109 | blk.11.ffn_gate.weight | 0x5e485720 | 0x1570000 |
| 110 | blk.11.ffn_norm.weight | 0x5f9f5720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x5f9f9720 | 0x1570000 |
| 112 | blk.12.attn_k.weight | 0x60f69720 | 0x188000 |
| 113 | blk.12.attn_norm.weight | 0x610f1720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x610f5720 | 0x900000 |
| 115 | blk.12.attn_q.weight | 0x619f5720 | 0x620000 |
| 116 | blk.12.attn_v.weight | 0x62015720 | 0x1b8000 |
| 117 | blk.12.ffn_down.weight | 0x621cd720 | 0x1f80000 |
| 118 | blk.12.ffn_gate.weight | 0x6414d720 | 0x1570000 |
| 119 | blk.12.ffn_norm.weight | 0x656bd720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x656c1720 | 0x1570000 |
| 121 | blk.13.attn_k.weight | 0x66c31720 | 0x1b8000 |
| 122 | blk.13.attn_norm.weight | 0x66de9720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x66ded720 | 0x900000 |
| 124 | blk.13.attn_q.weight | 0x676ed720 | 0x6e0000 |
| 125 | blk.13.attn_v.weight | 0x67dcd720 | 0x240000 |
| 126 | blk.13.ffn_down.weight | 0x6800d720 | 0x1f80000 |
| 127 | blk.13.ffn_gate.weight | 0x69f8d720 | 0x1570000 |
| 128 | blk.13.ffn_norm.weight | 0x6b4fd720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x6b501720 | 0x1570000 |
| 130 | blk.14.attn_k.weight | 0x6ca71720 | 0x1b8000 |
| 131 | blk.14.attn_norm.weight | 0x6cc29720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x6cc2d720 | 0x900000 |
| 133 | blk.14.attn_q.weight | 0x6d52d720 | 0x6e0000 |
| 134 | blk.14.attn_v.weight | 0x6dc0d720 | 0x240000 |
| 135 | blk.14.ffn_down.weight | 0x6de4d720 | 0x1f80000 |
| 136 | blk.14.ffn_gate.weight | 0x6fdcd720 | 0x1570000 |
| 137 | blk.14.ffn_norm.weight | 0x7133d720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x71341720 | 0x1570000 |
| 139 | blk.15.attn_k.weight | 0x728b1720 | 0x188000 |
| 140 | blk.15.attn_norm.weight | 0x72a39720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x72a3d720 | 0x900000 |
| 142 | blk.15.attn_q.weight | 0x7333d720 | 0x620000 |
| 143 | blk.15.attn_v.weight | 0x7395d720 | 0x1b8000 |
| 144 | blk.15.ffn_down.weight | 0x73b15720 | 0x1f80000 |
| 145 | blk.15.ffn_gate.weight | 0x75a95720 | 0x1570000 |
| 146 | blk.15.ffn_norm.weight | 0x77005720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x77009720 | 0x1570000 |
| 148 | blk.16.attn_k.weight | 0x78579720 | 0x1b8000 |
| 149 | blk.16.attn_norm.weight | 0x78731720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x78735720 | 0x900000 |
| 151 | blk.16.attn_q.weight | 0x79035720 | 0x6e0000 |
| 152 | blk.16.attn_v.weight | 0x79715720 | 0x240000 |
| 153 | blk.16.ffn_down.weight | 0x79955720 | 0x1f80000 |
| 154 | blk.16.ffn_gate.weight | 0x7b8d5720 | 0x1810000 |
| 155 | blk.16.ffn_norm.weight | 0x7d0e5720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x7d0e9720 | 0x1810000 |
| 157 | blk.17.attn_k.weight | 0x7e8f9720 | 0x188000 |
| 158 | blk.17.attn_norm.weight | 0x7ea81720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x7ea85720 | 0x900000 |
| 160 | blk.17.attn_q.weight | 0x7f385720 | 0x620000 |
| 161 | blk.17.attn_v.weight | 0x7f9a5720 | 0x1b8000 |
| 162 | blk.17.ffn_down.weight | 0x7fb5d720 | 0x1f80000 |
| 163 | blk.17.ffn_gate.weight | 0x81add720 | 0x1810000 |
| 164 | blk.17.ffn_norm.weight | 0x832ed720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x832f1720 | 0x1810000 |
| 166 | blk.18.attn_k.weight | 0x84b01720 | 0x1b8000 |
| 167 | blk.18.attn_norm.weight | 0x84cb9720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x84cbd720 | 0x900000 |
| 169 | blk.18.attn_q.weight | 0x855bd720 | 0x6e0000 |
| 170 | blk.18.attn_v.weight | 0x85c9d720 | 0x240000 |
| 171 | blk.18.ffn_down.weight | 0x85edd720 | 0x1f80000 |
| 172 | blk.18.ffn_gate.weight | 0x87e5d720 | 0x1810000 |
| 173 | blk.18.ffn_norm.weight | 0x8966d720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x89671720 | 0x1810000 |
| 175 | blk.19.attn_k.weight | 0x8ae81720 | 0x1b8000 |
| 176 | blk.19.attn_norm.weight | 0x8b039720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x8b03d720 | 0x900000 |
| 178 | blk.19.attn_q.weight | 0x8b93d720 | 0x6e0000 |
| 179 | blk.19.attn_v.weight | 0x8c01d720 | 0x240000 |
| 180 | blk.19.ffn_down.weight | 0x8c25d720 | 0x1f80000 |
| 181 | blk.19.ffn_gate.weight | 0x8e1dd720 | 0x1810000 |
| 182 | blk.19.ffn_norm.weight | 0x8f9ed720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0x8f9f1720 | 0x1810000 |
| 184 | blk.20.attn_k.weight | 0x91201720 | 0x1b8000 |
| 185 | blk.20.attn_norm.weight | 0x913b9720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0x913bd720 | 0x900000 |
| 187 | blk.20.attn_q.weight | 0x91cbd720 | 0x6e0000 |
| 188 | blk.20.attn_v.weight | 0x9239d720 | 0x240000 |
| 189 | blk.20.ffn_down.weight | 0x925dd720 | 0x1f80000 |
| 190 | blk.20.ffn_gate.weight | 0x9455d720 | 0x1810000 |
| 191 | blk.20.ffn_norm.weight | 0x95d6d720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x95d71720 | 0x1810000 |
| 193 | blk.21.attn_k.weight | 0x97581720 | 0x1b8000 |
| 194 | blk.21.attn_norm.weight | 0x97739720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x9773d720 | 0x900000 |
| 196 | blk.21.attn_q.weight | 0x9803d720 | 0x6e0000 |
| 197 | blk.21.attn_v.weight | 0x9871d720 | 0x240000 |
| 198 | blk.21.ffn_down.weight | 0x9895d720 | 0x1f80000 |
| 199 | blk.21.ffn_gate.weight | 0x9a8dd720 | 0x1810000 |
| 200 | blk.21.ffn_norm.weight | 0x9c0ed720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x9c0f1720 | 0x1810000 |
| 202 | blk.22.attn_k.weight | 0x9d901720 | 0x1b8000 |
| 203 | blk.22.attn_norm.weight | 0x9dab9720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x9dabd720 | 0x900000 |
| 205 | blk.22.attn_q.weight | 0x9e3bd720 | 0x6e0000 |
| 206 | blk.22.attn_v.weight | 0x9ea9d720 | 0x240000 |
| 207 | blk.22.ffn_down.weight | 0x9ecdd720 | 0x1f80000 |
| 208 | blk.22.ffn_gate.weight | 0xa0c5d720 | 0x1810000 |
| 209 | blk.22.ffn_norm.weight | 0xa246d720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xa2471720 | 0x1810000 |
| 211 | blk.23.attn_k.weight | 0xa3c81720 | 0x1b8000 |
| 212 | blk.23.attn_norm.weight | 0xa3e39720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xa3e3d720 | 0x900000 |
| 214 | blk.23.attn_q.weight | 0xa473d720 | 0x6e0000 |
| 215 | blk.23.attn_v.weight | 0xa4e1d720 | 0x240000 |
| 216 | blk.23.ffn_down.weight | 0xa505d720 | 0x1f80000 |
| 217 | blk.23.ffn_gate.weight | 0xa6fdd720 | 0x1810000 |
| 218 | blk.23.ffn_norm.weight | 0xa87ed720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xa87f1720 | 0x1810000 |
| 220 | blk.24.attn_k.weight | 0xaa001720 | 0x1b8000 |
| 221 | blk.24.attn_norm.weight | 0xaa1b9720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xaa1bd720 | 0x900000 |
| 223 | blk.24.attn_q.weight | 0xaaabd720 | 0x6e0000 |
| 224 | blk.24.attn_v.weight | 0xab19d720 | 0x240000 |
| 225 | blk.24.ffn_down.weight | 0xab3dd720 | 0x1f80000 |
| 226 | blk.24.ffn_gate.weight | 0xad35d720 | 0x1810000 |
| 227 | blk.24.ffn_norm.weight | 0xaeb6d720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xaeb71720 | 0x1810000 |
| 229 | blk.25.attn_k.weight | 0xb0381720 | 0x1b8000 |
| 230 | blk.25.attn_norm.weight | 0xb0539720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xb053d720 | 0x900000 |
| 232 | blk.25.attn_q.weight | 0xb0e3d720 | 0x6e0000 |
| 233 | blk.25.attn_v.weight | 0xb151d720 | 0x240000 |
| 234 | blk.25.ffn_down.weight | 0xb175d720 | 0x1f80000 |
| 235 | blk.25.ffn_gate.weight | 0xb36dd720 | 0x1810000 |
| 236 | blk.25.ffn_norm.weight | 0xb4eed720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xb4ef1720 | 0x1810000 |
| 238 | blk.26.attn_k.weight | 0xb6701720 | 0x1b8000 |
| 239 | blk.26.attn_norm.weight | 0xb68b9720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xb68bd720 | 0x900000 |
| 241 | blk.26.attn_q.weight | 0xb71bd720 | 0x6e0000 |
| 242 | blk.26.attn_v.weight | 0xb789d720 | 0x240000 |
| 243 | blk.26.ffn_down.weight | 0xb7add720 | 0x1f80000 |
| 244 | blk.26.ffn_gate.weight | 0xb9a5d720 | 0x1810000 |
| 245 | blk.26.ffn_norm.weight | 0xbb26d720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xbb271720 | 0x1810000 |
| 247 | blk.27.attn_k.weight | 0xbca81720 | 0x1b8000 |
| 248 | blk.27.attn_norm.weight | 0xbcc39720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xbcc3d720 | 0x900000 |
| 250 | blk.27.attn_q.weight | 0xbd53d720 | 0x6e0000 |
| 251 | blk.27.attn_v.weight | 0xbdc1d720 | 0x240000 |
| 252 | blk.27.ffn_down.weight | 0xbde5d720 | 0x1f80000 |
| 253 | blk.27.ffn_gate.weight | 0xbfddd720 | 0x1810000 |
| 254 | blk.27.ffn_norm.weight | 0xc15ed720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xc15f1720 | 0x1810000 |
| 256 | blk.28.attn_k.weight | 0xc2e01720 | 0x1b8000 |
| 257 | blk.28.attn_norm.weight | 0xc2fb9720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xc2fbd720 | 0x900000 |
| 259 | blk.28.attn_q.weight | 0xc38bd720 | 0x6e0000 |
| 260 | blk.28.attn_v.weight | 0xc3f9d720 | 0x240000 |
| 261 | blk.28.ffn_down.weight | 0xc41dd720 | 0x1f80000 |
| 262 | blk.28.ffn_gate.weight | 0xc615d720 | 0x1810000 |
| 263 | blk.28.ffn_norm.weight | 0xc796d720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xc7971720 | 0x1810000 |
| 265 | blk.29.attn_k.weight | 0xc9181720 | 0x1b8000 |
| 266 | blk.29.attn_norm.weight | 0xc9339720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xc933d720 | 0x900000 |
| 268 | blk.29.attn_q.weight | 0xc9c3d720 | 0x6e0000 |
| 269 | blk.29.attn_v.weight | 0xca31d720 | 0x240000 |
| 270 | blk.29.ffn_down.weight | 0xca55d720 | 0x1f80000 |
| 271 | blk.29.ffn_gate.weight | 0xcc4dd720 | 0x1810000 |
| 272 | blk.29.ffn_norm.weight | 0xcdced720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xcdcf1720 | 0x1810000 |
| 274 | blk.30.attn_k.weight | 0xcf501720 | 0x1b8000 |
| 275 | blk.30.attn_norm.weight | 0xcf6b9720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xcf6bd720 | 0x900000 |
| 277 | blk.30.attn_q.weight | 0xcffbd720 | 0x6e0000 |
| 278 | blk.30.attn_v.weight | 0xd069d720 | 0x240000 |
| 279 | blk.30.ffn_down.weight | 0xd08dd720 | 0x1f80000 |
| 280 | blk.30.ffn_gate.weight | 0xd285d720 | 0x1810000 |
| 281 | blk.30.ffn_norm.weight | 0xd406d720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xd4071720 | 0x1810000 |
| 283 | blk.31.attn_k.weight | 0xd5881720 | 0x188000 |
| 284 | blk.31.attn_norm.weight | 0xd5a09720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xd5a0d720 | 0x900000 |
| 286 | blk.31.attn_q.weight | 0xd630d720 | 0x620000 |
| 287 | blk.31.attn_v.weight | 0xd692d720 | 0x1b8000 |
| 288 | blk.31.ffn_down.weight | 0xd6ae5720 | 0x1f80000 |
| 289 | blk.31.ffn_gate.weight | 0xd8a65720 | 0x1810000 |
| 290 | blk.31.ffn_norm.weight | 0xda275720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0xda279720 | 0x1810000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:------|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_S |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_S |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-IQ3_S.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-IQ3_S.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 26 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-IQ3\_S.gguf - GGUF Internal File Dump](#watt-tool-8b-iq3_sgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0xbfca000 |
| 1 | output_norm.weight | 0xc743620 | 0x4000 |
| 2 | rope_freqs.weight | 0xc747620 | 0x100 |
| 3 | token_embd.weight | 0xc747720 | 0xbfca000 |
| 4 | blk.0.attn_k.weight | 0x18711720 | 0x188000 |
| 5 | blk.0.attn_norm.weight | 0x18899720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1889d720 | 0x6e0000 |
| 7 | blk.0.attn_q.weight | 0x18f7d720 | 0x620000 |
| 8 | blk.0.attn_v.weight | 0x1959d720 | 0x1b8000 |
| 9 | blk.0.ffn_down.weight | 0x19755720 | 0x1810000 |
| 10 | blk.0.ffn_gate.weight | 0x1af65720 | 0x1570000 |
| 11 | blk.0.ffn_norm.weight | 0x1c4d5720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x1c4d9720 | 0x1570000 |
| 13 | blk.1.attn_k.weight | 0x1da49720 | 0x188000 |
| 14 | blk.1.attn_norm.weight | 0x1dbd1720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x1dbd5720 | 0x6e0000 |
| 16 | blk.1.attn_q.weight | 0x1e2b5720 | 0x620000 |
| 17 | blk.1.attn_v.weight | 0x1e8d5720 | 0x1b8000 |
| 18 | blk.1.ffn_down.weight | 0x1ea8d720 | 0x1f80000 |
| 19 | blk.1.ffn_gate.weight | 0x20a0d720 | 0x1570000 |
| 20 | blk.1.ffn_norm.weight | 0x21f7d720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x21f81720 | 0x1570000 |
| 22 | blk.2.attn_k.weight | 0x234f1720 | 0x188000 |
| 23 | blk.2.attn_norm.weight | 0x23679720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x2367d720 | 0x6e0000 |
| 25 | blk.2.attn_q.weight | 0x23d5d720 | 0x620000 |
| 26 | blk.2.attn_v.weight | 0x2437d720 | 0x1b8000 |
| 27 | blk.2.ffn_down.weight | 0x24535720 | 0x1810000 |
| 28 | blk.2.ffn_gate.weight | 0x25d45720 | 0x1570000 |
| 29 | blk.2.ffn_norm.weight | 0x272b5720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x272b9720 | 0x1570000 |
| 31 | blk.3.attn_k.weight | 0x28829720 | 0x188000 |
| 32 | blk.3.attn_norm.weight | 0x289b1720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x289b5720 | 0x6e0000 |
| 34 | blk.3.attn_q.weight | 0x29095720 | 0x620000 |
| 35 | blk.3.attn_v.weight | 0x296b5720 | 0x1b8000 |
| 36 | blk.3.ffn_down.weight | 0x2986d720 | 0x1810000 |
| 37 | blk.3.ffn_gate.weight | 0x2b07d720 | 0x1570000 |
| 38 | blk.3.ffn_norm.weight | 0x2c5ed720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x2c5f1720 | 0x1570000 |
| 40 | blk.4.attn_k.weight | 0x2db61720 | 0x188000 |
| 41 | blk.4.attn_norm.weight | 0x2dce9720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x2dced720 | 0x6e0000 |
| 43 | blk.4.attn_q.weight | 0x2e3cd720 | 0x620000 |
| 44 | blk.4.attn_v.weight | 0x2e9ed720 | 0x1b8000 |
| 45 | blk.4.ffn_down.weight | 0x2eba5720 | 0x1810000 |
| 46 | blk.4.ffn_gate.weight | 0x303b5720 | 0x1570000 |
| 47 | blk.4.ffn_norm.weight | 0x31925720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x31929720 | 0x1570000 |
| 49 | blk.5.attn_k.weight | 0x32e99720 | 0x188000 |
| 50 | blk.5.attn_norm.weight | 0x33021720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x33025720 | 0x6e0000 |
| 52 | blk.5.attn_q.weight | 0x33705720 | 0x620000 |
| 53 | blk.5.attn_v.weight | 0x33d25720 | 0x1b8000 |
| 54 | blk.5.ffn_down.weight | 0x33edd720 | 0x1810000 |
| 55 | blk.5.ffn_gate.weight | 0x356ed720 | 0x1570000 |
| 56 | blk.5.ffn_norm.weight | 0x36c5d720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x36c61720 | 0x1570000 |
| 58 | blk.6.attn_k.weight | 0x381d1720 | 0x188000 |
| 59 | blk.6.attn_norm.weight | 0x38359720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x3835d720 | 0x6e0000 |
| 61 | blk.6.attn_q.weight | 0x38a3d720 | 0x620000 |
| 62 | blk.6.attn_v.weight | 0x3905d720 | 0x1b8000 |
| 63 | blk.6.ffn_down.weight | 0x39215720 | 0x1810000 |
| 64 | blk.6.ffn_gate.weight | 0x3aa25720 | 0x1570000 |
| 65 | blk.6.ffn_norm.weight | 0x3bf95720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x3bf99720 | 0x1570000 |
| 67 | blk.7.attn_k.weight | 0x3d509720 | 0x188000 |
| 68 | blk.7.attn_norm.weight | 0x3d691720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x3d695720 | 0x6e0000 |
| 70 | blk.7.attn_q.weight | 0x3dd75720 | 0x620000 |
| 71 | blk.7.attn_v.weight | 0x3e395720 | 0x1b8000 |
| 72 | blk.7.ffn_down.weight | 0x3e54d720 | 0x1810000 |
| 73 | blk.7.ffn_gate.weight | 0x3fd5d720 | 0x1570000 |
| 74 | blk.7.ffn_norm.weight | 0x412cd720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x412d1720 | 0x1570000 |
| 76 | blk.8.attn_k.weight | 0x42841720 | 0x188000 |
| 77 | blk.8.attn_norm.weight | 0x429c9720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x429cd720 | 0x6e0000 |
| 79 | blk.8.attn_q.weight | 0x430ad720 | 0x620000 |
| 80 | blk.8.attn_v.weight | 0x436cd720 | 0x1b8000 |
| 81 | blk.8.ffn_down.weight | 0x43885720 | 0x1810000 |
| 82 | blk.8.ffn_gate.weight | 0x45095720 | 0x1570000 |
| 83 | blk.8.ffn_norm.weight | 0x46605720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x46609720 | 0x1570000 |
| 85 | blk.9.attn_k.weight | 0x47b79720 | 0x188000 |
| 86 | blk.9.attn_norm.weight | 0x47d01720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x47d05720 | 0x6e0000 |
| 88 | blk.9.attn_q.weight | 0x483e5720 | 0x620000 |
| 89 | blk.9.attn_v.weight | 0x48a05720 | 0x1b8000 |
| 90 | blk.9.ffn_down.weight | 0x48bbd720 | 0x1810000 |
| 91 | blk.9.ffn_gate.weight | 0x4a3cd720 | 0x1570000 |
| 92 | blk.9.ffn_norm.weight | 0x4b93d720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x4b941720 | 0x1570000 |
| 94 | blk.10.attn_k.weight | 0x4ceb1720 | 0x188000 |
| 95 | blk.10.attn_norm.weight | 0x4d039720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x4d03d720 | 0x6e0000 |
| 97 | blk.10.attn_q.weight | 0x4d71d720 | 0x620000 |
| 98 | blk.10.attn_v.weight | 0x4dd3d720 | 0x1b8000 |
| 99 | blk.10.ffn_down.weight | 0x4def5720 | 0x1810000 |
| 100 | blk.10.ffn_gate.weight | 0x4f705720 | 0x1570000 |
| 101 | blk.10.ffn_norm.weight | 0x50c75720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x50c79720 | 0x1570000 |
| 103 | blk.11.attn_k.weight | 0x521e9720 | 0x188000 |
| 104 | blk.11.attn_norm.weight | 0x52371720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x52375720 | 0x6e0000 |
| 106 | blk.11.attn_q.weight | 0x52a55720 | 0x620000 |
| 107 | blk.11.attn_v.weight | 0x53075720 | 0x1b8000 |
| 108 | blk.11.ffn_down.weight | 0x5322d720 | 0x1810000 |
| 109 | blk.11.ffn_gate.weight | 0x54a3d720 | 0x1570000 |
| 110 | blk.11.ffn_norm.weight | 0x55fad720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x55fb1720 | 0x1570000 |
| 112 | blk.12.attn_k.weight | 0x57521720 | 0x188000 |
| 113 | blk.12.attn_norm.weight | 0x576a9720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x576ad720 | 0x6e0000 |
| 115 | blk.12.attn_q.weight | 0x57d8d720 | 0x620000 |
| 116 | blk.12.attn_v.weight | 0x583ad720 | 0x1b8000 |
| 117 | blk.12.ffn_down.weight | 0x58565720 | 0x1810000 |
| 118 | blk.12.ffn_gate.weight | 0x59d75720 | 0x1570000 |
| 119 | blk.12.ffn_norm.weight | 0x5b2e5720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x5b2e9720 | 0x1570000 |
| 121 | blk.13.attn_k.weight | 0x5c859720 | 0x1b8000 |
| 122 | blk.13.attn_norm.weight | 0x5ca11720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x5ca15720 | 0x6e0000 |
| 124 | blk.13.attn_q.weight | 0x5d0f5720 | 0x6e0000 |
| 125 | blk.13.attn_v.weight | 0x5d7d5720 | 0x1b8000 |
| 126 | blk.13.ffn_down.weight | 0x5d98d720 | 0x1810000 |
| 127 | blk.13.ffn_gate.weight | 0x5f19d720 | 0x1570000 |
| 128 | blk.13.ffn_norm.weight | 0x6070d720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x60711720 | 0x1570000 |
| 130 | blk.14.attn_k.weight | 0x61c81720 | 0x1b8000 |
| 131 | blk.14.attn_norm.weight | 0x61e39720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x61e3d720 | 0x6e0000 |
| 133 | blk.14.attn_q.weight | 0x6251d720 | 0x6e0000 |
| 134 | blk.14.attn_v.weight | 0x62bfd720 | 0x1b8000 |
| 135 | blk.14.ffn_down.weight | 0x62db5720 | 0x1810000 |
| 136 | blk.14.ffn_gate.weight | 0x645c5720 | 0x1570000 |
| 137 | blk.14.ffn_norm.weight | 0x65b35720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x65b39720 | 0x1570000 |
| 139 | blk.15.attn_k.weight | 0x670a9720 | 0x188000 |
| 140 | blk.15.attn_norm.weight | 0x67231720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x67235720 | 0x6e0000 |
| 142 | blk.15.attn_q.weight | 0x67915720 | 0x620000 |
| 143 | blk.15.attn_v.weight | 0x67f35720 | 0x1b8000 |
| 144 | blk.15.ffn_down.weight | 0x680ed720 | 0x1810000 |
| 145 | blk.15.ffn_gate.weight | 0x698fd720 | 0x1570000 |
| 146 | blk.15.ffn_norm.weight | 0x6ae6d720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x6ae71720 | 0x1570000 |
| 148 | blk.16.attn_k.weight | 0x6c3e1720 | 0x1b8000 |
| 149 | blk.16.attn_norm.weight | 0x6c599720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x6c59d720 | 0x6e0000 |
| 151 | blk.16.attn_q.weight | 0x6cc7d720 | 0x6e0000 |
| 152 | blk.16.attn_v.weight | 0x6d35d720 | 0x1b8000 |
| 153 | blk.16.ffn_down.weight | 0x6d515720 | 0x1810000 |
| 154 | blk.16.ffn_gate.weight | 0x6ed25720 | 0x1810000 |
| 155 | blk.16.ffn_norm.weight | 0x70535720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x70539720 | 0x1810000 |
| 157 | blk.17.attn_k.weight | 0x71d49720 | 0x188000 |
| 158 | blk.17.attn_norm.weight | 0x71ed1720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x71ed5720 | 0x6e0000 |
| 160 | blk.17.attn_q.weight | 0x725b5720 | 0x620000 |
| 161 | blk.17.attn_v.weight | 0x72bd5720 | 0x1b8000 |
| 162 | blk.17.ffn_down.weight | 0x72d8d720 | 0x1f80000 |
| 163 | blk.17.ffn_gate.weight | 0x74d0d720 | 0x1810000 |
| 164 | blk.17.ffn_norm.weight | 0x7651d720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x76521720 | 0x1810000 |
| 166 | blk.18.attn_k.weight | 0x77d31720 | 0x1b8000 |
| 167 | blk.18.attn_norm.weight | 0x77ee9720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x77eed720 | 0x6e0000 |
| 169 | blk.18.attn_q.weight | 0x785cd720 | 0x6e0000 |
| 170 | blk.18.attn_v.weight | 0x78cad720 | 0x1b8000 |
| 171 | blk.18.ffn_down.weight | 0x78e65720 | 0x1f80000 |
| 172 | blk.18.ffn_gate.weight | 0x7ade5720 | 0x1810000 |
| 173 | blk.18.ffn_norm.weight | 0x7c5f5720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x7c5f9720 | 0x1810000 |
| 175 | blk.19.attn_k.weight | 0x7de09720 | 0x1b8000 |
| 176 | blk.19.attn_norm.weight | 0x7dfc1720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x7dfc5720 | 0x6e0000 |
| 178 | blk.19.attn_q.weight | 0x7e6a5720 | 0x6e0000 |
| 179 | blk.19.attn_v.weight | 0x7ed85720 | 0x1b8000 |
| 180 | blk.19.ffn_down.weight | 0x7ef3d720 | 0x1f80000 |
| 181 | blk.19.ffn_gate.weight | 0x80ebd720 | 0x1810000 |
| 182 | blk.19.ffn_norm.weight | 0x826cd720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0x826d1720 | 0x1810000 |
| 184 | blk.20.attn_k.weight | 0x83ee1720 | 0x1b8000 |
| 185 | blk.20.attn_norm.weight | 0x84099720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0x8409d720 | 0x6e0000 |
| 187 | blk.20.attn_q.weight | 0x8477d720 | 0x6e0000 |
| 188 | blk.20.attn_v.weight | 0x84e5d720 | 0x1b8000 |
| 189 | blk.20.ffn_down.weight | 0x85015720 | 0x1f80000 |
| 190 | blk.20.ffn_gate.weight | 0x86f95720 | 0x1810000 |
| 191 | blk.20.ffn_norm.weight | 0x887a5720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x887a9720 | 0x1810000 |
| 193 | blk.21.attn_k.weight | 0x89fb9720 | 0x1b8000 |
| 194 | blk.21.attn_norm.weight | 0x8a171720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x8a175720 | 0x6e0000 |
| 196 | blk.21.attn_q.weight | 0x8a855720 | 0x6e0000 |
| 197 | blk.21.attn_v.weight | 0x8af35720 | 0x1b8000 |
| 198 | blk.21.ffn_down.weight | 0x8b0ed720 | 0x1f80000 |
| 199 | blk.21.ffn_gate.weight | 0x8d06d720 | 0x1810000 |
| 200 | blk.21.ffn_norm.weight | 0x8e87d720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x8e881720 | 0x1810000 |
| 202 | blk.22.attn_k.weight | 0x90091720 | 0x1b8000 |
| 203 | blk.22.attn_norm.weight | 0x90249720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x9024d720 | 0x6e0000 |
| 205 | blk.22.attn_q.weight | 0x9092d720 | 0x6e0000 |
| 206 | blk.22.attn_v.weight | 0x9100d720 | 0x1b8000 |
| 207 | blk.22.ffn_down.weight | 0x911c5720 | 0x1f80000 |
| 208 | blk.22.ffn_gate.weight | 0x93145720 | 0x1810000 |
| 209 | blk.22.ffn_norm.weight | 0x94955720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0x94959720 | 0x1810000 |
| 211 | blk.23.attn_k.weight | 0x96169720 | 0x1b8000 |
| 212 | blk.23.attn_norm.weight | 0x96321720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0x96325720 | 0x6e0000 |
| 214 | blk.23.attn_q.weight | 0x96a05720 | 0x6e0000 |
| 215 | blk.23.attn_v.weight | 0x970e5720 | 0x1b8000 |
| 216 | blk.23.ffn_down.weight | 0x9729d720 | 0x1f80000 |
| 217 | blk.23.ffn_gate.weight | 0x9921d720 | 0x1810000 |
| 218 | blk.23.ffn_norm.weight | 0x9aa2d720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0x9aa31720 | 0x1810000 |
| 220 | blk.24.attn_k.weight | 0x9c241720 | 0x1b8000 |
| 221 | blk.24.attn_norm.weight | 0x9c3f9720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0x9c3fd720 | 0x6e0000 |
| 223 | blk.24.attn_q.weight | 0x9cadd720 | 0x6e0000 |
| 224 | blk.24.attn_v.weight | 0x9d1bd720 | 0x1b8000 |
| 225 | blk.24.ffn_down.weight | 0x9d375720 | 0x1f80000 |
| 226 | blk.24.ffn_gate.weight | 0x9f2f5720 | 0x1810000 |
| 227 | blk.24.ffn_norm.weight | 0xa0b05720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xa0b09720 | 0x1810000 |
| 229 | blk.25.attn_k.weight | 0xa2319720 | 0x1b8000 |
| 230 | blk.25.attn_norm.weight | 0xa24d1720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xa24d5720 | 0x6e0000 |
| 232 | blk.25.attn_q.weight | 0xa2bb5720 | 0x6e0000 |
| 233 | blk.25.attn_v.weight | 0xa3295720 | 0x1b8000 |
| 234 | blk.25.ffn_down.weight | 0xa344d720 | 0x1f80000 |
| 235 | blk.25.ffn_gate.weight | 0xa53cd720 | 0x1810000 |
| 236 | blk.25.ffn_norm.weight | 0xa6bdd720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xa6be1720 | 0x1810000 |
| 238 | blk.26.attn_k.weight | 0xa83f1720 | 0x1b8000 |
| 239 | blk.26.attn_norm.weight | 0xa85a9720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xa85ad720 | 0x6e0000 |
| 241 | blk.26.attn_q.weight | 0xa8c8d720 | 0x6e0000 |
| 242 | blk.26.attn_v.weight | 0xa936d720 | 0x1b8000 |
| 243 | blk.26.ffn_down.weight | 0xa9525720 | 0x1f80000 |
| 244 | blk.26.ffn_gate.weight | 0xab4a5720 | 0x1810000 |
| 245 | blk.26.ffn_norm.weight | 0xaccb5720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xaccb9720 | 0x1810000 |
| 247 | blk.27.attn_k.weight | 0xae4c9720 | 0x1b8000 |
| 248 | blk.27.attn_norm.weight | 0xae681720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xae685720 | 0x6e0000 |
| 250 | blk.27.attn_q.weight | 0xaed65720 | 0x6e0000 |
| 251 | blk.27.attn_v.weight | 0xaf445720 | 0x1b8000 |
| 252 | blk.27.ffn_down.weight | 0xaf5fd720 | 0x1f80000 |
| 253 | blk.27.ffn_gate.weight | 0xb157d720 | 0x1810000 |
| 254 | blk.27.ffn_norm.weight | 0xb2d8d720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xb2d91720 | 0x1810000 |
| 256 | blk.28.attn_k.weight | 0xb45a1720 | 0x1b8000 |
| 257 | blk.28.attn_norm.weight | 0xb4759720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xb475d720 | 0x6e0000 |
| 259 | blk.28.attn_q.weight | 0xb4e3d720 | 0x6e0000 |
| 260 | blk.28.attn_v.weight | 0xb551d720 | 0x1b8000 |
| 261 | blk.28.ffn_down.weight | 0xb56d5720 | 0x1f80000 |
| 262 | blk.28.ffn_gate.weight | 0xb7655720 | 0x1810000 |
| 263 | blk.28.ffn_norm.weight | 0xb8e65720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xb8e69720 | 0x1810000 |
| 265 | blk.29.attn_k.weight | 0xba679720 | 0x1b8000 |
| 266 | blk.29.attn_norm.weight | 0xba831720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xba835720 | 0x6e0000 |
| 268 | blk.29.attn_q.weight | 0xbaf15720 | 0x6e0000 |
| 269 | blk.29.attn_v.weight | 0xbb5f5720 | 0x1b8000 |
| 270 | blk.29.ffn_down.weight | 0xbb7ad720 | 0x1f80000 |
| 271 | blk.29.ffn_gate.weight | 0xbd72d720 | 0x1810000 |
| 272 | blk.29.ffn_norm.weight | 0xbef3d720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xbef41720 | 0x1810000 |
| 274 | blk.30.attn_k.weight | 0xc0751720 | 0x1b8000 |
| 275 | blk.30.attn_norm.weight | 0xc0909720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xc090d720 | 0x6e0000 |
| 277 | blk.30.attn_q.weight | 0xc0fed720 | 0x6e0000 |
| 278 | blk.30.attn_v.weight | 0xc16cd720 | 0x1b8000 |
| 279 | blk.30.ffn_down.weight | 0xc1885720 | 0x1f80000 |
| 280 | blk.30.ffn_gate.weight | 0xc3805720 | 0x1810000 |
| 281 | blk.30.ffn_norm.weight | 0xc5015720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xc5019720 | 0x1810000 |
| 283 | blk.31.attn_k.weight | 0xc6829720 | 0x188000 |
| 284 | blk.31.attn_norm.weight | 0xc69b1720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xc69b5720 | 0x6e0000 |
| 286 | blk.31.attn_q.weight | 0xc7095720 | 0x620000 |
| 287 | blk.31.attn_v.weight | 0xc76b5720 | 0x1b8000 |
| 288 | blk.31.ffn_down.weight | 0xc786d720 | 0x1f80000 |
| 289 | blk.31.ffn_gate.weight | 0xc97ed720 | 0x1810000 |
| 290 | blk.31.ffn_norm.weight | 0xcaffd720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0xcb001720 | 0x1810000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:--------|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_XXS |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_XXS |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:--------|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_XXS |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:------|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ3_S |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:--------|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_XXS |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_XXS |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | IQ4_NL |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-IQ4_NL.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-IQ4_NL.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 25 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-IQ4\_NL.gguf - GGUF Internal File Dump](#watt-tool-8b-iq4_nlgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x119d0000 |
| 1 | output_norm.weight | 0x12149620 | 0x4000 |
| 2 | rope_freqs.weight | 0x1214d620 | 0x100 |
| 3 | token_embd.weight | 0x1214d720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x1f893720 | 0x1b8000 |
| 5 | blk.0.attn_norm.weight | 0x1fa4b720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1fa4f720 | 0x900000 |
| 7 | blk.0.attn_q.weight | 0x2034f720 | 0x6e0000 |
| 8 | blk.0.attn_v.weight | 0x20a2f720 | 0x220000 |
| 9 | blk.0.ffn_down.weight | 0x20c4f720 | 0x2680000 |
| 10 | blk.0.ffn_gate.weight | 0x232cf720 | 0x1810000 |
| 11 | blk.0.ffn_norm.weight | 0x24adf720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x24ae3720 | 0x1810000 |
| 13 | blk.1.attn_k.weight | 0x262f3720 | 0x1b8000 |
| 14 | blk.1.attn_norm.weight | 0x264ab720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x264af720 | 0x900000 |
| 16 | blk.1.attn_q.weight | 0x26daf720 | 0x6e0000 |
| 17 | blk.1.attn_v.weight | 0x2748f720 | 0x220000 |
| 18 | blk.1.ffn_down.weight | 0x276af720 | 0x2680000 |
| 19 | blk.1.ffn_gate.weight | 0x29d2f720 | 0x1810000 |
| 20 | blk.1.ffn_norm.weight | 0x2b53f720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x2b543720 | 0x1810000 |
| 22 | blk.2.attn_k.weight | 0x2cd53720 | 0x1b8000 |
| 23 | blk.2.attn_norm.weight | 0x2cf0b720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x2cf0f720 | 0x900000 |
| 25 | blk.2.attn_q.weight | 0x2d80f720 | 0x6e0000 |
| 26 | blk.2.attn_v.weight | 0x2deef720 | 0x220000 |
| 27 | blk.2.ffn_down.weight | 0x2e10f720 | 0x2680000 |
| 28 | blk.2.ffn_gate.weight | 0x3078f720 | 0x1810000 |
| 29 | blk.2.ffn_norm.weight | 0x31f9f720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x31fa3720 | 0x1810000 |
| 31 | blk.3.attn_k.weight | 0x337b3720 | 0x1b8000 |
| 32 | blk.3.attn_norm.weight | 0x3396b720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x3396f720 | 0x900000 |
| 34 | blk.3.attn_q.weight | 0x3426f720 | 0x6e0000 |
| 35 | blk.3.attn_v.weight | 0x3494f720 | 0x220000 |
| 36 | blk.3.ffn_down.weight | 0x34b6f720 | 0x2680000 |
| 37 | blk.3.ffn_gate.weight | 0x371ef720 | 0x1810000 |
| 38 | blk.3.ffn_norm.weight | 0x389ff720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x38a03720 | 0x1810000 |
| 40 | blk.4.attn_k.weight | 0x3a213720 | 0x1b8000 |
| 41 | blk.4.attn_norm.weight | 0x3a3cb720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x3a3cf720 | 0x900000 |
| 43 | blk.4.attn_q.weight | 0x3accf720 | 0x6e0000 |
| 44 | blk.4.attn_v.weight | 0x3b3af720 | 0x220000 |
| 45 | blk.4.ffn_down.weight | 0x3b5cf720 | 0x2680000 |
| 46 | blk.4.ffn_gate.weight | 0x3dc4f720 | 0x1810000 |
| 47 | blk.4.ffn_norm.weight | 0x3f45f720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x3f463720 | 0x1810000 |
| 49 | blk.5.attn_k.weight | 0x40c73720 | 0x1b8000 |
| 50 | blk.5.attn_norm.weight | 0x40e2b720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x40e2f720 | 0x900000 |
| 52 | blk.5.attn_q.weight | 0x4172f720 | 0x6e0000 |
| 53 | blk.5.attn_v.weight | 0x41e0f720 | 0x220000 |
| 54 | blk.5.ffn_down.weight | 0x4202f720 | 0x2680000 |
| 55 | blk.5.ffn_gate.weight | 0x446af720 | 0x1810000 |
| 56 | blk.5.ffn_norm.weight | 0x45ebf720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x45ec3720 | 0x1810000 |
| 58 | blk.6.attn_k.weight | 0x476d3720 | 0x1b8000 |
| 59 | blk.6.attn_norm.weight | 0x4788b720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x4788f720 | 0x900000 |
| 61 | blk.6.attn_q.weight | 0x4818f720 | 0x6e0000 |
| 62 | blk.6.attn_v.weight | 0x4886f720 | 0x220000 |
| 63 | blk.6.ffn_down.weight | 0x48a8f720 | 0x2680000 |
| 64 | blk.6.ffn_gate.weight | 0x4b10f720 | 0x1810000 |
| 65 | blk.6.ffn_norm.weight | 0x4c91f720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x4c923720 | 0x1810000 |
| 67 | blk.7.attn_k.weight | 0x4e133720 | 0x1b8000 |
| 68 | blk.7.attn_norm.weight | 0x4e2eb720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x4e2ef720 | 0x900000 |
| 70 | blk.7.attn_q.weight | 0x4ebef720 | 0x6e0000 |
| 71 | blk.7.attn_v.weight | 0x4f2cf720 | 0x220000 |
| 72 | blk.7.ffn_down.weight | 0x4f4ef720 | 0x2680000 |
| 73 | blk.7.ffn_gate.weight | 0x51b6f720 | 0x1810000 |
| 74 | blk.7.ffn_norm.weight | 0x5337f720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x53383720 | 0x1810000 |
| 76 | blk.8.attn_k.weight | 0x54b93720 | 0x1b8000 |
| 77 | blk.8.attn_norm.weight | 0x54d4b720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x54d4f720 | 0x900000 |
| 79 | blk.8.attn_q.weight | 0x5564f720 | 0x6e0000 |
| 80 | blk.8.attn_v.weight | 0x55d2f720 | 0x220000 |
| 81 | blk.8.ffn_down.weight | 0x55f4f720 | 0x2680000 |
| 82 | blk.8.ffn_gate.weight | 0x585cf720 | 0x1810000 |
| 83 | blk.8.ffn_norm.weight | 0x59ddf720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x59de3720 | 0x1810000 |
| 85 | blk.9.attn_k.weight | 0x5b5f3720 | 0x1b8000 |
| 86 | blk.9.attn_norm.weight | 0x5b7ab720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x5b7af720 | 0x900000 |
| 88 | blk.9.attn_q.weight | 0x5c0af720 | 0x6e0000 |
| 89 | blk.9.attn_v.weight | 0x5c78f720 | 0x220000 |
| 90 | blk.9.ffn_down.weight | 0x5c9af720 | 0x2680000 |
| 91 | blk.9.ffn_gate.weight | 0x5f02f720 | 0x1810000 |
| 92 | blk.9.ffn_norm.weight | 0x6083f720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x60843720 | 0x1810000 |
| 94 | blk.10.attn_k.weight | 0x62053720 | 0x1b8000 |
| 95 | blk.10.attn_norm.weight | 0x6220b720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x6220f720 | 0x900000 |
| 97 | blk.10.attn_q.weight | 0x62b0f720 | 0x6e0000 |
| 98 | blk.10.attn_v.weight | 0x631ef720 | 0x220000 |
| 99 | blk.10.ffn_down.weight | 0x6340f720 | 0x2680000 |
| 100 | blk.10.ffn_gate.weight | 0x65a8f720 | 0x1810000 |
| 101 | blk.10.ffn_norm.weight | 0x6729f720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x672a3720 | 0x1810000 |
| 103 | blk.11.attn_k.weight | 0x68ab3720 | 0x1b8000 |
| 104 | blk.11.attn_norm.weight | 0x68c6b720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x68c6f720 | 0x900000 |
| 106 | blk.11.attn_q.weight | 0x6956f720 | 0x6e0000 |
| 107 | blk.11.attn_v.weight | 0x69c4f720 | 0x220000 |
| 108 | blk.11.ffn_down.weight | 0x69e6f720 | 0x2680000 |
| 109 | blk.11.ffn_gate.weight | 0x6c4ef720 | 0x1810000 |
| 110 | blk.11.ffn_norm.weight | 0x6dcff720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x6dd03720 | 0x1810000 |
| 112 | blk.12.attn_k.weight | 0x6f513720 | 0x1b8000 |
| 113 | blk.12.attn_norm.weight | 0x6f6cb720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x6f6cf720 | 0x900000 |
| 115 | blk.12.attn_q.weight | 0x6ffcf720 | 0x6e0000 |
| 116 | blk.12.attn_v.weight | 0x706af720 | 0x220000 |
| 117 | blk.12.ffn_down.weight | 0x708cf720 | 0x2680000 |
| 118 | blk.12.ffn_gate.weight | 0x72f4f720 | 0x1810000 |
| 119 | blk.12.ffn_norm.weight | 0x7475f720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x74763720 | 0x1810000 |
| 121 | blk.13.attn_k.weight | 0x75f73720 | 0x240000 |
| 122 | blk.13.attn_norm.weight | 0x761b3720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x761b7720 | 0x900000 |
| 124 | blk.13.attn_q.weight | 0x76ab7720 | 0x900000 |
| 125 | blk.13.attn_v.weight | 0x773b7720 | 0x240000 |
| 126 | blk.13.ffn_down.weight | 0x775f7720 | 0x2680000 |
| 127 | blk.13.ffn_gate.weight | 0x79c77720 | 0x1810000 |
| 128 | blk.13.ffn_norm.weight | 0x7b487720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x7b48b720 | 0x1810000 |
| 130 | blk.14.attn_k.weight | 0x7cc9b720 | 0x240000 |
| 131 | blk.14.attn_norm.weight | 0x7cedb720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x7cedf720 | 0x900000 |
| 133 | blk.14.attn_q.weight | 0x7d7df720 | 0x900000 |
| 134 | blk.14.attn_v.weight | 0x7e0df720 | 0x240000 |
| 135 | blk.14.ffn_down.weight | 0x7e31f720 | 0x2680000 |
| 136 | blk.14.ffn_gate.weight | 0x8099f720 | 0x1810000 |
| 137 | blk.14.ffn_norm.weight | 0x821af720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x821b3720 | 0x1810000 |
| 139 | blk.15.attn_k.weight | 0x839c3720 | 0x1b8000 |
| 140 | blk.15.attn_norm.weight | 0x83b7b720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x83b7f720 | 0x900000 |
| 142 | blk.15.attn_q.weight | 0x8447f720 | 0x6e0000 |
| 143 | blk.15.attn_v.weight | 0x84b5f720 | 0x220000 |
| 144 | blk.15.ffn_down.weight | 0x84d7f720 | 0x2680000 |
| 145 | blk.15.ffn_gate.weight | 0x873ff720 | 0x1810000 |
| 146 | blk.15.ffn_norm.weight | 0x88c0f720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x88c13720 | 0x1810000 |
| 148 | blk.16.attn_k.weight | 0x8a423720 | 0x240000 |
| 149 | blk.16.attn_norm.weight | 0x8a663720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x8a667720 | 0x900000 |
| 151 | blk.16.attn_q.weight | 0x8af67720 | 0x900000 |
| 152 | blk.16.attn_v.weight | 0x8b867720 | 0x240000 |
| 153 | blk.16.ffn_down.weight | 0x8baa7720 | 0x2680000 |
| 154 | blk.16.ffn_gate.weight | 0x8e127720 | 0x1f80000 |
| 155 | blk.16.ffn_norm.weight | 0x900a7720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x900ab720 | 0x1f80000 |
| 157 | blk.17.attn_k.weight | 0x9202b720 | 0x1b8000 |
| 158 | blk.17.attn_norm.weight | 0x921e3720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x921e7720 | 0x900000 |
| 160 | blk.17.attn_q.weight | 0x92ae7720 | 0x6e0000 |
| 161 | blk.17.attn_v.weight | 0x931c7720 | 0x220000 |
| 162 | blk.17.ffn_down.weight | 0x933e7720 | 0x2680000 |
| 163 | blk.17.ffn_gate.weight | 0x95a67720 | 0x1f80000 |
| 164 | blk.17.ffn_norm.weight | 0x979e7720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x979eb720 | 0x1f80000 |
| 166 | blk.18.attn_k.weight | 0x9996b720 | 0x240000 |
| 167 | blk.18.attn_norm.weight | 0x99bab720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x99baf720 | 0x900000 |
| 169 | blk.18.attn_q.weight | 0x9a4af720 | 0x900000 |
| 170 | blk.18.attn_v.weight | 0x9adaf720 | 0x240000 |
| 171 | blk.18.ffn_down.weight | 0x9afef720 | 0x2680000 |
| 172 | blk.18.ffn_gate.weight | 0x9d66f720 | 0x1f80000 |
| 173 | blk.18.ffn_norm.weight | 0x9f5ef720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x9f5f3720 | 0x1f80000 |
| 175 | blk.19.attn_k.weight | 0xa1573720 | 0x240000 |
| 176 | blk.19.attn_norm.weight | 0xa17b3720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0xa17b7720 | 0x900000 |
| 178 | blk.19.attn_q.weight | 0xa20b7720 | 0x900000 |
| 179 | blk.19.attn_v.weight | 0xa29b7720 | 0x240000 |
| 180 | blk.19.ffn_down.weight | 0xa2bf7720 | 0x2680000 |
| 181 | blk.19.ffn_gate.weight | 0xa5277720 | 0x1f80000 |
| 182 | blk.19.ffn_norm.weight | 0xa71f7720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0xa71fb720 | 0x1f80000 |
| 184 | blk.20.attn_k.weight | 0xa917b720 | 0x240000 |
| 185 | blk.20.attn_norm.weight | 0xa93bb720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0xa93bf720 | 0x900000 |
| 187 | blk.20.attn_q.weight | 0xa9cbf720 | 0x900000 |
| 188 | blk.20.attn_v.weight | 0xaa5bf720 | 0x240000 |
| 189 | blk.20.ffn_down.weight | 0xaa7ff720 | 0x2680000 |
| 190 | blk.20.ffn_gate.weight | 0xace7f720 | 0x1f80000 |
| 191 | blk.20.ffn_norm.weight | 0xaedff720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0xaee03720 | 0x1f80000 |
| 193 | blk.21.attn_k.weight | 0xb0d83720 | 0x240000 |
| 194 | blk.21.attn_norm.weight | 0xb0fc3720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0xb0fc7720 | 0x900000 |
| 196 | blk.21.attn_q.weight | 0xb18c7720 | 0x900000 |
| 197 | blk.21.attn_v.weight | 0xb21c7720 | 0x240000 |
| 198 | blk.21.ffn_down.weight | 0xb2407720 | 0x2680000 |
| 199 | blk.21.ffn_gate.weight | 0xb4a87720 | 0x1f80000 |
| 200 | blk.21.ffn_norm.weight | 0xb6a07720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0xb6a0b720 | 0x1f80000 |
| 202 | blk.22.attn_k.weight | 0xb898b720 | 0x240000 |
| 203 | blk.22.attn_norm.weight | 0xb8bcb720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0xb8bcf720 | 0x900000 |
| 205 | blk.22.attn_q.weight | 0xb94cf720 | 0x900000 |
| 206 | blk.22.attn_v.weight | 0xb9dcf720 | 0x240000 |
| 207 | blk.22.ffn_down.weight | 0xba00f720 | 0x2680000 |
| 208 | blk.22.ffn_gate.weight | 0xbc68f720 | 0x1f80000 |
| 209 | blk.22.ffn_norm.weight | 0xbe60f720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xbe613720 | 0x1f80000 |
| 211 | blk.23.attn_k.weight | 0xc0593720 | 0x240000 |
| 212 | blk.23.attn_norm.weight | 0xc07d3720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xc07d7720 | 0x900000 |
| 214 | blk.23.attn_q.weight | 0xc10d7720 | 0x900000 |
| 215 | blk.23.attn_v.weight | 0xc19d7720 | 0x240000 |
| 216 | blk.23.ffn_down.weight | 0xc1c17720 | 0x2680000 |
| 217 | blk.23.ffn_gate.weight | 0xc4297720 | 0x1f80000 |
| 218 | blk.23.ffn_norm.weight | 0xc6217720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xc621b720 | 0x1f80000 |
| 220 | blk.24.attn_k.weight | 0xc819b720 | 0x240000 |
| 221 | blk.24.attn_norm.weight | 0xc83db720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xc83df720 | 0x900000 |
| 223 | blk.24.attn_q.weight | 0xc8cdf720 | 0x900000 |
| 224 | blk.24.attn_v.weight | 0xc95df720 | 0x240000 |
| 225 | blk.24.ffn_down.weight | 0xc981f720 | 0x2680000 |
| 226 | blk.24.ffn_gate.weight | 0xcbe9f720 | 0x1f80000 |
| 227 | blk.24.ffn_norm.weight | 0xcde1f720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xcde23720 | 0x1f80000 |
| 229 | blk.25.attn_k.weight | 0xcfda3720 | 0x240000 |
| 230 | blk.25.attn_norm.weight | 0xcffe3720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xcffe7720 | 0x900000 |
| 232 | blk.25.attn_q.weight | 0xd08e7720 | 0x900000 |
| 233 | blk.25.attn_v.weight | 0xd11e7720 | 0x240000 |
| 234 | blk.25.ffn_down.weight | 0xd1427720 | 0x2680000 |
| 235 | blk.25.ffn_gate.weight | 0xd3aa7720 | 0x1f80000 |
| 236 | blk.25.ffn_norm.weight | 0xd5a27720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xd5a2b720 | 0x1f80000 |
| 238 | blk.26.attn_k.weight | 0xd79ab720 | 0x240000 |
| 239 | blk.26.attn_norm.weight | 0xd7beb720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xd7bef720 | 0x900000 |
| 241 | blk.26.attn_q.weight | 0xd84ef720 | 0x900000 |
| 242 | blk.26.attn_v.weight | 0xd8def720 | 0x240000 |
| 243 | blk.26.ffn_down.weight | 0xd902f720 | 0x2680000 |
| 244 | blk.26.ffn_gate.weight | 0xdb6af720 | 0x1f80000 |
| 245 | blk.26.ffn_norm.weight | 0xdd62f720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xdd633720 | 0x1f80000 |
| 247 | blk.27.attn_k.weight | 0xdf5b3720 | 0x240000 |
| 248 | blk.27.attn_norm.weight | 0xdf7f3720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xdf7f7720 | 0x900000 |
| 250 | blk.27.attn_q.weight | 0xe00f7720 | 0x900000 |
| 251 | blk.27.attn_v.weight | 0xe09f7720 | 0x240000 |
| 252 | blk.27.ffn_down.weight | 0xe0c37720 | 0x2680000 |
| 253 | blk.27.ffn_gate.weight | 0xe32b7720 | 0x1f80000 |
| 254 | blk.27.ffn_norm.weight | 0xe5237720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xe523b720 | 0x1f80000 |
| 256 | blk.28.attn_k.weight | 0xe71bb720 | 0x240000 |
| 257 | blk.28.attn_norm.weight | 0xe73fb720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xe73ff720 | 0x900000 |
| 259 | blk.28.attn_q.weight | 0xe7cff720 | 0x900000 |
| 260 | blk.28.attn_v.weight | 0xe85ff720 | 0x240000 |
| 261 | blk.28.ffn_down.weight | 0xe883f720 | 0x2680000 |
| 262 | blk.28.ffn_gate.weight | 0xeaebf720 | 0x1f80000 |
| 263 | blk.28.ffn_norm.weight | 0xece3f720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xece43720 | 0x1f80000 |
| 265 | blk.29.attn_k.weight | 0xeedc3720 | 0x240000 |
| 266 | blk.29.attn_norm.weight | 0xef003720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xef007720 | 0x900000 |
| 268 | blk.29.attn_q.weight | 0xef907720 | 0x900000 |
| 269 | blk.29.attn_v.weight | 0xf0207720 | 0x240000 |
| 270 | blk.29.ffn_down.weight | 0xf0447720 | 0x2680000 |
| 271 | blk.29.ffn_gate.weight | 0xf2ac7720 | 0x1f80000 |
| 272 | blk.29.ffn_norm.weight | 0xf4a47720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xf4a4b720 | 0x1f80000 |
| 274 | blk.30.attn_k.weight | 0xf69cb720 | 0x240000 |
| 275 | blk.30.attn_norm.weight | 0xf6c0b720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xf6c0f720 | 0x900000 |
| 277 | blk.30.attn_q.weight | 0xf750f720 | 0x900000 |
| 278 | blk.30.attn_v.weight | 0xf7e0f720 | 0x240000 |
| 279 | blk.30.ffn_down.weight | 0xf804f720 | 0x2680000 |
| 280 | blk.30.ffn_gate.weight | 0xfa6cf720 | 0x1f80000 |
| 281 | blk.30.ffn_norm.weight | 0xfc64f720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xfc653720 | 0x1f80000 |
| 283 | blk.31.attn_k.weight | 0xfe5d3720 | 0x1b8000 |
| 284 | blk.31.attn_norm.weight | 0xfe78b720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xfe78f720 | 0x900000 |
| 286 | blk.31.attn_q.weight | 0xff08f720 | 0x6e0000 |
| 287 | blk.31.attn_v.weight | 0xff76f720 | 0x220000 |
| 288 | blk.31.ffn_down.weight | 0xff98f720 | 0x2680000 |
| 289 | blk.31.ffn_gate.weight | 0x10200f720 | 0x1f80000 |
| 290 | blk.31.ffn_norm.weight | 0x103f8f720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0x103f93720 | 0x1f80000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-------|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ4_NL |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | IQ3_S |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-------|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ3_S |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_NL |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-------|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ3_S |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ4_NL |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | IQ3_S |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | IQ4_XS |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | IQ4_NL |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q3_K_L.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q3_K_L.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 13 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q3\_K\_L.gguf - GGUF Internal File Dump](#watt-tool-8b-q3_k_lgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0xd746000 |
| 1 | output_norm.weight | 0xdebf620 | 0x4000 |
| 2 | rope_freqs.weight | 0xdec3620 | 0x100 |
| 3 | token_embd.weight | 0xdec3720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x1b609720 | 0x150000 |
| 5 | blk.0.attn_norm.weight | 0x1b759720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1b75d720 | 0xb00000 |
| 7 | blk.0.attn_q.weight | 0x1c25d720 | 0x540000 |
| 8 | blk.0.attn_v.weight | 0x1c79d720 | 0x240000 |
| 9 | blk.0.ffn_down.weight | 0x1c9dd720 | 0x1f80000 |
| 10 | blk.0.ffn_gate.weight | 0x1e95d720 | 0x1260000 |
| 11 | blk.0.ffn_norm.weight | 0x1fbbd720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x1fbc1720 | 0x1260000 |
| 13 | blk.1.attn_k.weight | 0x20e21720 | 0x150000 |
| 14 | blk.1.attn_norm.weight | 0x20f71720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x20f75720 | 0xb00000 |
| 16 | blk.1.attn_q.weight | 0x21a75720 | 0x540000 |
| 17 | blk.1.attn_v.weight | 0x21fb5720 | 0x240000 |
| 18 | blk.1.ffn_down.weight | 0x221f5720 | 0x2680000 |
| 19 | blk.1.ffn_gate.weight | 0x24875720 | 0x1260000 |
| 20 | blk.1.ffn_norm.weight | 0x25ad5720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x25ad9720 | 0x1260000 |
| 22 | blk.2.attn_k.weight | 0x26d39720 | 0x150000 |
| 23 | blk.2.attn_norm.weight | 0x26e89720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x26e8d720 | 0xb00000 |
| 25 | blk.2.attn_q.weight | 0x2798d720 | 0x540000 |
| 26 | blk.2.attn_v.weight | 0x27ecd720 | 0x240000 |
| 27 | blk.2.ffn_down.weight | 0x2810d720 | 0x1f80000 |
| 28 | blk.2.ffn_gate.weight | 0x2a08d720 | 0x1260000 |
| 29 | blk.2.ffn_norm.weight | 0x2b2ed720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x2b2f1720 | 0x1260000 |
| 31 | blk.3.attn_k.weight | 0x2c551720 | 0x150000 |
| 32 | blk.3.attn_norm.weight | 0x2c6a1720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x2c6a5720 | 0xb00000 |
| 34 | blk.3.attn_q.weight | 0x2d1a5720 | 0x540000 |
| 35 | blk.3.attn_v.weight | 0x2d6e5720 | 0x240000 |
| 36 | blk.3.ffn_down.weight | 0x2d925720 | 0x1f80000 |
| 37 | blk.3.ffn_gate.weight | 0x2f8a5720 | 0x1260000 |
| 38 | blk.3.ffn_norm.weight | 0x30b05720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x30b09720 | 0x1260000 |
| 40 | blk.4.attn_k.weight | 0x31d69720 | 0x150000 |
| 41 | blk.4.attn_norm.weight | 0x31eb9720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x31ebd720 | 0xb00000 |
| 43 | blk.4.attn_q.weight | 0x329bd720 | 0x540000 |
| 44 | blk.4.attn_v.weight | 0x32efd720 | 0x240000 |
| 45 | blk.4.ffn_down.weight | 0x3313d720 | 0x1f80000 |
| 46 | blk.4.ffn_gate.weight | 0x350bd720 | 0x1260000 |
| 47 | blk.4.ffn_norm.weight | 0x3631d720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x36321720 | 0x1260000 |
| 49 | blk.5.attn_k.weight | 0x37581720 | 0x150000 |
| 50 | blk.5.attn_norm.weight | 0x376d1720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x376d5720 | 0xb00000 |
| 52 | blk.5.attn_q.weight | 0x381d5720 | 0x540000 |
| 53 | blk.5.attn_v.weight | 0x38715720 | 0x240000 |
| 54 | blk.5.ffn_down.weight | 0x38955720 | 0x1f80000 |
| 55 | blk.5.ffn_gate.weight | 0x3a8d5720 | 0x1260000 |
| 56 | blk.5.ffn_norm.weight | 0x3bb35720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x3bb39720 | 0x1260000 |
| 58 | blk.6.attn_k.weight | 0x3cd99720 | 0x150000 |
| 59 | blk.6.attn_norm.weight | 0x3cee9720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x3ceed720 | 0xb00000 |
| 61 | blk.6.attn_q.weight | 0x3d9ed720 | 0x540000 |
| 62 | blk.6.attn_v.weight | 0x3df2d720 | 0x240000 |
| 63 | blk.6.ffn_down.weight | 0x3e16d720 | 0x1f80000 |
| 64 | blk.6.ffn_gate.weight | 0x400ed720 | 0x1260000 |
| 65 | blk.6.ffn_norm.weight | 0x4134d720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x41351720 | 0x1260000 |
| 67 | blk.7.attn_k.weight | 0x425b1720 | 0x150000 |
| 68 | blk.7.attn_norm.weight | 0x42701720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x42705720 | 0xb00000 |
| 70 | blk.7.attn_q.weight | 0x43205720 | 0x540000 |
| 71 | blk.7.attn_v.weight | 0x43745720 | 0x240000 |
| 72 | blk.7.ffn_down.weight | 0x43985720 | 0x1f80000 |
| 73 | blk.7.ffn_gate.weight | 0x45905720 | 0x1260000 |
| 74 | blk.7.ffn_norm.weight | 0x46b65720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x46b69720 | 0x1260000 |
| 76 | blk.8.attn_k.weight | 0x47dc9720 | 0x150000 |
| 77 | blk.8.attn_norm.weight | 0x47f19720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x47f1d720 | 0xb00000 |
| 79 | blk.8.attn_q.weight | 0x48a1d720 | 0x540000 |
| 80 | blk.8.attn_v.weight | 0x48f5d720 | 0x240000 |
| 81 | blk.8.ffn_down.weight | 0x4919d720 | 0x1f80000 |
| 82 | blk.8.ffn_gate.weight | 0x4b11d720 | 0x1260000 |
| 83 | blk.8.ffn_norm.weight | 0x4c37d720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x4c381720 | 0x1260000 |
| 85 | blk.9.attn_k.weight | 0x4d5e1720 | 0x150000 |
| 86 | blk.9.attn_norm.weight | 0x4d731720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x4d735720 | 0xb00000 |
| 88 | blk.9.attn_q.weight | 0x4e235720 | 0x540000 |
| 89 | blk.9.attn_v.weight | 0x4e775720 | 0x240000 |
| 90 | blk.9.ffn_down.weight | 0x4e9b5720 | 0x1f80000 |
| 91 | blk.9.ffn_gate.weight | 0x50935720 | 0x1260000 |
| 92 | blk.9.ffn_norm.weight | 0x51b95720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x51b99720 | 0x1260000 |
| 94 | blk.10.attn_k.weight | 0x52df9720 | 0x150000 |
| 95 | blk.10.attn_norm.weight | 0x52f49720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x52f4d720 | 0xb00000 |
| 97 | blk.10.attn_q.weight | 0x53a4d720 | 0x540000 |
| 98 | blk.10.attn_v.weight | 0x53f8d720 | 0x240000 |
| 99 | blk.10.ffn_down.weight | 0x541cd720 | 0x1f80000 |
| 100 | blk.10.ffn_gate.weight | 0x5614d720 | 0x1260000 |
| 101 | blk.10.ffn_norm.weight | 0x573ad720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x573b1720 | 0x1260000 |
| 103 | blk.11.attn_k.weight | 0x58611720 | 0x150000 |
| 104 | blk.11.attn_norm.weight | 0x58761720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x58765720 | 0xb00000 |
| 106 | blk.11.attn_q.weight | 0x59265720 | 0x540000 |
| 107 | blk.11.attn_v.weight | 0x597a5720 | 0x240000 |
| 108 | blk.11.ffn_down.weight | 0x599e5720 | 0x1f80000 |
| 109 | blk.11.ffn_gate.weight | 0x5b965720 | 0x1260000 |
| 110 | blk.11.ffn_norm.weight | 0x5cbc5720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x5cbc9720 | 0x1260000 |
| 112 | blk.12.attn_k.weight | 0x5de29720 | 0x150000 |
| 113 | blk.12.attn_norm.weight | 0x5df79720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x5df7d720 | 0xb00000 |
| 115 | blk.12.attn_q.weight | 0x5ea7d720 | 0x540000 |
| 116 | blk.12.attn_v.weight | 0x5efbd720 | 0x240000 |
| 117 | blk.12.ffn_down.weight | 0x5f1fd720 | 0x1f80000 |
| 118 | blk.12.ffn_gate.weight | 0x6117d720 | 0x1260000 |
| 119 | blk.12.ffn_norm.weight | 0x623dd720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x623e1720 | 0x1260000 |
| 121 | blk.13.attn_k.weight | 0x63641720 | 0x1b8000 |
| 122 | blk.13.attn_norm.weight | 0x637f9720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x637fd720 | 0xb00000 |
| 124 | blk.13.attn_q.weight | 0x642fd720 | 0x6e0000 |
| 125 | blk.13.attn_v.weight | 0x649dd720 | 0x240000 |
| 126 | blk.13.ffn_down.weight | 0x64c1d720 | 0x1f80000 |
| 127 | blk.13.ffn_gate.weight | 0x66b9d720 | 0x1260000 |
| 128 | blk.13.ffn_norm.weight | 0x67dfd720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x67e01720 | 0x1260000 |
| 130 | blk.14.attn_k.weight | 0x69061720 | 0x1b8000 |
| 131 | blk.14.attn_norm.weight | 0x69219720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x6921d720 | 0xb00000 |
| 133 | blk.14.attn_q.weight | 0x69d1d720 | 0x6e0000 |
| 134 | blk.14.attn_v.weight | 0x6a3fd720 | 0x240000 |
| 135 | blk.14.ffn_down.weight | 0x6a63d720 | 0x1f80000 |
| 136 | blk.14.ffn_gate.weight | 0x6c5bd720 | 0x1260000 |
| 137 | blk.14.ffn_norm.weight | 0x6d81d720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x6d821720 | 0x1260000 |
| 139 | blk.15.attn_k.weight | 0x6ea81720 | 0x150000 |
| 140 | blk.15.attn_norm.weight | 0x6ebd1720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x6ebd5720 | 0xb00000 |
| 142 | blk.15.attn_q.weight | 0x6f6d5720 | 0x540000 |
| 143 | blk.15.attn_v.weight | 0x6fc15720 | 0x240000 |
| 144 | blk.15.ffn_down.weight | 0x6fe55720 | 0x1f80000 |
| 145 | blk.15.ffn_gate.weight | 0x71dd5720 | 0x1260000 |
| 146 | blk.15.ffn_norm.weight | 0x73035720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x73039720 | 0x1260000 |
| 148 | blk.16.attn_k.weight | 0x74299720 | 0x1b8000 |
| 149 | blk.16.attn_norm.weight | 0x74451720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x74455720 | 0xb00000 |
| 151 | blk.16.attn_q.weight | 0x74f55720 | 0x6e0000 |
| 152 | blk.16.attn_v.weight | 0x75635720 | 0x240000 |
| 153 | blk.16.ffn_down.weight | 0x75875720 | 0x1f80000 |
| 154 | blk.16.ffn_gate.weight | 0x777f5720 | 0x1810000 |
| 155 | blk.16.ffn_norm.weight | 0x79005720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x79009720 | 0x1810000 |
| 157 | blk.17.attn_k.weight | 0x7a819720 | 0x150000 |
| 158 | blk.17.attn_norm.weight | 0x7a969720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x7a96d720 | 0xb00000 |
| 160 | blk.17.attn_q.weight | 0x7b46d720 | 0x540000 |
| 161 | blk.17.attn_v.weight | 0x7b9ad720 | 0x240000 |
| 162 | blk.17.ffn_down.weight | 0x7bbed720 | 0x2680000 |
| 163 | blk.17.ffn_gate.weight | 0x7e26d720 | 0x1810000 |
| 164 | blk.17.ffn_norm.weight | 0x7fa7d720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x7fa81720 | 0x1810000 |
| 166 | blk.18.attn_k.weight | 0x81291720 | 0x1b8000 |
| 167 | blk.18.attn_norm.weight | 0x81449720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x8144d720 | 0xb00000 |
| 169 | blk.18.attn_q.weight | 0x81f4d720 | 0x6e0000 |
| 170 | blk.18.attn_v.weight | 0x8262d720 | 0x240000 |
| 171 | blk.18.ffn_down.weight | 0x8286d720 | 0x2680000 |
| 172 | blk.18.ffn_gate.weight | 0x84eed720 | 0x1810000 |
| 173 | blk.18.ffn_norm.weight | 0x866fd720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x86701720 | 0x1810000 |
| 175 | blk.19.attn_k.weight | 0x87f11720 | 0x1b8000 |
| 176 | blk.19.attn_norm.weight | 0x880c9720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x880cd720 | 0xb00000 |
| 178 | blk.19.attn_q.weight | 0x88bcd720 | 0x6e0000 |
| 179 | blk.19.attn_v.weight | 0x892ad720 | 0x240000 |
| 180 | blk.19.ffn_down.weight | 0x894ed720 | 0x2680000 |
| 181 | blk.19.ffn_gate.weight | 0x8bb6d720 | 0x1810000 |
| 182 | blk.19.ffn_norm.weight | 0x8d37d720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0x8d381720 | 0x1810000 |
| 184 | blk.20.attn_k.weight | 0x8eb91720 | 0x1b8000 |
| 185 | blk.20.attn_norm.weight | 0x8ed49720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0x8ed4d720 | 0xb00000 |
| 187 | blk.20.attn_q.weight | 0x8f84d720 | 0x6e0000 |
| 188 | blk.20.attn_v.weight | 0x8ff2d720 | 0x240000 |
| 189 | blk.20.ffn_down.weight | 0x9016d720 | 0x2680000 |
| 190 | blk.20.ffn_gate.weight | 0x927ed720 | 0x1810000 |
| 191 | blk.20.ffn_norm.weight | 0x93ffd720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x94001720 | 0x1810000 |
| 193 | blk.21.attn_k.weight | 0x95811720 | 0x1b8000 |
| 194 | blk.21.attn_norm.weight | 0x959c9720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x959cd720 | 0xb00000 |
| 196 | blk.21.attn_q.weight | 0x964cd720 | 0x6e0000 |
| 197 | blk.21.attn_v.weight | 0x96bad720 | 0x240000 |
| 198 | blk.21.ffn_down.weight | 0x96ded720 | 0x2680000 |
| 199 | blk.21.ffn_gate.weight | 0x9946d720 | 0x1810000 |
| 200 | blk.21.ffn_norm.weight | 0x9ac7d720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x9ac81720 | 0x1810000 |
| 202 | blk.22.attn_k.weight | 0x9c491720 | 0x1b8000 |
| 203 | blk.22.attn_norm.weight | 0x9c649720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x9c64d720 | 0xb00000 |
| 205 | blk.22.attn_q.weight | 0x9d14d720 | 0x6e0000 |
| 206 | blk.22.attn_v.weight | 0x9d82d720 | 0x240000 |
| 207 | blk.22.ffn_down.weight | 0x9da6d720 | 0x2680000 |
| 208 | blk.22.ffn_gate.weight | 0xa00ed720 | 0x1810000 |
| 209 | blk.22.ffn_norm.weight | 0xa18fd720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xa1901720 | 0x1810000 |
| 211 | blk.23.attn_k.weight | 0xa3111720 | 0x1b8000 |
| 212 | blk.23.attn_norm.weight | 0xa32c9720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xa32cd720 | 0xb00000 |
| 214 | blk.23.attn_q.weight | 0xa3dcd720 | 0x6e0000 |
| 215 | blk.23.attn_v.weight | 0xa44ad720 | 0x240000 |
| 216 | blk.23.ffn_down.weight | 0xa46ed720 | 0x2680000 |
| 217 | blk.23.ffn_gate.weight | 0xa6d6d720 | 0x1810000 |
| 218 | blk.23.ffn_norm.weight | 0xa857d720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xa8581720 | 0x1810000 |
| 220 | blk.24.attn_k.weight | 0xa9d91720 | 0x1b8000 |
| 221 | blk.24.attn_norm.weight | 0xa9f49720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xa9f4d720 | 0xb00000 |
| 223 | blk.24.attn_q.weight | 0xaaa4d720 | 0x6e0000 |
| 224 | blk.24.attn_v.weight | 0xab12d720 | 0x240000 |
| 225 | blk.24.ffn_down.weight | 0xab36d720 | 0x2680000 |
| 226 | blk.24.ffn_gate.weight | 0xad9ed720 | 0x1810000 |
| 227 | blk.24.ffn_norm.weight | 0xaf1fd720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xaf201720 | 0x1810000 |
| 229 | blk.25.attn_k.weight | 0xb0a11720 | 0x1b8000 |
| 230 | blk.25.attn_norm.weight | 0xb0bc9720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xb0bcd720 | 0xb00000 |
| 232 | blk.25.attn_q.weight | 0xb16cd720 | 0x6e0000 |
| 233 | blk.25.attn_v.weight | 0xb1dad720 | 0x240000 |
| 234 | blk.25.ffn_down.weight | 0xb1fed720 | 0x2680000 |
| 235 | blk.25.ffn_gate.weight | 0xb466d720 | 0x1810000 |
| 236 | blk.25.ffn_norm.weight | 0xb5e7d720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xb5e81720 | 0x1810000 |
| 238 | blk.26.attn_k.weight | 0xb7691720 | 0x1b8000 |
| 239 | blk.26.attn_norm.weight | 0xb7849720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xb784d720 | 0xb00000 |
| 241 | blk.26.attn_q.weight | 0xb834d720 | 0x6e0000 |
| 242 | blk.26.attn_v.weight | 0xb8a2d720 | 0x240000 |
| 243 | blk.26.ffn_down.weight | 0xb8c6d720 | 0x2680000 |
| 244 | blk.26.ffn_gate.weight | 0xbb2ed720 | 0x1810000 |
| 245 | blk.26.ffn_norm.weight | 0xbcafd720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xbcb01720 | 0x1810000 |
| 247 | blk.27.attn_k.weight | 0xbe311720 | 0x1b8000 |
| 248 | blk.27.attn_norm.weight | 0xbe4c9720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xbe4cd720 | 0xb00000 |
| 250 | blk.27.attn_q.weight | 0xbefcd720 | 0x6e0000 |
| 251 | blk.27.attn_v.weight | 0xbf6ad720 | 0x240000 |
| 252 | blk.27.ffn_down.weight | 0xbf8ed720 | 0x2680000 |
| 253 | blk.27.ffn_gate.weight | 0xc1f6d720 | 0x1810000 |
| 254 | blk.27.ffn_norm.weight | 0xc377d720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xc3781720 | 0x1810000 |
| 256 | blk.28.attn_k.weight | 0xc4f91720 | 0x1b8000 |
| 257 | blk.28.attn_norm.weight | 0xc5149720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xc514d720 | 0xb00000 |
| 259 | blk.28.attn_q.weight | 0xc5c4d720 | 0x6e0000 |
| 260 | blk.28.attn_v.weight | 0xc632d720 | 0x240000 |
| 261 | blk.28.ffn_down.weight | 0xc656d720 | 0x2680000 |
| 262 | blk.28.ffn_gate.weight | 0xc8bed720 | 0x1810000 |
| 263 | blk.28.ffn_norm.weight | 0xca3fd720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xca401720 | 0x1810000 |
| 265 | blk.29.attn_k.weight | 0xcbc11720 | 0x1b8000 |
| 266 | blk.29.attn_norm.weight | 0xcbdc9720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xcbdcd720 | 0xb00000 |
| 268 | blk.29.attn_q.weight | 0xcc8cd720 | 0x6e0000 |
| 269 | blk.29.attn_v.weight | 0xccfad720 | 0x240000 |
| 270 | blk.29.ffn_down.weight | 0xcd1ed720 | 0x2680000 |
| 271 | blk.29.ffn_gate.weight | 0xcf86d720 | 0x1810000 |
| 272 | blk.29.ffn_norm.weight | 0xd107d720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xd1081720 | 0x1810000 |
| 274 | blk.30.attn_k.weight | 0xd2891720 | 0x1b8000 |
| 275 | blk.30.attn_norm.weight | 0xd2a49720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xd2a4d720 | 0xb00000 |
| 277 | blk.30.attn_q.weight | 0xd354d720 | 0x6e0000 |
| 278 | blk.30.attn_v.weight | 0xd3c2d720 | 0x240000 |
| 279 | blk.30.ffn_down.weight | 0xd3e6d720 | 0x2680000 |
| 280 | blk.30.ffn_gate.weight | 0xd64ed720 | 0x1810000 |
| 281 | blk.30.ffn_norm.weight | 0xd7cfd720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xd7d01720 | 0x1810000 |
| 283 | blk.31.attn_k.weight | 0xd9511720 | 0x150000 |
| 284 | blk.31.attn_norm.weight | 0xd9661720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xd9665720 | 0xb00000 |
| 286 | blk.31.attn_q.weight | 0xda165720 | 0x540000 |
| 287 | blk.31.attn_v.weight | 0xda6a5720 | 0x240000 |
| 288 | blk.31.ffn_down.weight | 0xda8e5720 | 0x2680000 |
| 289 | blk.31.ffn_gate.weight | 0xdcf65720 | 0x1810000 |
| 290 | blk.31.ffn_norm.weight | 0xde775720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0xde779720 | 0x1810000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q3_K_M.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q3_K_M.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 12 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q3\_K\_M.gguf - GGUF Internal File Dump](#watt-tool-8b-q3_k_mgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0xd746000 |
| 1 | output_norm.weight | 0xdebf620 | 0x4000 |
| 2 | rope_freqs.weight | 0xdec3620 | 0x100 |
| 3 | token_embd.weight | 0xdec3720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x1b609720 | 0x150000 |
| 5 | blk.0.attn_norm.weight | 0x1b759720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1b75d720 | 0x900000 |
| 7 | blk.0.attn_q.weight | 0x1c05d720 | 0x540000 |
| 8 | blk.0.attn_v.weight | 0x1c59d720 | 0x1b8000 |
| 9 | blk.0.ffn_down.weight | 0x1c755720 | 0x1f80000 |
| 10 | blk.0.ffn_gate.weight | 0x1e6d5720 | 0x1260000 |
| 11 | blk.0.ffn_norm.weight | 0x1f935720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x1f939720 | 0x1260000 |
| 13 | blk.1.attn_k.weight | 0x20b99720 | 0x150000 |
| 14 | blk.1.attn_norm.weight | 0x20ce9720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x20ced720 | 0x900000 |
| 16 | blk.1.attn_q.weight | 0x215ed720 | 0x540000 |
| 17 | blk.1.attn_v.weight | 0x21b2d720 | 0x1b8000 |
| 18 | blk.1.ffn_down.weight | 0x21ce5720 | 0x1f80000 |
| 19 | blk.1.ffn_gate.weight | 0x23c65720 | 0x1260000 |
| 20 | blk.1.ffn_norm.weight | 0x24ec5720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x24ec9720 | 0x1260000 |
| 22 | blk.2.attn_k.weight | 0x26129720 | 0x150000 |
| 23 | blk.2.attn_norm.weight | 0x26279720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x2627d720 | 0x900000 |
| 25 | blk.2.attn_q.weight | 0x26b7d720 | 0x540000 |
| 26 | blk.2.attn_v.weight | 0x270bd720 | 0x1b8000 |
| 27 | blk.2.ffn_down.weight | 0x27275720 | 0x1f80000 |
| 28 | blk.2.ffn_gate.weight | 0x291f5720 | 0x1260000 |
| 29 | blk.2.ffn_norm.weight | 0x2a455720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x2a459720 | 0x1260000 |
| 31 | blk.3.attn_k.weight | 0x2b6b9720 | 0x150000 |
| 32 | blk.3.attn_norm.weight | 0x2b809720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x2b80d720 | 0x900000 |
| 34 | blk.3.attn_q.weight | 0x2c10d720 | 0x540000 |
| 35 | blk.3.attn_v.weight | 0x2c64d720 | 0x1b8000 |
| 36 | blk.3.ffn_down.weight | 0x2c805720 | 0x1f80000 |
| 37 | blk.3.ffn_gate.weight | 0x2e785720 | 0x1260000 |
| 38 | blk.3.ffn_norm.weight | 0x2f9e5720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x2f9e9720 | 0x1260000 |
| 40 | blk.4.attn_k.weight | 0x30c49720 | 0x150000 |
| 41 | blk.4.attn_norm.weight | 0x30d99720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x30d9d720 | 0x900000 |
| 43 | blk.4.attn_q.weight | 0x3169d720 | 0x540000 |
| 44 | blk.4.attn_v.weight | 0x31bdd720 | 0x1b8000 |
| 45 | blk.4.ffn_down.weight | 0x31d95720 | 0x1f80000 |
| 46 | blk.4.ffn_gate.weight | 0x33d15720 | 0x1260000 |
| 47 | blk.4.ffn_norm.weight | 0x34f75720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x34f79720 | 0x1260000 |
| 49 | blk.5.attn_k.weight | 0x361d9720 | 0x150000 |
| 50 | blk.5.attn_norm.weight | 0x36329720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x3632d720 | 0x900000 |
| 52 | blk.5.attn_q.weight | 0x36c2d720 | 0x540000 |
| 53 | blk.5.attn_v.weight | 0x3716d720 | 0x1b8000 |
| 54 | blk.5.ffn_down.weight | 0x37325720 | 0x1f80000 |
| 55 | blk.5.ffn_gate.weight | 0x392a5720 | 0x1260000 |
| 56 | blk.5.ffn_norm.weight | 0x3a505720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x3a509720 | 0x1260000 |
| 58 | blk.6.attn_k.weight | 0x3b769720 | 0x150000 |
| 59 | blk.6.attn_norm.weight | 0x3b8b9720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x3b8bd720 | 0x900000 |
| 61 | blk.6.attn_q.weight | 0x3c1bd720 | 0x540000 |
| 62 | blk.6.attn_v.weight | 0x3c6fd720 | 0x1b8000 |
| 63 | blk.6.ffn_down.weight | 0x3c8b5720 | 0x1f80000 |
| 64 | blk.6.ffn_gate.weight | 0x3e835720 | 0x1260000 |
| 65 | blk.6.ffn_norm.weight | 0x3fa95720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x3fa99720 | 0x1260000 |
| 67 | blk.7.attn_k.weight | 0x40cf9720 | 0x150000 |
| 68 | blk.7.attn_norm.weight | 0x40e49720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x40e4d720 | 0x900000 |
| 70 | blk.7.attn_q.weight | 0x4174d720 | 0x540000 |
| 71 | blk.7.attn_v.weight | 0x41c8d720 | 0x1b8000 |
| 72 | blk.7.ffn_down.weight | 0x41e45720 | 0x1f80000 |
| 73 | blk.7.ffn_gate.weight | 0x43dc5720 | 0x1260000 |
| 74 | blk.7.ffn_norm.weight | 0x45025720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x45029720 | 0x1260000 |
| 76 | blk.8.attn_k.weight | 0x46289720 | 0x150000 |
| 77 | blk.8.attn_norm.weight | 0x463d9720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x463dd720 | 0x900000 |
| 79 | blk.8.attn_q.weight | 0x46cdd720 | 0x540000 |
| 80 | blk.8.attn_v.weight | 0x4721d720 | 0x1b8000 |
| 81 | blk.8.ffn_down.weight | 0x473d5720 | 0x1f80000 |
| 82 | blk.8.ffn_gate.weight | 0x49355720 | 0x1260000 |
| 83 | blk.8.ffn_norm.weight | 0x4a5b5720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x4a5b9720 | 0x1260000 |
| 85 | blk.9.attn_k.weight | 0x4b819720 | 0x150000 |
| 86 | blk.9.attn_norm.weight | 0x4b969720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x4b96d720 | 0x900000 |
| 88 | blk.9.attn_q.weight | 0x4c26d720 | 0x540000 |
| 89 | blk.9.attn_v.weight | 0x4c7ad720 | 0x1b8000 |
| 90 | blk.9.ffn_down.weight | 0x4c965720 | 0x1f80000 |
| 91 | blk.9.ffn_gate.weight | 0x4e8e5720 | 0x1260000 |
| 92 | blk.9.ffn_norm.weight | 0x4fb45720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x4fb49720 | 0x1260000 |
| 94 | blk.10.attn_k.weight | 0x50da9720 | 0x150000 |
| 95 | blk.10.attn_norm.weight | 0x50ef9720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x50efd720 | 0x900000 |
| 97 | blk.10.attn_q.weight | 0x517fd720 | 0x540000 |
| 98 | blk.10.attn_v.weight | 0x51d3d720 | 0x1b8000 |
| 99 | blk.10.ffn_down.weight | 0x51ef5720 | 0x1f80000 |
| 100 | blk.10.ffn_gate.weight | 0x53e75720 | 0x1260000 |
| 101 | blk.10.ffn_norm.weight | 0x550d5720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x550d9720 | 0x1260000 |
| 103 | blk.11.attn_k.weight | 0x56339720 | 0x150000 |
| 104 | blk.11.attn_norm.weight | 0x56489720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x5648d720 | 0x900000 |
| 106 | blk.11.attn_q.weight | 0x56d8d720 | 0x540000 |
| 107 | blk.11.attn_v.weight | 0x572cd720 | 0x1b8000 |
| 108 | blk.11.ffn_down.weight | 0x57485720 | 0x1f80000 |
| 109 | blk.11.ffn_gate.weight | 0x59405720 | 0x1260000 |
| 110 | blk.11.ffn_norm.weight | 0x5a665720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x5a669720 | 0x1260000 |
| 112 | blk.12.attn_k.weight | 0x5b8c9720 | 0x150000 |
| 113 | blk.12.attn_norm.weight | 0x5ba19720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x5ba1d720 | 0x900000 |
| 115 | blk.12.attn_q.weight | 0x5c31d720 | 0x540000 |
| 116 | blk.12.attn_v.weight | 0x5c85d720 | 0x1b8000 |
| 117 | blk.12.ffn_down.weight | 0x5ca15720 | 0x1f80000 |
| 118 | blk.12.ffn_gate.weight | 0x5e995720 | 0x1260000 |
| 119 | blk.12.ffn_norm.weight | 0x5fbf5720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x5fbf9720 | 0x1260000 |
| 121 | blk.13.attn_k.weight | 0x60e59720 | 0x1b8000 |
| 122 | blk.13.attn_norm.weight | 0x61011720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x61015720 | 0x900000 |
| 124 | blk.13.attn_q.weight | 0x61915720 | 0x6e0000 |
| 125 | blk.13.attn_v.weight | 0x61ff5720 | 0x240000 |
| 126 | blk.13.ffn_down.weight | 0x62235720 | 0x1f80000 |
| 127 | blk.13.ffn_gate.weight | 0x641b5720 | 0x1260000 |
| 128 | blk.13.ffn_norm.weight | 0x65415720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x65419720 | 0x1260000 |
| 130 | blk.14.attn_k.weight | 0x66679720 | 0x1b8000 |
| 131 | blk.14.attn_norm.weight | 0x66831720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x66835720 | 0x900000 |
| 133 | blk.14.attn_q.weight | 0x67135720 | 0x6e0000 |
| 134 | blk.14.attn_v.weight | 0x67815720 | 0x240000 |
| 135 | blk.14.ffn_down.weight | 0x67a55720 | 0x1f80000 |
| 136 | blk.14.ffn_gate.weight | 0x699d5720 | 0x1260000 |
| 137 | blk.14.ffn_norm.weight | 0x6ac35720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x6ac39720 | 0x1260000 |
| 139 | blk.15.attn_k.weight | 0x6be99720 | 0x150000 |
| 140 | blk.15.attn_norm.weight | 0x6bfe9720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x6bfed720 | 0x900000 |
| 142 | blk.15.attn_q.weight | 0x6c8ed720 | 0x540000 |
| 143 | blk.15.attn_v.weight | 0x6ce2d720 | 0x1b8000 |
| 144 | blk.15.ffn_down.weight | 0x6cfe5720 | 0x1f80000 |
| 145 | blk.15.ffn_gate.weight | 0x6ef65720 | 0x1260000 |
| 146 | blk.15.ffn_norm.weight | 0x701c5720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x701c9720 | 0x1260000 |
| 148 | blk.16.attn_k.weight | 0x71429720 | 0x1b8000 |
| 149 | blk.16.attn_norm.weight | 0x715e1720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x715e5720 | 0x900000 |
| 151 | blk.16.attn_q.weight | 0x71ee5720 | 0x6e0000 |
| 152 | blk.16.attn_v.weight | 0x725c5720 | 0x240000 |
| 153 | blk.16.ffn_down.weight | 0x72805720 | 0x1f80000 |
| 154 | blk.16.ffn_gate.weight | 0x74785720 | 0x1810000 |
| 155 | blk.16.ffn_norm.weight | 0x75f95720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x75f99720 | 0x1810000 |
| 157 | blk.17.attn_k.weight | 0x777a9720 | 0x150000 |
| 158 | blk.17.attn_norm.weight | 0x778f9720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x778fd720 | 0x900000 |
| 160 | blk.17.attn_q.weight | 0x781fd720 | 0x540000 |
| 161 | blk.17.attn_v.weight | 0x7873d720 | 0x1b8000 |
| 162 | blk.17.ffn_down.weight | 0x788f5720 | 0x1f80000 |
| 163 | blk.17.ffn_gate.weight | 0x7a875720 | 0x1810000 |
| 164 | blk.17.ffn_norm.weight | 0x7c085720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x7c089720 | 0x1810000 |
| 166 | blk.18.attn_k.weight | 0x7d899720 | 0x1b8000 |
| 167 | blk.18.attn_norm.weight | 0x7da51720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x7da55720 | 0x900000 |
| 169 | blk.18.attn_q.weight | 0x7e355720 | 0x6e0000 |
| 170 | blk.18.attn_v.weight | 0x7ea35720 | 0x240000 |
| 171 | blk.18.ffn_down.weight | 0x7ec75720 | 0x1f80000 |
| 172 | blk.18.ffn_gate.weight | 0x80bf5720 | 0x1810000 |
| 173 | blk.18.ffn_norm.weight | 0x82405720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x82409720 | 0x1810000 |
| 175 | blk.19.attn_k.weight | 0x83c19720 | 0x1b8000 |
| 176 | blk.19.attn_norm.weight | 0x83dd1720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x83dd5720 | 0x900000 |
| 178 | blk.19.attn_q.weight | 0x846d5720 | 0x6e0000 |
| 179 | blk.19.attn_v.weight | 0x84db5720 | 0x240000 |
| 180 | blk.19.ffn_down.weight | 0x84ff5720 | 0x1f80000 |
| 181 | blk.19.ffn_gate.weight | 0x86f75720 | 0x1810000 |
| 182 | blk.19.ffn_norm.weight | 0x88785720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0x88789720 | 0x1810000 |
| 184 | blk.20.attn_k.weight | 0x89f99720 | 0x1b8000 |
| 185 | blk.20.attn_norm.weight | 0x8a151720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0x8a155720 | 0x900000 |
| 187 | blk.20.attn_q.weight | 0x8aa55720 | 0x6e0000 |
| 188 | blk.20.attn_v.weight | 0x8b135720 | 0x240000 |
| 189 | blk.20.ffn_down.weight | 0x8b375720 | 0x1f80000 |
| 190 | blk.20.ffn_gate.weight | 0x8d2f5720 | 0x1810000 |
| 191 | blk.20.ffn_norm.weight | 0x8eb05720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x8eb09720 | 0x1810000 |
| 193 | blk.21.attn_k.weight | 0x90319720 | 0x1b8000 |
| 194 | blk.21.attn_norm.weight | 0x904d1720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x904d5720 | 0x900000 |
| 196 | blk.21.attn_q.weight | 0x90dd5720 | 0x6e0000 |
| 197 | blk.21.attn_v.weight | 0x914b5720 | 0x240000 |
| 198 | blk.21.ffn_down.weight | 0x916f5720 | 0x1f80000 |
| 199 | blk.21.ffn_gate.weight | 0x93675720 | 0x1810000 |
| 200 | blk.21.ffn_norm.weight | 0x94e85720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x94e89720 | 0x1810000 |
| 202 | blk.22.attn_k.weight | 0x96699720 | 0x1b8000 |
| 203 | blk.22.attn_norm.weight | 0x96851720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x96855720 | 0x900000 |
| 205 | blk.22.attn_q.weight | 0x97155720 | 0x6e0000 |
| 206 | blk.22.attn_v.weight | 0x97835720 | 0x240000 |
| 207 | blk.22.ffn_down.weight | 0x97a75720 | 0x1f80000 |
| 208 | blk.22.ffn_gate.weight | 0x999f5720 | 0x1810000 |
| 209 | blk.22.ffn_norm.weight | 0x9b205720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0x9b209720 | 0x1810000 |
| 211 | blk.23.attn_k.weight | 0x9ca19720 | 0x1b8000 |
| 212 | blk.23.attn_norm.weight | 0x9cbd1720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0x9cbd5720 | 0x900000 |
| 214 | blk.23.attn_q.weight | 0x9d4d5720 | 0x6e0000 |
| 215 | blk.23.attn_v.weight | 0x9dbb5720 | 0x240000 |
| 216 | blk.23.ffn_down.weight | 0x9ddf5720 | 0x1f80000 |
| 217 | blk.23.ffn_gate.weight | 0x9fd75720 | 0x1810000 |
| 218 | blk.23.ffn_norm.weight | 0xa1585720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xa1589720 | 0x1810000 |
| 220 | blk.24.attn_k.weight | 0xa2d99720 | 0x1b8000 |
| 221 | blk.24.attn_norm.weight | 0xa2f51720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xa2f55720 | 0x900000 |
| 223 | blk.24.attn_q.weight | 0xa3855720 | 0x6e0000 |
| 224 | blk.24.attn_v.weight | 0xa3f35720 | 0x240000 |
| 225 | blk.24.ffn_down.weight | 0xa4175720 | 0x1f80000 |
| 226 | blk.24.ffn_gate.weight | 0xa60f5720 | 0x1810000 |
| 227 | blk.24.ffn_norm.weight | 0xa7905720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xa7909720 | 0x1810000 |
| 229 | blk.25.attn_k.weight | 0xa9119720 | 0x1b8000 |
| 230 | blk.25.attn_norm.weight | 0xa92d1720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xa92d5720 | 0x900000 |
| 232 | blk.25.attn_q.weight | 0xa9bd5720 | 0x6e0000 |
| 233 | blk.25.attn_v.weight | 0xaa2b5720 | 0x240000 |
| 234 | blk.25.ffn_down.weight | 0xaa4f5720 | 0x1f80000 |
| 235 | blk.25.ffn_gate.weight | 0xac475720 | 0x1810000 |
| 236 | blk.25.ffn_norm.weight | 0xadc85720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xadc89720 | 0x1810000 |
| 238 | blk.26.attn_k.weight | 0xaf499720 | 0x1b8000 |
| 239 | blk.26.attn_norm.weight | 0xaf651720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xaf655720 | 0x900000 |
| 241 | blk.26.attn_q.weight | 0xaff55720 | 0x6e0000 |
| 242 | blk.26.attn_v.weight | 0xb0635720 | 0x240000 |
| 243 | blk.26.ffn_down.weight | 0xb0875720 | 0x1f80000 |
| 244 | blk.26.ffn_gate.weight | 0xb27f5720 | 0x1810000 |
| 245 | blk.26.ffn_norm.weight | 0xb4005720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xb4009720 | 0x1810000 |
| 247 | blk.27.attn_k.weight | 0xb5819720 | 0x1b8000 |
| 248 | blk.27.attn_norm.weight | 0xb59d1720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xb59d5720 | 0x900000 |
| 250 | blk.27.attn_q.weight | 0xb62d5720 | 0x6e0000 |
| 251 | blk.27.attn_v.weight | 0xb69b5720 | 0x240000 |
| 252 | blk.27.ffn_down.weight | 0xb6bf5720 | 0x1f80000 |
| 253 | blk.27.ffn_gate.weight | 0xb8b75720 | 0x1810000 |
| 254 | blk.27.ffn_norm.weight | 0xba385720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xba389720 | 0x1810000 |
| 256 | blk.28.attn_k.weight | 0xbbb99720 | 0x1b8000 |
| 257 | blk.28.attn_norm.weight | 0xbbd51720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xbbd55720 | 0x900000 |
| 259 | blk.28.attn_q.weight | 0xbc655720 | 0x6e0000 |
| 260 | blk.28.attn_v.weight | 0xbcd35720 | 0x240000 |
| 261 | blk.28.ffn_down.weight | 0xbcf75720 | 0x1f80000 |
| 262 | blk.28.ffn_gate.weight | 0xbeef5720 | 0x1810000 |
| 263 | blk.28.ffn_norm.weight | 0xc0705720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xc0709720 | 0x1810000 |
| 265 | blk.29.attn_k.weight | 0xc1f19720 | 0x1b8000 |
| 266 | blk.29.attn_norm.weight | 0xc20d1720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xc20d5720 | 0x900000 |
| 268 | blk.29.attn_q.weight | 0xc29d5720 | 0x6e0000 |
| 269 | blk.29.attn_v.weight | 0xc30b5720 | 0x240000 |
| 270 | blk.29.ffn_down.weight | 0xc32f5720 | 0x1f80000 |
| 271 | blk.29.ffn_gate.weight | 0xc5275720 | 0x1810000 |
| 272 | blk.29.ffn_norm.weight | 0xc6a85720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xc6a89720 | 0x1810000 |
| 274 | blk.30.attn_k.weight | 0xc8299720 | 0x1b8000 |
| 275 | blk.30.attn_norm.weight | 0xc8451720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xc8455720 | 0x900000 |
| 277 | blk.30.attn_q.weight | 0xc8d55720 | 0x6e0000 |
| 278 | blk.30.attn_v.weight | 0xc9435720 | 0x240000 |
| 279 | blk.30.ffn_down.weight | 0xc9675720 | 0x1f80000 |
| 280 | blk.30.ffn_gate.weight | 0xcb5f5720 | 0x1810000 |
| 281 | blk.30.ffn_norm.weight | 0xcce05720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xcce09720 | 0x1810000 |
| 283 | blk.31.attn_k.weight | 0xce619720 | 0x150000 |
| 284 | blk.31.attn_norm.weight | 0xce769720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xce76d720 | 0x900000 |
| 286 | blk.31.attn_q.weight | 0xcf06d720 | 0x540000 |
| 287 | blk.31.attn_v.weight | 0xcf5ad720 | 0x1b8000 |
| 288 | blk.31.ffn_down.weight | 0xcf765720 | 0x1f80000 |
| 289 | blk.31.ffn_gate.weight | 0xd16e5720 | 0x1810000 |
| 290 | blk.31.ffn_norm.weight | 0xd2ef5720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0xd2ef9720 | 0x1810000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q3_K_S.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q3_K_S.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 11 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q3\_K\_S.gguf - GGUF Internal File Dump](#watt-tool-8b-q3_k_sgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0xd746000 |
| 1 | output_norm.weight | 0xdebf620 | 0x4000 |
| 2 | rope_freqs.weight | 0xdec3620 | 0x100 |
| 3 | token_embd.weight | 0xdec3720 | 0xa464000 |
| 4 | blk.0.attn_k.weight | 0x18327720 | 0x150000 |
| 5 | blk.0.attn_norm.weight | 0x18477720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1847b720 | 0x6e0000 |
| 7 | blk.0.attn_q.weight | 0x18b5b720 | 0x540000 |
| 8 | blk.0.attn_v.weight | 0x1909b720 | 0x1b8000 |
| 9 | blk.0.ffn_down.weight | 0x19253720 | 0x1810000 |
| 10 | blk.0.ffn_gate.weight | 0x1aa63720 | 0x1260000 |
| 11 | blk.0.ffn_norm.weight | 0x1bcc3720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x1bcc7720 | 0x1260000 |
| 13 | blk.1.attn_k.weight | 0x1cf27720 | 0x150000 |
| 14 | blk.1.attn_norm.weight | 0x1d077720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x1d07b720 | 0x6e0000 |
| 16 | blk.1.attn_q.weight | 0x1d75b720 | 0x540000 |
| 17 | blk.1.attn_v.weight | 0x1dc9b720 | 0x1b8000 |
| 18 | blk.1.ffn_down.weight | 0x1de53720 | 0x1f80000 |
| 19 | blk.1.ffn_gate.weight | 0x1fdd3720 | 0x1260000 |
| 20 | blk.1.ffn_norm.weight | 0x21033720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x21037720 | 0x1260000 |
| 22 | blk.2.attn_k.weight | 0x22297720 | 0x150000 |
| 23 | blk.2.attn_norm.weight | 0x223e7720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x223eb720 | 0x6e0000 |
| 25 | blk.2.attn_q.weight | 0x22acb720 | 0x540000 |
| 26 | blk.2.attn_v.weight | 0x2300b720 | 0x1b8000 |
| 27 | blk.2.ffn_down.weight | 0x231c3720 | 0x1810000 |
| 28 | blk.2.ffn_gate.weight | 0x249d3720 | 0x1260000 |
| 29 | blk.2.ffn_norm.weight | 0x25c33720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x25c37720 | 0x1260000 |
| 31 | blk.3.attn_k.weight | 0x26e97720 | 0x150000 |
| 32 | blk.3.attn_norm.weight | 0x26fe7720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x26feb720 | 0x6e0000 |
| 34 | blk.3.attn_q.weight | 0x276cb720 | 0x540000 |
| 35 | blk.3.attn_v.weight | 0x27c0b720 | 0x1b8000 |
| 36 | blk.3.ffn_down.weight | 0x27dc3720 | 0x1810000 |
| 37 | blk.3.ffn_gate.weight | 0x295d3720 | 0x1260000 |
| 38 | blk.3.ffn_norm.weight | 0x2a833720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x2a837720 | 0x1260000 |
| 40 | blk.4.attn_k.weight | 0x2ba97720 | 0x150000 |
| 41 | blk.4.attn_norm.weight | 0x2bbe7720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x2bbeb720 | 0x6e0000 |
| 43 | blk.4.attn_q.weight | 0x2c2cb720 | 0x540000 |
| 44 | blk.4.attn_v.weight | 0x2c80b720 | 0x1b8000 |
| 45 | blk.4.ffn_down.weight | 0x2c9c3720 | 0x1810000 |
| 46 | blk.4.ffn_gate.weight | 0x2e1d3720 | 0x1260000 |
| 47 | blk.4.ffn_norm.weight | 0x2f433720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x2f437720 | 0x1260000 |
| 49 | blk.5.attn_k.weight | 0x30697720 | 0x150000 |
| 50 | blk.5.attn_norm.weight | 0x307e7720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x307eb720 | 0x6e0000 |
| 52 | blk.5.attn_q.weight | 0x30ecb720 | 0x540000 |
| 53 | blk.5.attn_v.weight | 0x3140b720 | 0x1b8000 |
| 54 | blk.5.ffn_down.weight | 0x315c3720 | 0x1810000 |
| 55 | blk.5.ffn_gate.weight | 0x32dd3720 | 0x1260000 |
| 56 | blk.5.ffn_norm.weight | 0x34033720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x34037720 | 0x1260000 |
| 58 | blk.6.attn_k.weight | 0x35297720 | 0x150000 |
| 59 | blk.6.attn_norm.weight | 0x353e7720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x353eb720 | 0x6e0000 |
| 61 | blk.6.attn_q.weight | 0x35acb720 | 0x540000 |
| 62 | blk.6.attn_v.weight | 0x3600b720 | 0x1b8000 |
| 63 | blk.6.ffn_down.weight | 0x361c3720 | 0x1810000 |
| 64 | blk.6.ffn_gate.weight | 0x379d3720 | 0x1260000 |
| 65 | blk.6.ffn_norm.weight | 0x38c33720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x38c37720 | 0x1260000 |
| 67 | blk.7.attn_k.weight | 0x39e97720 | 0x150000 |
| 68 | blk.7.attn_norm.weight | 0x39fe7720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x39feb720 | 0x6e0000 |
| 70 | blk.7.attn_q.weight | 0x3a6cb720 | 0x540000 |
| 71 | blk.7.attn_v.weight | 0x3ac0b720 | 0x1b8000 |
| 72 | blk.7.ffn_down.weight | 0x3adc3720 | 0x1810000 |
| 73 | blk.7.ffn_gate.weight | 0x3c5d3720 | 0x1260000 |
| 74 | blk.7.ffn_norm.weight | 0x3d833720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x3d837720 | 0x1260000 |
| 76 | blk.8.attn_k.weight | 0x3ea97720 | 0x150000 |
| 77 | blk.8.attn_norm.weight | 0x3ebe7720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x3ebeb720 | 0x6e0000 |
| 79 | blk.8.attn_q.weight | 0x3f2cb720 | 0x540000 |
| 80 | blk.8.attn_v.weight | 0x3f80b720 | 0x1b8000 |
| 81 | blk.8.ffn_down.weight | 0x3f9c3720 | 0x1810000 |
| 82 | blk.8.ffn_gate.weight | 0x411d3720 | 0x1260000 |
| 83 | blk.8.ffn_norm.weight | 0x42433720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x42437720 | 0x1260000 |
| 85 | blk.9.attn_k.weight | 0x43697720 | 0x150000 |
| 86 | blk.9.attn_norm.weight | 0x437e7720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x437eb720 | 0x6e0000 |
| 88 | blk.9.attn_q.weight | 0x43ecb720 | 0x540000 |
| 89 | blk.9.attn_v.weight | 0x4440b720 | 0x1b8000 |
| 90 | blk.9.ffn_down.weight | 0x445c3720 | 0x1810000 |
| 91 | blk.9.ffn_gate.weight | 0x45dd3720 | 0x1260000 |
| 92 | blk.9.ffn_norm.weight | 0x47033720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x47037720 | 0x1260000 |
| 94 | blk.10.attn_k.weight | 0x48297720 | 0x150000 |
| 95 | blk.10.attn_norm.weight | 0x483e7720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x483eb720 | 0x6e0000 |
| 97 | blk.10.attn_q.weight | 0x48acb720 | 0x540000 |
| 98 | blk.10.attn_v.weight | 0x4900b720 | 0x1b8000 |
| 99 | blk.10.ffn_down.weight | 0x491c3720 | 0x1810000 |
| 100 | blk.10.ffn_gate.weight | 0x4a9d3720 | 0x1260000 |
| 101 | blk.10.ffn_norm.weight | 0x4bc33720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x4bc37720 | 0x1260000 |
| 103 | blk.11.attn_k.weight | 0x4ce97720 | 0x150000 |
| 104 | blk.11.attn_norm.weight | 0x4cfe7720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x4cfeb720 | 0x6e0000 |
| 106 | blk.11.attn_q.weight | 0x4d6cb720 | 0x540000 |
| 107 | blk.11.attn_v.weight | 0x4dc0b720 | 0x1b8000 |
| 108 | blk.11.ffn_down.weight | 0x4ddc3720 | 0x1810000 |
| 109 | blk.11.ffn_gate.weight | 0x4f5d3720 | 0x1260000 |
| 110 | blk.11.ffn_norm.weight | 0x50833720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x50837720 | 0x1260000 |
| 112 | blk.12.attn_k.weight | 0x51a97720 | 0x150000 |
| 113 | blk.12.attn_norm.weight | 0x51be7720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x51beb720 | 0x6e0000 |
| 115 | blk.12.attn_q.weight | 0x522cb720 | 0x540000 |
| 116 | blk.12.attn_v.weight | 0x5280b720 | 0x1b8000 |
| 117 | blk.12.ffn_down.weight | 0x529c3720 | 0x1810000 |
| 118 | blk.12.ffn_gate.weight | 0x541d3720 | 0x1260000 |
| 119 | blk.12.ffn_norm.weight | 0x55433720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x55437720 | 0x1260000 |
| 121 | blk.13.attn_k.weight | 0x56697720 | 0x1b8000 |
| 122 | blk.13.attn_norm.weight | 0x5684f720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x56853720 | 0x6e0000 |
| 124 | blk.13.attn_q.weight | 0x56f33720 | 0x6e0000 |
| 125 | blk.13.attn_v.weight | 0x57613720 | 0x1b8000 |
| 126 | blk.13.ffn_down.weight | 0x577cb720 | 0x1810000 |
| 127 | blk.13.ffn_gate.weight | 0x58fdb720 | 0x1260000 |
| 128 | blk.13.ffn_norm.weight | 0x5a23b720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x5a23f720 | 0x1260000 |
| 130 | blk.14.attn_k.weight | 0x5b49f720 | 0x1b8000 |
| 131 | blk.14.attn_norm.weight | 0x5b657720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x5b65b720 | 0x6e0000 |
| 133 | blk.14.attn_q.weight | 0x5bd3b720 | 0x6e0000 |
| 134 | blk.14.attn_v.weight | 0x5c41b720 | 0x1b8000 |
| 135 | blk.14.ffn_down.weight | 0x5c5d3720 | 0x1810000 |
| 136 | blk.14.ffn_gate.weight | 0x5dde3720 | 0x1260000 |
| 137 | blk.14.ffn_norm.weight | 0x5f043720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x5f047720 | 0x1260000 |
| 139 | blk.15.attn_k.weight | 0x602a7720 | 0x150000 |
| 140 | blk.15.attn_norm.weight | 0x603f7720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x603fb720 | 0x6e0000 |
| 142 | blk.15.attn_q.weight | 0x60adb720 | 0x540000 |
| 143 | blk.15.attn_v.weight | 0x6101b720 | 0x1b8000 |
| 144 | blk.15.ffn_down.weight | 0x611d3720 | 0x1810000 |
| 145 | blk.15.ffn_gate.weight | 0x629e3720 | 0x1260000 |
| 146 | blk.15.ffn_norm.weight | 0x63c43720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x63c47720 | 0x1260000 |
| 148 | blk.16.attn_k.weight | 0x64ea7720 | 0x1b8000 |
| 149 | blk.16.attn_norm.weight | 0x6505f720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x65063720 | 0x6e0000 |
| 151 | blk.16.attn_q.weight | 0x65743720 | 0x6e0000 |
| 152 | blk.16.attn_v.weight | 0x65e23720 | 0x1b8000 |
| 153 | blk.16.ffn_down.weight | 0x65fdb720 | 0x1810000 |
| 154 | blk.16.ffn_gate.weight | 0x677eb720 | 0x1810000 |
| 155 | blk.16.ffn_norm.weight | 0x68ffb720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x68fff720 | 0x1810000 |
| 157 | blk.17.attn_k.weight | 0x6a80f720 | 0x150000 |
| 158 | blk.17.attn_norm.weight | 0x6a95f720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x6a963720 | 0x6e0000 |
| 160 | blk.17.attn_q.weight | 0x6b043720 | 0x540000 |
| 161 | blk.17.attn_v.weight | 0x6b583720 | 0x1b8000 |
| 162 | blk.17.ffn_down.weight | 0x6b73b720 | 0x1f80000 |
| 163 | blk.17.ffn_gate.weight | 0x6d6bb720 | 0x1810000 |
| 164 | blk.17.ffn_norm.weight | 0x6eecb720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x6eecf720 | 0x1810000 |
| 166 | blk.18.attn_k.weight | 0x706df720 | 0x1b8000 |
| 167 | blk.18.attn_norm.weight | 0x70897720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x7089b720 | 0x6e0000 |
| 169 | blk.18.attn_q.weight | 0x70f7b720 | 0x6e0000 |
| 170 | blk.18.attn_v.weight | 0x7165b720 | 0x1b8000 |
| 171 | blk.18.ffn_down.weight | 0x71813720 | 0x1f80000 |
| 172 | blk.18.ffn_gate.weight | 0x73793720 | 0x1810000 |
| 173 | blk.18.ffn_norm.weight | 0x74fa3720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x74fa7720 | 0x1810000 |
| 175 | blk.19.attn_k.weight | 0x767b7720 | 0x1b8000 |
| 176 | blk.19.attn_norm.weight | 0x7696f720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x76973720 | 0x6e0000 |
| 178 | blk.19.attn_q.weight | 0x77053720 | 0x6e0000 |
| 179 | blk.19.attn_v.weight | 0x77733720 | 0x1b8000 |
| 180 | blk.19.ffn_down.weight | 0x778eb720 | 0x1f80000 |
| 181 | blk.19.ffn_gate.weight | 0x7986b720 | 0x1810000 |
| 182 | blk.19.ffn_norm.weight | 0x7b07b720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0x7b07f720 | 0x1810000 |
| 184 | blk.20.attn_k.weight | 0x7c88f720 | 0x1b8000 |
| 185 | blk.20.attn_norm.weight | 0x7ca47720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0x7ca4b720 | 0x6e0000 |
| 187 | blk.20.attn_q.weight | 0x7d12b720 | 0x6e0000 |
| 188 | blk.20.attn_v.weight | 0x7d80b720 | 0x1b8000 |
| 189 | blk.20.ffn_down.weight | 0x7d9c3720 | 0x1f80000 |
| 190 | blk.20.ffn_gate.weight | 0x7f943720 | 0x1810000 |
| 191 | blk.20.ffn_norm.weight | 0x81153720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x81157720 | 0x1810000 |
| 193 | blk.21.attn_k.weight | 0x82967720 | 0x1b8000 |
| 194 | blk.21.attn_norm.weight | 0x82b1f720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x82b23720 | 0x6e0000 |
| 196 | blk.21.attn_q.weight | 0x83203720 | 0x6e0000 |
| 197 | blk.21.attn_v.weight | 0x838e3720 | 0x1b8000 |
| 198 | blk.21.ffn_down.weight | 0x83a9b720 | 0x1f80000 |
| 199 | blk.21.ffn_gate.weight | 0x85a1b720 | 0x1810000 |
| 200 | blk.21.ffn_norm.weight | 0x8722b720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x8722f720 | 0x1810000 |
| 202 | blk.22.attn_k.weight | 0x88a3f720 | 0x1b8000 |
| 203 | blk.22.attn_norm.weight | 0x88bf7720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x88bfb720 | 0x6e0000 |
| 205 | blk.22.attn_q.weight | 0x892db720 | 0x6e0000 |
| 206 | blk.22.attn_v.weight | 0x899bb720 | 0x1b8000 |
| 207 | blk.22.ffn_down.weight | 0x89b73720 | 0x1f80000 |
| 208 | blk.22.ffn_gate.weight | 0x8baf3720 | 0x1810000 |
| 209 | blk.22.ffn_norm.weight | 0x8d303720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0x8d307720 | 0x1810000 |
| 211 | blk.23.attn_k.weight | 0x8eb17720 | 0x1b8000 |
| 212 | blk.23.attn_norm.weight | 0x8eccf720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0x8ecd3720 | 0x6e0000 |
| 214 | blk.23.attn_q.weight | 0x8f3b3720 | 0x6e0000 |
| 215 | blk.23.attn_v.weight | 0x8fa93720 | 0x1b8000 |
| 216 | blk.23.ffn_down.weight | 0x8fc4b720 | 0x1f80000 |
| 217 | blk.23.ffn_gate.weight | 0x91bcb720 | 0x1810000 |
| 218 | blk.23.ffn_norm.weight | 0x933db720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0x933df720 | 0x1810000 |
| 220 | blk.24.attn_k.weight | 0x94bef720 | 0x1b8000 |
| 221 | blk.24.attn_norm.weight | 0x94da7720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0x94dab720 | 0x6e0000 |
| 223 | blk.24.attn_q.weight | 0x9548b720 | 0x6e0000 |
| 224 | blk.24.attn_v.weight | 0x95b6b720 | 0x1b8000 |
| 225 | blk.24.ffn_down.weight | 0x95d23720 | 0x1f80000 |
| 226 | blk.24.ffn_gate.weight | 0x97ca3720 | 0x1810000 |
| 227 | blk.24.ffn_norm.weight | 0x994b3720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0x994b7720 | 0x1810000 |
| 229 | blk.25.attn_k.weight | 0x9acc7720 | 0x1b8000 |
| 230 | blk.25.attn_norm.weight | 0x9ae7f720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0x9ae83720 | 0x6e0000 |
| 232 | blk.25.attn_q.weight | 0x9b563720 | 0x6e0000 |
| 233 | blk.25.attn_v.weight | 0x9bc43720 | 0x1b8000 |
| 234 | blk.25.ffn_down.weight | 0x9bdfb720 | 0x1f80000 |
| 235 | blk.25.ffn_gate.weight | 0x9dd7b720 | 0x1810000 |
| 236 | blk.25.ffn_norm.weight | 0x9f58b720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0x9f58f720 | 0x1810000 |
| 238 | blk.26.attn_k.weight | 0xa0d9f720 | 0x1b8000 |
| 239 | blk.26.attn_norm.weight | 0xa0f57720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xa0f5b720 | 0x6e0000 |
| 241 | blk.26.attn_q.weight | 0xa163b720 | 0x6e0000 |
| 242 | blk.26.attn_v.weight | 0xa1d1b720 | 0x1b8000 |
| 243 | blk.26.ffn_down.weight | 0xa1ed3720 | 0x1f80000 |
| 244 | blk.26.ffn_gate.weight | 0xa3e53720 | 0x1810000 |
| 245 | blk.26.ffn_norm.weight | 0xa5663720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xa5667720 | 0x1810000 |
| 247 | blk.27.attn_k.weight | 0xa6e77720 | 0x1b8000 |
| 248 | blk.27.attn_norm.weight | 0xa702f720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xa7033720 | 0x6e0000 |
| 250 | blk.27.attn_q.weight | 0xa7713720 | 0x6e0000 |
| 251 | blk.27.attn_v.weight | 0xa7df3720 | 0x1b8000 |
| 252 | blk.27.ffn_down.weight | 0xa7fab720 | 0x1f80000 |
| 253 | blk.27.ffn_gate.weight | 0xa9f2b720 | 0x1810000 |
| 254 | blk.27.ffn_norm.weight | 0xab73b720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xab73f720 | 0x1810000 |
| 256 | blk.28.attn_k.weight | 0xacf4f720 | 0x1b8000 |
| 257 | blk.28.attn_norm.weight | 0xad107720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xad10b720 | 0x6e0000 |
| 259 | blk.28.attn_q.weight | 0xad7eb720 | 0x6e0000 |
| 260 | blk.28.attn_v.weight | 0xadecb720 | 0x1b8000 |
| 261 | blk.28.ffn_down.weight | 0xae083720 | 0x1f80000 |
| 262 | blk.28.ffn_gate.weight | 0xb0003720 | 0x1810000 |
| 263 | blk.28.ffn_norm.weight | 0xb1813720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xb1817720 | 0x1810000 |
| 265 | blk.29.attn_k.weight | 0xb3027720 | 0x1b8000 |
| 266 | blk.29.attn_norm.weight | 0xb31df720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xb31e3720 | 0x6e0000 |
| 268 | blk.29.attn_q.weight | 0xb38c3720 | 0x6e0000 |
| 269 | blk.29.attn_v.weight | 0xb3fa3720 | 0x1b8000 |
| 270 | blk.29.ffn_down.weight | 0xb415b720 | 0x1f80000 |
| 271 | blk.29.ffn_gate.weight | 0xb60db720 | 0x1810000 |
| 272 | blk.29.ffn_norm.weight | 0xb78eb720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xb78ef720 | 0x1810000 |
| 274 | blk.30.attn_k.weight | 0xb90ff720 | 0x1b8000 |
| 275 | blk.30.attn_norm.weight | 0xb92b7720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xb92bb720 | 0x6e0000 |
| 277 | blk.30.attn_q.weight | 0xb999b720 | 0x6e0000 |
| 278 | blk.30.attn_v.weight | 0xba07b720 | 0x1b8000 |
| 279 | blk.30.ffn_down.weight | 0xba233720 | 0x1f80000 |
| 280 | blk.30.ffn_gate.weight | 0xbc1b3720 | 0x1810000 |
| 281 | blk.30.ffn_norm.weight | 0xbd9c3720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xbd9c7720 | 0x1810000 |
| 283 | blk.31.attn_k.weight | 0xbf1d7720 | 0x150000 |
| 284 | blk.31.attn_norm.weight | 0xbf327720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xbf32b720 | 0x6e0000 |
| 286 | blk.31.attn_q.weight | 0xbfa0b720 | 0x540000 |
| 287 | blk.31.attn_v.weight | 0xbff4b720 | 0x1b8000 |
| 288 | blk.31.ffn_down.weight | 0xc0103720 | 0x1f80000 |
| 289 | blk.31.ffn_gate.weight | 0xc2083720 | 0x1810000 |
| 290 | blk.31.ffn_norm.weight | 0xc3893720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0xc3897720 | 0x1810000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q2_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q2_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q3_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q2_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q2_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q4_K_M.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q4_K_M.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 15 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q4\_K\_M.gguf - GGUF Internal File Dump](#watt-tool-8b-q4_k_mgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x119d0000 |
| 1 | output_norm.weight | 0x12149620 | 0x4000 |
| 2 | rope_freqs.weight | 0x1214d620 | 0x100 |
| 3 | token_embd.weight | 0x1214d720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x1f893720 | 0x1b8000 |
| 5 | blk.0.attn_norm.weight | 0x1fa4b720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1fa4f720 | 0x900000 |
| 7 | blk.0.attn_q.weight | 0x2034f720 | 0x6e0000 |
| 8 | blk.0.attn_v.weight | 0x20a2f720 | 0x240000 |
| 9 | blk.0.ffn_down.weight | 0x20c6f720 | 0x2680000 |
| 10 | blk.0.ffn_gate.weight | 0x232ef720 | 0x1810000 |
| 11 | blk.0.ffn_norm.weight | 0x24aff720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x24b03720 | 0x1810000 |
| 13 | blk.1.attn_k.weight | 0x26313720 | 0x1b8000 |
| 14 | blk.1.attn_norm.weight | 0x264cb720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x264cf720 | 0x900000 |
| 16 | blk.1.attn_q.weight | 0x26dcf720 | 0x6e0000 |
| 17 | blk.1.attn_v.weight | 0x274af720 | 0x240000 |
| 18 | blk.1.ffn_down.weight | 0x276ef720 | 0x2680000 |
| 19 | blk.1.ffn_gate.weight | 0x29d6f720 | 0x1810000 |
| 20 | blk.1.ffn_norm.weight | 0x2b57f720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x2b583720 | 0x1810000 |
| 22 | blk.2.attn_k.weight | 0x2cd93720 | 0x1b8000 |
| 23 | blk.2.attn_norm.weight | 0x2cf4b720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x2cf4f720 | 0x900000 |
| 25 | blk.2.attn_q.weight | 0x2d84f720 | 0x6e0000 |
| 26 | blk.2.attn_v.weight | 0x2df2f720 | 0x240000 |
| 27 | blk.2.ffn_down.weight | 0x2e16f720 | 0x2680000 |
| 28 | blk.2.ffn_gate.weight | 0x307ef720 | 0x1810000 |
| 29 | blk.2.ffn_norm.weight | 0x31fff720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x32003720 | 0x1810000 |
| 31 | blk.3.attn_k.weight | 0x33813720 | 0x1b8000 |
| 32 | blk.3.attn_norm.weight | 0x339cb720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x339cf720 | 0x900000 |
| 34 | blk.3.attn_q.weight | 0x342cf720 | 0x6e0000 |
| 35 | blk.3.attn_v.weight | 0x349af720 | 0x240000 |
| 36 | blk.3.ffn_down.weight | 0x34bef720 | 0x2680000 |
| 37 | blk.3.ffn_gate.weight | 0x3726f720 | 0x1810000 |
| 38 | blk.3.ffn_norm.weight | 0x38a7f720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x38a83720 | 0x1810000 |
| 40 | blk.4.attn_k.weight | 0x3a293720 | 0x1b8000 |
| 41 | blk.4.attn_norm.weight | 0x3a44b720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x3a44f720 | 0x900000 |
| 43 | blk.4.attn_q.weight | 0x3ad4f720 | 0x6e0000 |
| 44 | blk.4.attn_v.weight | 0x3b42f720 | 0x240000 |
| 45 | blk.4.ffn_down.weight | 0x3b66f720 | 0x2680000 |
| 46 | blk.4.ffn_gate.weight | 0x3dcef720 | 0x1810000 |
| 47 | blk.4.ffn_norm.weight | 0x3f4ff720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x3f503720 | 0x1810000 |
| 49 | blk.5.attn_k.weight | 0x40d13720 | 0x1b8000 |
| 50 | blk.5.attn_norm.weight | 0x40ecb720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x40ecf720 | 0x900000 |
| 52 | blk.5.attn_q.weight | 0x417cf720 | 0x6e0000 |
| 53 | blk.5.attn_v.weight | 0x41eaf720 | 0x240000 |
| 54 | blk.5.ffn_down.weight | 0x420ef720 | 0x2680000 |
| 55 | blk.5.ffn_gate.weight | 0x4476f720 | 0x1810000 |
| 56 | blk.5.ffn_norm.weight | 0x45f7f720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x45f83720 | 0x1810000 |
| 58 | blk.6.attn_k.weight | 0x47793720 | 0x1b8000 |
| 59 | blk.6.attn_norm.weight | 0x4794b720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x4794f720 | 0x900000 |
| 61 | blk.6.attn_q.weight | 0x4824f720 | 0x6e0000 |
| 62 | blk.6.attn_v.weight | 0x4892f720 | 0x240000 |
| 63 | blk.6.ffn_down.weight | 0x48b6f720 | 0x2680000 |
| 64 | blk.6.ffn_gate.weight | 0x4b1ef720 | 0x1810000 |
| 65 | blk.6.ffn_norm.weight | 0x4c9ff720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x4ca03720 | 0x1810000 |
| 67 | blk.7.attn_k.weight | 0x4e213720 | 0x1b8000 |
| 68 | blk.7.attn_norm.weight | 0x4e3cb720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x4e3cf720 | 0x900000 |
| 70 | blk.7.attn_q.weight | 0x4eccf720 | 0x6e0000 |
| 71 | blk.7.attn_v.weight | 0x4f3af720 | 0x240000 |
| 72 | blk.7.ffn_down.weight | 0x4f5ef720 | 0x2680000 |
| 73 | blk.7.ffn_gate.weight | 0x51c6f720 | 0x1810000 |
| 74 | blk.7.ffn_norm.weight | 0x5347f720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x53483720 | 0x1810000 |
| 76 | blk.8.attn_k.weight | 0x54c93720 | 0x1b8000 |
| 77 | blk.8.attn_norm.weight | 0x54e4b720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x54e4f720 | 0x900000 |
| 79 | blk.8.attn_q.weight | 0x5574f720 | 0x6e0000 |
| 80 | blk.8.attn_v.weight | 0x55e2f720 | 0x240000 |
| 81 | blk.8.ffn_down.weight | 0x5606f720 | 0x2680000 |
| 82 | blk.8.ffn_gate.weight | 0x586ef720 | 0x1810000 |
| 83 | blk.8.ffn_norm.weight | 0x59eff720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x59f03720 | 0x1810000 |
| 85 | blk.9.attn_k.weight | 0x5b713720 | 0x1b8000 |
| 86 | blk.9.attn_norm.weight | 0x5b8cb720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x5b8cf720 | 0x900000 |
| 88 | blk.9.attn_q.weight | 0x5c1cf720 | 0x6e0000 |
| 89 | blk.9.attn_v.weight | 0x5c8af720 | 0x240000 |
| 90 | blk.9.ffn_down.weight | 0x5caef720 | 0x2680000 |
| 91 | blk.9.ffn_gate.weight | 0x5f16f720 | 0x1810000 |
| 92 | blk.9.ffn_norm.weight | 0x6097f720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x60983720 | 0x1810000 |
| 94 | blk.10.attn_k.weight | 0x62193720 | 0x1b8000 |
| 95 | blk.10.attn_norm.weight | 0x6234b720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x6234f720 | 0x900000 |
| 97 | blk.10.attn_q.weight | 0x62c4f720 | 0x6e0000 |
| 98 | blk.10.attn_v.weight | 0x6332f720 | 0x240000 |
| 99 | blk.10.ffn_down.weight | 0x6356f720 | 0x2680000 |
| 100 | blk.10.ffn_gate.weight | 0x65bef720 | 0x1810000 |
| 101 | blk.10.ffn_norm.weight | 0x673ff720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x67403720 | 0x1810000 |
| 103 | blk.11.attn_k.weight | 0x68c13720 | 0x1b8000 |
| 104 | blk.11.attn_norm.weight | 0x68dcb720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x68dcf720 | 0x900000 |
| 106 | blk.11.attn_q.weight | 0x696cf720 | 0x6e0000 |
| 107 | blk.11.attn_v.weight | 0x69daf720 | 0x240000 |
| 108 | blk.11.ffn_down.weight | 0x69fef720 | 0x2680000 |
| 109 | blk.11.ffn_gate.weight | 0x6c66f720 | 0x1810000 |
| 110 | blk.11.ffn_norm.weight | 0x6de7f720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x6de83720 | 0x1810000 |
| 112 | blk.12.attn_k.weight | 0x6f693720 | 0x1b8000 |
| 113 | blk.12.attn_norm.weight | 0x6f84b720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x6f84f720 | 0x900000 |
| 115 | blk.12.attn_q.weight | 0x7014f720 | 0x6e0000 |
| 116 | blk.12.attn_v.weight | 0x7082f720 | 0x240000 |
| 117 | blk.12.ffn_down.weight | 0x70a6f720 | 0x2680000 |
| 118 | blk.12.ffn_gate.weight | 0x730ef720 | 0x1810000 |
| 119 | blk.12.ffn_norm.weight | 0x748ff720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x74903720 | 0x1810000 |
| 121 | blk.13.attn_k.weight | 0x76113720 | 0x240000 |
| 122 | blk.13.attn_norm.weight | 0x76353720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x76357720 | 0x900000 |
| 124 | blk.13.attn_q.weight | 0x76c57720 | 0x900000 |
| 125 | blk.13.attn_v.weight | 0x77557720 | 0x2c0000 |
| 126 | blk.13.ffn_down.weight | 0x77817720 | 0x2680000 |
| 127 | blk.13.ffn_gate.weight | 0x79e97720 | 0x1810000 |
| 128 | blk.13.ffn_norm.weight | 0x7b6a7720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x7b6ab720 | 0x1810000 |
| 130 | blk.14.attn_k.weight | 0x7cebb720 | 0x240000 |
| 131 | blk.14.attn_norm.weight | 0x7d0fb720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x7d0ff720 | 0x900000 |
| 133 | blk.14.attn_q.weight | 0x7d9ff720 | 0x900000 |
| 134 | blk.14.attn_v.weight | 0x7e2ff720 | 0x2c0000 |
| 135 | blk.14.ffn_down.weight | 0x7e5bf720 | 0x2680000 |
| 136 | blk.14.ffn_gate.weight | 0x80c3f720 | 0x1810000 |
| 137 | blk.14.ffn_norm.weight | 0x8244f720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x82453720 | 0x1810000 |
| 139 | blk.15.attn_k.weight | 0x83c63720 | 0x1b8000 |
| 140 | blk.15.attn_norm.weight | 0x83e1b720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x83e1f720 | 0x900000 |
| 142 | blk.15.attn_q.weight | 0x8471f720 | 0x6e0000 |
| 143 | blk.15.attn_v.weight | 0x84dff720 | 0x240000 |
| 144 | blk.15.ffn_down.weight | 0x8503f720 | 0x2680000 |
| 145 | blk.15.ffn_gate.weight | 0x876bf720 | 0x1810000 |
| 146 | blk.15.ffn_norm.weight | 0x88ecf720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x88ed3720 | 0x1810000 |
| 148 | blk.16.attn_k.weight | 0x8a6e3720 | 0x240000 |
| 149 | blk.16.attn_norm.weight | 0x8a923720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x8a927720 | 0x900000 |
| 151 | blk.16.attn_q.weight | 0x8b227720 | 0x900000 |
| 152 | blk.16.attn_v.weight | 0x8bb27720 | 0x2c0000 |
| 153 | blk.16.ffn_down.weight | 0x8bde7720 | 0x2680000 |
| 154 | blk.16.ffn_gate.weight | 0x8e467720 | 0x1f80000 |
| 155 | blk.16.ffn_norm.weight | 0x903e7720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x903eb720 | 0x1f80000 |
| 157 | blk.17.attn_k.weight | 0x9236b720 | 0x1b8000 |
| 158 | blk.17.attn_norm.weight | 0x92523720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x92527720 | 0x900000 |
| 160 | blk.17.attn_q.weight | 0x92e27720 | 0x6e0000 |
| 161 | blk.17.attn_v.weight | 0x93507720 | 0x240000 |
| 162 | blk.17.ffn_down.weight | 0x93747720 | 0x2680000 |
| 163 | blk.17.ffn_gate.weight | 0x95dc7720 | 0x1f80000 |
| 164 | blk.17.ffn_norm.weight | 0x97d47720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x97d4b720 | 0x1f80000 |
| 166 | blk.18.attn_k.weight | 0x99ccb720 | 0x240000 |
| 167 | blk.18.attn_norm.weight | 0x99f0b720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x99f0f720 | 0x900000 |
| 169 | blk.18.attn_q.weight | 0x9a80f720 | 0x900000 |
| 170 | blk.18.attn_v.weight | 0x9b10f720 | 0x2c0000 |
| 171 | blk.18.ffn_down.weight | 0x9b3cf720 | 0x2680000 |
| 172 | blk.18.ffn_gate.weight | 0x9da4f720 | 0x1f80000 |
| 173 | blk.18.ffn_norm.weight | 0x9f9cf720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x9f9d3720 | 0x1f80000 |
| 175 | blk.19.attn_k.weight | 0xa1953720 | 0x240000 |
| 176 | blk.19.attn_norm.weight | 0xa1b93720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0xa1b97720 | 0x900000 |
| 178 | blk.19.attn_q.weight | 0xa2497720 | 0x900000 |
| 179 | blk.19.attn_v.weight | 0xa2d97720 | 0x2c0000 |
| 180 | blk.19.ffn_down.weight | 0xa3057720 | 0x2680000 |
| 181 | blk.19.ffn_gate.weight | 0xa56d7720 | 0x1f80000 |
| 182 | blk.19.ffn_norm.weight | 0xa7657720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0xa765b720 | 0x1f80000 |
| 184 | blk.20.attn_k.weight | 0xa95db720 | 0x240000 |
| 185 | blk.20.attn_norm.weight | 0xa981b720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0xa981f720 | 0x900000 |
| 187 | blk.20.attn_q.weight | 0xaa11f720 | 0x900000 |
| 188 | blk.20.attn_v.weight | 0xaaa1f720 | 0x2c0000 |
| 189 | blk.20.ffn_down.weight | 0xaacdf720 | 0x2680000 |
| 190 | blk.20.ffn_gate.weight | 0xad35f720 | 0x1f80000 |
| 191 | blk.20.ffn_norm.weight | 0xaf2df720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0xaf2e3720 | 0x1f80000 |
| 193 | blk.21.attn_k.weight | 0xb1263720 | 0x240000 |
| 194 | blk.21.attn_norm.weight | 0xb14a3720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0xb14a7720 | 0x900000 |
| 196 | blk.21.attn_q.weight | 0xb1da7720 | 0x900000 |
| 197 | blk.21.attn_v.weight | 0xb26a7720 | 0x2c0000 |
| 198 | blk.21.ffn_down.weight | 0xb2967720 | 0x2680000 |
| 199 | blk.21.ffn_gate.weight | 0xb4fe7720 | 0x1f80000 |
| 200 | blk.21.ffn_norm.weight | 0xb6f67720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0xb6f6b720 | 0x1f80000 |
| 202 | blk.22.attn_k.weight | 0xb8eeb720 | 0x240000 |
| 203 | blk.22.attn_norm.weight | 0xb912b720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0xb912f720 | 0x900000 |
| 205 | blk.22.attn_q.weight | 0xb9a2f720 | 0x900000 |
| 206 | blk.22.attn_v.weight | 0xba32f720 | 0x2c0000 |
| 207 | blk.22.ffn_down.weight | 0xba5ef720 | 0x2680000 |
| 208 | blk.22.ffn_gate.weight | 0xbcc6f720 | 0x1f80000 |
| 209 | blk.22.ffn_norm.weight | 0xbebef720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xbebf3720 | 0x1f80000 |
| 211 | blk.23.attn_k.weight | 0xc0b73720 | 0x240000 |
| 212 | blk.23.attn_norm.weight | 0xc0db3720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xc0db7720 | 0x900000 |
| 214 | blk.23.attn_q.weight | 0xc16b7720 | 0x900000 |
| 215 | blk.23.attn_v.weight | 0xc1fb7720 | 0x2c0000 |
| 216 | blk.23.ffn_down.weight | 0xc2277720 | 0x2680000 |
| 217 | blk.23.ffn_gate.weight | 0xc48f7720 | 0x1f80000 |
| 218 | blk.23.ffn_norm.weight | 0xc6877720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xc687b720 | 0x1f80000 |
| 220 | blk.24.attn_k.weight | 0xc87fb720 | 0x240000 |
| 221 | blk.24.attn_norm.weight | 0xc8a3b720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xc8a3f720 | 0x900000 |
| 223 | blk.24.attn_q.weight | 0xc933f720 | 0x900000 |
| 224 | blk.24.attn_v.weight | 0xc9c3f720 | 0x2c0000 |
| 225 | blk.24.ffn_down.weight | 0xc9eff720 | 0x2680000 |
| 226 | blk.24.ffn_gate.weight | 0xcc57f720 | 0x1f80000 |
| 227 | blk.24.ffn_norm.weight | 0xce4ff720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xce503720 | 0x1f80000 |
| 229 | blk.25.attn_k.weight | 0xd0483720 | 0x240000 |
| 230 | blk.25.attn_norm.weight | 0xd06c3720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xd06c7720 | 0x900000 |
| 232 | blk.25.attn_q.weight | 0xd0fc7720 | 0x900000 |
| 233 | blk.25.attn_v.weight | 0xd18c7720 | 0x2c0000 |
| 234 | blk.25.ffn_down.weight | 0xd1b87720 | 0x2680000 |
| 235 | blk.25.ffn_gate.weight | 0xd4207720 | 0x1f80000 |
| 236 | blk.25.ffn_norm.weight | 0xd6187720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xd618b720 | 0x1f80000 |
| 238 | blk.26.attn_k.weight | 0xd810b720 | 0x240000 |
| 239 | blk.26.attn_norm.weight | 0xd834b720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xd834f720 | 0x900000 |
| 241 | blk.26.attn_q.weight | 0xd8c4f720 | 0x900000 |
| 242 | blk.26.attn_v.weight | 0xd954f720 | 0x2c0000 |
| 243 | blk.26.ffn_down.weight | 0xd980f720 | 0x2680000 |
| 244 | blk.26.ffn_gate.weight | 0xdbe8f720 | 0x1f80000 |
| 245 | blk.26.ffn_norm.weight | 0xdde0f720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xdde13720 | 0x1f80000 |
| 247 | blk.27.attn_k.weight | 0xdfd93720 | 0x240000 |
| 248 | blk.27.attn_norm.weight | 0xdffd3720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xdffd7720 | 0x900000 |
| 250 | blk.27.attn_q.weight | 0xe08d7720 | 0x900000 |
| 251 | blk.27.attn_v.weight | 0xe11d7720 | 0x2c0000 |
| 252 | blk.27.ffn_down.weight | 0xe1497720 | 0x2680000 |
| 253 | blk.27.ffn_gate.weight | 0xe3b17720 | 0x1f80000 |
| 254 | blk.27.ffn_norm.weight | 0xe5a97720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xe5a9b720 | 0x1f80000 |
| 256 | blk.28.attn_k.weight | 0xe7a1b720 | 0x240000 |
| 257 | blk.28.attn_norm.weight | 0xe7c5b720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xe7c5f720 | 0x900000 |
| 259 | blk.28.attn_q.weight | 0xe855f720 | 0x900000 |
| 260 | blk.28.attn_v.weight | 0xe8e5f720 | 0x2c0000 |
| 261 | blk.28.ffn_down.weight | 0xe911f720 | 0x2680000 |
| 262 | blk.28.ffn_gate.weight | 0xeb79f720 | 0x1f80000 |
| 263 | blk.28.ffn_norm.weight | 0xed71f720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xed723720 | 0x1f80000 |
| 265 | blk.29.attn_k.weight | 0xef6a3720 | 0x240000 |
| 266 | blk.29.attn_norm.weight | 0xef8e3720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xef8e7720 | 0x900000 |
| 268 | blk.29.attn_q.weight | 0xf01e7720 | 0x900000 |
| 269 | blk.29.attn_v.weight | 0xf0ae7720 | 0x2c0000 |
| 270 | blk.29.ffn_down.weight | 0xf0da7720 | 0x2680000 |
| 271 | blk.29.ffn_gate.weight | 0xf3427720 | 0x1f80000 |
| 272 | blk.29.ffn_norm.weight | 0xf53a7720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xf53ab720 | 0x1f80000 |
| 274 | blk.30.attn_k.weight | 0xf732b720 | 0x240000 |
| 275 | blk.30.attn_norm.weight | 0xf756b720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xf756f720 | 0x900000 |
| 277 | blk.30.attn_q.weight | 0xf7e6f720 | 0x900000 |
| 278 | blk.30.attn_v.weight | 0xf876f720 | 0x2c0000 |
| 279 | blk.30.ffn_down.weight | 0xf8a2f720 | 0x2680000 |
| 280 | blk.30.ffn_gate.weight | 0xfb0af720 | 0x1f80000 |
| 281 | blk.30.ffn_norm.weight | 0xfd02f720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xfd033720 | 0x1f80000 |
| 283 | blk.31.attn_k.weight | 0xfefb3720 | 0x1b8000 |
| 284 | blk.31.attn_norm.weight | 0xff16b720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xff16f720 | 0x900000 |
| 286 | blk.31.attn_q.weight | 0xffa6f720 | 0x6e0000 |
| 287 | blk.31.attn_v.weight | 0x10014f720 | 0x240000 |
| 288 | blk.31.ffn_down.weight | 0x10038f720 | 0x2680000 |
| 289 | blk.31.ffn_gate.weight | 0x102a0f720 | 0x1f80000 |
| 290 | blk.31.ffn_norm.weight | 0x10498f720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0x104993720 | 0x1f80000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q4_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q4_K_S.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q4_K_S.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 14 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q4\_K\_S.gguf - GGUF Internal File Dump](#watt-tool-8b-q4_k_sgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x119d0000 |
| 1 | output_norm.weight | 0x12149620 | 0x4000 |
| 2 | rope_freqs.weight | 0x1214d620 | 0x100 |
| 3 | token_embd.weight | 0x1214d720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x1f893720 | 0x1b8000 |
| 5 | blk.0.attn_norm.weight | 0x1fa4b720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x1fa4f720 | 0x900000 |
| 7 | blk.0.attn_q.weight | 0x2034f720 | 0x6e0000 |
| 8 | blk.0.attn_v.weight | 0x20a2f720 | 0x240000 |
| 9 | blk.0.ffn_down.weight | 0x20c6f720 | 0x1f80000 |
| 10 | blk.0.ffn_gate.weight | 0x22bef720 | 0x1810000 |
| 11 | blk.0.ffn_norm.weight | 0x243ff720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x24403720 | 0x1810000 |
| 13 | blk.1.attn_k.weight | 0x25c13720 | 0x1b8000 |
| 14 | blk.1.attn_norm.weight | 0x25dcb720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x25dcf720 | 0x900000 |
| 16 | blk.1.attn_q.weight | 0x266cf720 | 0x6e0000 |
| 17 | blk.1.attn_v.weight | 0x26daf720 | 0x240000 |
| 18 | blk.1.ffn_down.weight | 0x26fef720 | 0x2680000 |
| 19 | blk.1.ffn_gate.weight | 0x2966f720 | 0x1810000 |
| 20 | blk.1.ffn_norm.weight | 0x2ae7f720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x2ae83720 | 0x1810000 |
| 22 | blk.2.attn_k.weight | 0x2c693720 | 0x1b8000 |
| 23 | blk.2.attn_norm.weight | 0x2c84b720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x2c84f720 | 0x900000 |
| 25 | blk.2.attn_q.weight | 0x2d14f720 | 0x6e0000 |
| 26 | blk.2.attn_v.weight | 0x2d82f720 | 0x240000 |
| 27 | blk.2.ffn_down.weight | 0x2da6f720 | 0x1f80000 |
| 28 | blk.2.ffn_gate.weight | 0x2f9ef720 | 0x1810000 |
| 29 | blk.2.ffn_norm.weight | 0x311ff720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x31203720 | 0x1810000 |
| 31 | blk.3.attn_k.weight | 0x32a13720 | 0x1b8000 |
| 32 | blk.3.attn_norm.weight | 0x32bcb720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x32bcf720 | 0x900000 |
| 34 | blk.3.attn_q.weight | 0x334cf720 | 0x6e0000 |
| 35 | blk.3.attn_v.weight | 0x33baf720 | 0x240000 |
| 36 | blk.3.ffn_down.weight | 0x33def720 | 0x1f80000 |
| 37 | blk.3.ffn_gate.weight | 0x35d6f720 | 0x1810000 |
| 38 | blk.3.ffn_norm.weight | 0x3757f720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x37583720 | 0x1810000 |
| 40 | blk.4.attn_k.weight | 0x38d93720 | 0x1b8000 |
| 41 | blk.4.attn_norm.weight | 0x38f4b720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x38f4f720 | 0x900000 |
| 43 | blk.4.attn_q.weight | 0x3984f720 | 0x6e0000 |
| 44 | blk.4.attn_v.weight | 0x39f2f720 | 0x240000 |
| 45 | blk.4.ffn_down.weight | 0x3a16f720 | 0x1f80000 |
| 46 | blk.4.ffn_gate.weight | 0x3c0ef720 | 0x1810000 |
| 47 | blk.4.ffn_norm.weight | 0x3d8ff720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x3d903720 | 0x1810000 |
| 49 | blk.5.attn_k.weight | 0x3f113720 | 0x1b8000 |
| 50 | blk.5.attn_norm.weight | 0x3f2cb720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x3f2cf720 | 0x900000 |
| 52 | blk.5.attn_q.weight | 0x3fbcf720 | 0x6e0000 |
| 53 | blk.5.attn_v.weight | 0x402af720 | 0x240000 |
| 54 | blk.5.ffn_down.weight | 0x404ef720 | 0x1f80000 |
| 55 | blk.5.ffn_gate.weight | 0x4246f720 | 0x1810000 |
| 56 | blk.5.ffn_norm.weight | 0x43c7f720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x43c83720 | 0x1810000 |
| 58 | blk.6.attn_k.weight | 0x45493720 | 0x1b8000 |
| 59 | blk.6.attn_norm.weight | 0x4564b720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x4564f720 | 0x900000 |
| 61 | blk.6.attn_q.weight | 0x45f4f720 | 0x6e0000 |
| 62 | blk.6.attn_v.weight | 0x4662f720 | 0x240000 |
| 63 | blk.6.ffn_down.weight | 0x4686f720 | 0x1f80000 |
| 64 | blk.6.ffn_gate.weight | 0x487ef720 | 0x1810000 |
| 65 | blk.6.ffn_norm.weight | 0x49fff720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x4a003720 | 0x1810000 |
| 67 | blk.7.attn_k.weight | 0x4b813720 | 0x1b8000 |
| 68 | blk.7.attn_norm.weight | 0x4b9cb720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x4b9cf720 | 0x900000 |
| 70 | blk.7.attn_q.weight | 0x4c2cf720 | 0x6e0000 |
| 71 | blk.7.attn_v.weight | 0x4c9af720 | 0x240000 |
| 72 | blk.7.ffn_down.weight | 0x4cbef720 | 0x1f80000 |
| 73 | blk.7.ffn_gate.weight | 0x4eb6f720 | 0x1810000 |
| 74 | blk.7.ffn_norm.weight | 0x5037f720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x50383720 | 0x1810000 |
| 76 | blk.8.attn_k.weight | 0x51b93720 | 0x1b8000 |
| 77 | blk.8.attn_norm.weight | 0x51d4b720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x51d4f720 | 0x900000 |
| 79 | blk.8.attn_q.weight | 0x5264f720 | 0x6e0000 |
| 80 | blk.8.attn_v.weight | 0x52d2f720 | 0x240000 |
| 81 | blk.8.ffn_down.weight | 0x52f6f720 | 0x1f80000 |
| 82 | blk.8.ffn_gate.weight | 0x54eef720 | 0x1810000 |
| 83 | blk.8.ffn_norm.weight | 0x566ff720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x56703720 | 0x1810000 |
| 85 | blk.9.attn_k.weight | 0x57f13720 | 0x1b8000 |
| 86 | blk.9.attn_norm.weight | 0x580cb720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x580cf720 | 0x900000 |
| 88 | blk.9.attn_q.weight | 0x589cf720 | 0x6e0000 |
| 89 | blk.9.attn_v.weight | 0x590af720 | 0x240000 |
| 90 | blk.9.ffn_down.weight | 0x592ef720 | 0x1f80000 |
| 91 | blk.9.ffn_gate.weight | 0x5b26f720 | 0x1810000 |
| 92 | blk.9.ffn_norm.weight | 0x5ca7f720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x5ca83720 | 0x1810000 |
| 94 | blk.10.attn_k.weight | 0x5e293720 | 0x1b8000 |
| 95 | blk.10.attn_norm.weight | 0x5e44b720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x5e44f720 | 0x900000 |
| 97 | blk.10.attn_q.weight | 0x5ed4f720 | 0x6e0000 |
| 98 | blk.10.attn_v.weight | 0x5f42f720 | 0x240000 |
| 99 | blk.10.ffn_down.weight | 0x5f66f720 | 0x1f80000 |
| 100 | blk.10.ffn_gate.weight | 0x615ef720 | 0x1810000 |
| 101 | blk.10.ffn_norm.weight | 0x62dff720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x62e03720 | 0x1810000 |
| 103 | blk.11.attn_k.weight | 0x64613720 | 0x1b8000 |
| 104 | blk.11.attn_norm.weight | 0x647cb720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x647cf720 | 0x900000 |
| 106 | blk.11.attn_q.weight | 0x650cf720 | 0x6e0000 |
| 107 | blk.11.attn_v.weight | 0x657af720 | 0x240000 |
| 108 | blk.11.ffn_down.weight | 0x659ef720 | 0x1f80000 |
| 109 | blk.11.ffn_gate.weight | 0x6796f720 | 0x1810000 |
| 110 | blk.11.ffn_norm.weight | 0x6917f720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x69183720 | 0x1810000 |
| 112 | blk.12.attn_k.weight | 0x6a993720 | 0x1b8000 |
| 113 | blk.12.attn_norm.weight | 0x6ab4b720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x6ab4f720 | 0x900000 |
| 115 | blk.12.attn_q.weight | 0x6b44f720 | 0x6e0000 |
| 116 | blk.12.attn_v.weight | 0x6bb2f720 | 0x240000 |
| 117 | blk.12.ffn_down.weight | 0x6bd6f720 | 0x1f80000 |
| 118 | blk.12.ffn_gate.weight | 0x6dcef720 | 0x1810000 |
| 119 | blk.12.ffn_norm.weight | 0x6f4ff720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x6f503720 | 0x1810000 |
| 121 | blk.13.attn_k.weight | 0x70d13720 | 0x240000 |
| 122 | blk.13.attn_norm.weight | 0x70f53720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x70f57720 | 0x900000 |
| 124 | blk.13.attn_q.weight | 0x71857720 | 0x900000 |
| 125 | blk.13.attn_v.weight | 0x72157720 | 0x240000 |
| 126 | blk.13.ffn_down.weight | 0x72397720 | 0x1f80000 |
| 127 | blk.13.ffn_gate.weight | 0x74317720 | 0x1810000 |
| 128 | blk.13.ffn_norm.weight | 0x75b27720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x75b2b720 | 0x1810000 |
| 130 | blk.14.attn_k.weight | 0x7733b720 | 0x240000 |
| 131 | blk.14.attn_norm.weight | 0x7757b720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x7757f720 | 0x900000 |
| 133 | blk.14.attn_q.weight | 0x77e7f720 | 0x900000 |
| 134 | blk.14.attn_v.weight | 0x7877f720 | 0x240000 |
| 135 | blk.14.ffn_down.weight | 0x789bf720 | 0x1f80000 |
| 136 | blk.14.ffn_gate.weight | 0x7a93f720 | 0x1810000 |
| 137 | blk.14.ffn_norm.weight | 0x7c14f720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x7c153720 | 0x1810000 |
| 139 | blk.15.attn_k.weight | 0x7d963720 | 0x1b8000 |
| 140 | blk.15.attn_norm.weight | 0x7db1b720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x7db1f720 | 0x900000 |
| 142 | blk.15.attn_q.weight | 0x7e41f720 | 0x6e0000 |
| 143 | blk.15.attn_v.weight | 0x7eaff720 | 0x240000 |
| 144 | blk.15.ffn_down.weight | 0x7ed3f720 | 0x1f80000 |
| 145 | blk.15.ffn_gate.weight | 0x80cbf720 | 0x1810000 |
| 146 | blk.15.ffn_norm.weight | 0x824cf720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0x824d3720 | 0x1810000 |
| 148 | blk.16.attn_k.weight | 0x83ce3720 | 0x240000 |
| 149 | blk.16.attn_norm.weight | 0x83f23720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0x83f27720 | 0x900000 |
| 151 | blk.16.attn_q.weight | 0x84827720 | 0x900000 |
| 152 | blk.16.attn_v.weight | 0x85127720 | 0x240000 |
| 153 | blk.16.ffn_down.weight | 0x85367720 | 0x1f80000 |
| 154 | blk.16.ffn_gate.weight | 0x872e7720 | 0x1f80000 |
| 155 | blk.16.ffn_norm.weight | 0x89267720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0x8926b720 | 0x1f80000 |
| 157 | blk.17.attn_k.weight | 0x8b1eb720 | 0x1b8000 |
| 158 | blk.17.attn_norm.weight | 0x8b3a3720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0x8b3a7720 | 0x900000 |
| 160 | blk.17.attn_q.weight | 0x8bca7720 | 0x6e0000 |
| 161 | blk.17.attn_v.weight | 0x8c387720 | 0x240000 |
| 162 | blk.17.ffn_down.weight | 0x8c5c7720 | 0x2680000 |
| 163 | blk.17.ffn_gate.weight | 0x8ec47720 | 0x1f80000 |
| 164 | blk.17.ffn_norm.weight | 0x90bc7720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x90bcb720 | 0x1f80000 |
| 166 | blk.18.attn_k.weight | 0x92b4b720 | 0x240000 |
| 167 | blk.18.attn_norm.weight | 0x92d8b720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x92d8f720 | 0x900000 |
| 169 | blk.18.attn_q.weight | 0x9368f720 | 0x900000 |
| 170 | blk.18.attn_v.weight | 0x93f8f720 | 0x240000 |
| 171 | blk.18.ffn_down.weight | 0x941cf720 | 0x2680000 |
| 172 | blk.18.ffn_gate.weight | 0x9684f720 | 0x1f80000 |
| 173 | blk.18.ffn_norm.weight | 0x987cf720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x987d3720 | 0x1f80000 |
| 175 | blk.19.attn_k.weight | 0x9a753720 | 0x240000 |
| 176 | blk.19.attn_norm.weight | 0x9a993720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x9a997720 | 0x900000 |
| 178 | blk.19.attn_q.weight | 0x9b297720 | 0x900000 |
| 179 | blk.19.attn_v.weight | 0x9bb97720 | 0x240000 |
| 180 | blk.19.ffn_down.weight | 0x9bdd7720 | 0x2680000 |
| 181 | blk.19.ffn_gate.weight | 0x9e457720 | 0x1f80000 |
| 182 | blk.19.ffn_norm.weight | 0xa03d7720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0xa03db720 | 0x1f80000 |
| 184 | blk.20.attn_k.weight | 0xa235b720 | 0x240000 |
| 185 | blk.20.attn_norm.weight | 0xa259b720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0xa259f720 | 0x900000 |
| 187 | blk.20.attn_q.weight | 0xa2e9f720 | 0x900000 |
| 188 | blk.20.attn_v.weight | 0xa379f720 | 0x240000 |
| 189 | blk.20.ffn_down.weight | 0xa39df720 | 0x2680000 |
| 190 | blk.20.ffn_gate.weight | 0xa605f720 | 0x1f80000 |
| 191 | blk.20.ffn_norm.weight | 0xa7fdf720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0xa7fe3720 | 0x1f80000 |
| 193 | blk.21.attn_k.weight | 0xa9f63720 | 0x240000 |
| 194 | blk.21.attn_norm.weight | 0xaa1a3720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0xaa1a7720 | 0x900000 |
| 196 | blk.21.attn_q.weight | 0xaaaa7720 | 0x900000 |
| 197 | blk.21.attn_v.weight | 0xab3a7720 | 0x240000 |
| 198 | blk.21.ffn_down.weight | 0xab5e7720 | 0x2680000 |
| 199 | blk.21.ffn_gate.weight | 0xadc67720 | 0x1f80000 |
| 200 | blk.21.ffn_norm.weight | 0xafbe7720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0xafbeb720 | 0x1f80000 |
| 202 | blk.22.attn_k.weight | 0xb1b6b720 | 0x240000 |
| 203 | blk.22.attn_norm.weight | 0xb1dab720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0xb1daf720 | 0x900000 |
| 205 | blk.22.attn_q.weight | 0xb26af720 | 0x900000 |
| 206 | blk.22.attn_v.weight | 0xb2faf720 | 0x240000 |
| 207 | blk.22.ffn_down.weight | 0xb31ef720 | 0x2680000 |
| 208 | blk.22.ffn_gate.weight | 0xb586f720 | 0x1f80000 |
| 209 | blk.22.ffn_norm.weight | 0xb77ef720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xb77f3720 | 0x1f80000 |
| 211 | blk.23.attn_k.weight | 0xb9773720 | 0x240000 |
| 212 | blk.23.attn_norm.weight | 0xb99b3720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xb99b7720 | 0x900000 |
| 214 | blk.23.attn_q.weight | 0xba2b7720 | 0x900000 |
| 215 | blk.23.attn_v.weight | 0xbabb7720 | 0x240000 |
| 216 | blk.23.ffn_down.weight | 0xbadf7720 | 0x2680000 |
| 217 | blk.23.ffn_gate.weight | 0xbd477720 | 0x1f80000 |
| 218 | blk.23.ffn_norm.weight | 0xbf3f7720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xbf3fb720 | 0x1f80000 |
| 220 | blk.24.attn_k.weight | 0xc137b720 | 0x240000 |
| 221 | blk.24.attn_norm.weight | 0xc15bb720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xc15bf720 | 0x900000 |
| 223 | blk.24.attn_q.weight | 0xc1ebf720 | 0x900000 |
| 224 | blk.24.attn_v.weight | 0xc27bf720 | 0x240000 |
| 225 | blk.24.ffn_down.weight | 0xc29ff720 | 0x2680000 |
| 226 | blk.24.ffn_gate.weight | 0xc507f720 | 0x1f80000 |
| 227 | blk.24.ffn_norm.weight | 0xc6fff720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xc7003720 | 0x1f80000 |
| 229 | blk.25.attn_k.weight | 0xc8f83720 | 0x240000 |
| 230 | blk.25.attn_norm.weight | 0xc91c3720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xc91c7720 | 0x900000 |
| 232 | blk.25.attn_q.weight | 0xc9ac7720 | 0x900000 |
| 233 | blk.25.attn_v.weight | 0xca3c7720 | 0x240000 |
| 234 | blk.25.ffn_down.weight | 0xca607720 | 0x2680000 |
| 235 | blk.25.ffn_gate.weight | 0xccc87720 | 0x1f80000 |
| 236 | blk.25.ffn_norm.weight | 0xcec07720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xcec0b720 | 0x1f80000 |
| 238 | blk.26.attn_k.weight | 0xd0b8b720 | 0x240000 |
| 239 | blk.26.attn_norm.weight | 0xd0dcb720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0xd0dcf720 | 0x900000 |
| 241 | blk.26.attn_q.weight | 0xd16cf720 | 0x900000 |
| 242 | blk.26.attn_v.weight | 0xd1fcf720 | 0x240000 |
| 243 | blk.26.ffn_down.weight | 0xd220f720 | 0x2680000 |
| 244 | blk.26.ffn_gate.weight | 0xd488f720 | 0x1f80000 |
| 245 | blk.26.ffn_norm.weight | 0xd680f720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0xd6813720 | 0x1f80000 |
| 247 | blk.27.attn_k.weight | 0xd8793720 | 0x240000 |
| 248 | blk.27.attn_norm.weight | 0xd89d3720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0xd89d7720 | 0x900000 |
| 250 | blk.27.attn_q.weight | 0xd92d7720 | 0x900000 |
| 251 | blk.27.attn_v.weight | 0xd9bd7720 | 0x240000 |
| 252 | blk.27.ffn_down.weight | 0xd9e17720 | 0x2680000 |
| 253 | blk.27.ffn_gate.weight | 0xdc497720 | 0x1f80000 |
| 254 | blk.27.ffn_norm.weight | 0xde417720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0xde41b720 | 0x1f80000 |
| 256 | blk.28.attn_k.weight | 0xe039b720 | 0x240000 |
| 257 | blk.28.attn_norm.weight | 0xe05db720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0xe05df720 | 0x900000 |
| 259 | blk.28.attn_q.weight | 0xe0edf720 | 0x900000 |
| 260 | blk.28.attn_v.weight | 0xe17df720 | 0x240000 |
| 261 | blk.28.ffn_down.weight | 0xe1a1f720 | 0x2680000 |
| 262 | blk.28.ffn_gate.weight | 0xe409f720 | 0x1f80000 |
| 263 | blk.28.ffn_norm.weight | 0xe601f720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0xe6023720 | 0x1f80000 |
| 265 | blk.29.attn_k.weight | 0xe7fa3720 | 0x240000 |
| 266 | blk.29.attn_norm.weight | 0xe81e3720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0xe81e7720 | 0x900000 |
| 268 | blk.29.attn_q.weight | 0xe8ae7720 | 0x900000 |
| 269 | blk.29.attn_v.weight | 0xe93e7720 | 0x240000 |
| 270 | blk.29.ffn_down.weight | 0xe9627720 | 0x2680000 |
| 271 | blk.29.ffn_gate.weight | 0xebca7720 | 0x1f80000 |
| 272 | blk.29.ffn_norm.weight | 0xedc27720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0xedc2b720 | 0x1f80000 |
| 274 | blk.30.attn_k.weight | 0xefbab720 | 0x240000 |
| 275 | blk.30.attn_norm.weight | 0xefdeb720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0xefdef720 | 0x900000 |
| 277 | blk.30.attn_q.weight | 0xf06ef720 | 0x900000 |
| 278 | blk.30.attn_v.weight | 0xf0fef720 | 0x240000 |
| 279 | blk.30.ffn_down.weight | 0xf122f720 | 0x2680000 |
| 280 | blk.30.ffn_gate.weight | 0xf38af720 | 0x1f80000 |
| 281 | blk.30.ffn_norm.weight | 0xf582f720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0xf5833720 | 0x1f80000 |
| 283 | blk.31.attn_k.weight | 0xf77b3720 | 0x1b8000 |
| 284 | blk.31.attn_norm.weight | 0xf796b720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0xf796f720 | 0x900000 |
| 286 | blk.31.attn_q.weight | 0xf826f720 | 0x6e0000 |
| 287 | blk.31.attn_v.weight | 0xf894f720 | 0x240000 |
| 288 | blk.31.ffn_down.weight | 0xf8b8f720 | 0x2680000 |
| 289 | blk.31.ffn_gate.weight | 0xfb20f720 | 0x1f80000 |
| 290 | blk.31.ffn_norm.weight | 0xfd18f720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0xfd193720 | 0x1f80000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q4_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q3_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q4_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q3_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q3_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q5_K_M.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q5_K_M.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 17 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q5\_K\_M.gguf - GGUF Internal File Dump](#watt-tool-8b-q5_k_mgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x15870000 |
| 1 | output_norm.weight | 0x15fe9620 | 0x4000 |
| 2 | rope_freqs.weight | 0x15fed620 | 0x100 |
| 3 | token_embd.weight | 0x15fed720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x23733720 | 0x240000 |
| 5 | blk.0.attn_norm.weight | 0x23973720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x23977720 | 0xb00000 |
| 7 | blk.0.attn_q.weight | 0x24477720 | 0x900000 |
| 8 | blk.0.attn_v.weight | 0x24d77720 | 0x2c0000 |
| 9 | blk.0.ffn_down.weight | 0x25037720 | 0x2df0000 |
| 10 | blk.0.ffn_gate.weight | 0x27e27720 | 0x1f80000 |
| 11 | blk.0.ffn_norm.weight | 0x29da7720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x29dab720 | 0x1f80000 |
| 13 | blk.1.attn_k.weight | 0x2bd2b720 | 0x240000 |
| 14 | blk.1.attn_norm.weight | 0x2bf6b720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x2bf6f720 | 0xb00000 |
| 16 | blk.1.attn_q.weight | 0x2ca6f720 | 0x900000 |
| 17 | blk.1.attn_v.weight | 0x2d36f720 | 0x2c0000 |
| 18 | blk.1.ffn_down.weight | 0x2d62f720 | 0x2df0000 |
| 19 | blk.1.ffn_gate.weight | 0x3041f720 | 0x1f80000 |
| 20 | blk.1.ffn_norm.weight | 0x3239f720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x323a3720 | 0x1f80000 |
| 22 | blk.2.attn_k.weight | 0x34323720 | 0x240000 |
| 23 | blk.2.attn_norm.weight | 0x34563720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x34567720 | 0xb00000 |
| 25 | blk.2.attn_q.weight | 0x35067720 | 0x900000 |
| 26 | blk.2.attn_v.weight | 0x35967720 | 0x2c0000 |
| 27 | blk.2.ffn_down.weight | 0x35c27720 | 0x2df0000 |
| 28 | blk.2.ffn_gate.weight | 0x38a17720 | 0x1f80000 |
| 29 | blk.2.ffn_norm.weight | 0x3a997720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x3a99b720 | 0x1f80000 |
| 31 | blk.3.attn_k.weight | 0x3c91b720 | 0x240000 |
| 32 | blk.3.attn_norm.weight | 0x3cb5b720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x3cb5f720 | 0xb00000 |
| 34 | blk.3.attn_q.weight | 0x3d65f720 | 0x900000 |
| 35 | blk.3.attn_v.weight | 0x3df5f720 | 0x2c0000 |
| 36 | blk.3.ffn_down.weight | 0x3e21f720 | 0x2df0000 |
| 37 | blk.3.ffn_gate.weight | 0x4100f720 | 0x1f80000 |
| 38 | blk.3.ffn_norm.weight | 0x42f8f720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x42f93720 | 0x1f80000 |
| 40 | blk.4.attn_k.weight | 0x44f13720 | 0x240000 |
| 41 | blk.4.attn_norm.weight | 0x45153720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x45157720 | 0xb00000 |
| 43 | blk.4.attn_q.weight | 0x45c57720 | 0x900000 |
| 44 | blk.4.attn_v.weight | 0x46557720 | 0x2c0000 |
| 45 | blk.4.ffn_down.weight | 0x46817720 | 0x2df0000 |
| 46 | blk.4.ffn_gate.weight | 0x49607720 | 0x1f80000 |
| 47 | blk.4.ffn_norm.weight | 0x4b587720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x4b58b720 | 0x1f80000 |
| 49 | blk.5.attn_k.weight | 0x4d50b720 | 0x240000 |
| 50 | blk.5.attn_norm.weight | 0x4d74b720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x4d74f720 | 0xb00000 |
| 52 | blk.5.attn_q.weight | 0x4e24f720 | 0x900000 |
| 53 | blk.5.attn_v.weight | 0x4eb4f720 | 0x2c0000 |
| 54 | blk.5.ffn_down.weight | 0x4ee0f720 | 0x2df0000 |
| 55 | blk.5.ffn_gate.weight | 0x51bff720 | 0x1f80000 |
| 56 | blk.5.ffn_norm.weight | 0x53b7f720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x53b83720 | 0x1f80000 |
| 58 | blk.6.attn_k.weight | 0x55b03720 | 0x240000 |
| 59 | blk.6.attn_norm.weight | 0x55d43720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x55d47720 | 0xb00000 |
| 61 | blk.6.attn_q.weight | 0x56847720 | 0x900000 |
| 62 | blk.6.attn_v.weight | 0x57147720 | 0x2c0000 |
| 63 | blk.6.ffn_down.weight | 0x57407720 | 0x2df0000 |
| 64 | blk.6.ffn_gate.weight | 0x5a1f7720 | 0x1f80000 |
| 65 | blk.6.ffn_norm.weight | 0x5c177720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x5c17b720 | 0x1f80000 |
| 67 | blk.7.attn_k.weight | 0x5e0fb720 | 0x240000 |
| 68 | blk.7.attn_norm.weight | 0x5e33b720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x5e33f720 | 0xb00000 |
| 70 | blk.7.attn_q.weight | 0x5ee3f720 | 0x900000 |
| 71 | blk.7.attn_v.weight | 0x5f73f720 | 0x2c0000 |
| 72 | blk.7.ffn_down.weight | 0x5f9ff720 | 0x2df0000 |
| 73 | blk.7.ffn_gate.weight | 0x627ef720 | 0x1f80000 |
| 74 | blk.7.ffn_norm.weight | 0x6476f720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x64773720 | 0x1f80000 |
| 76 | blk.8.attn_k.weight | 0x666f3720 | 0x240000 |
| 77 | blk.8.attn_norm.weight | 0x66933720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x66937720 | 0xb00000 |
| 79 | blk.8.attn_q.weight | 0x67437720 | 0x900000 |
| 80 | blk.8.attn_v.weight | 0x67d37720 | 0x2c0000 |
| 81 | blk.8.ffn_down.weight | 0x67ff7720 | 0x2df0000 |
| 82 | blk.8.ffn_gate.weight | 0x6ade7720 | 0x1f80000 |
| 83 | blk.8.ffn_norm.weight | 0x6cd67720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x6cd6b720 | 0x1f80000 |
| 85 | blk.9.attn_k.weight | 0x6eceb720 | 0x240000 |
| 86 | blk.9.attn_norm.weight | 0x6ef2b720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x6ef2f720 | 0xb00000 |
| 88 | blk.9.attn_q.weight | 0x6fa2f720 | 0x900000 |
| 89 | blk.9.attn_v.weight | 0x7032f720 | 0x2c0000 |
| 90 | blk.9.ffn_down.weight | 0x705ef720 | 0x2df0000 |
| 91 | blk.9.ffn_gate.weight | 0x733df720 | 0x1f80000 |
| 92 | blk.9.ffn_norm.weight | 0x7535f720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x75363720 | 0x1f80000 |
| 94 | blk.10.attn_k.weight | 0x772e3720 | 0x240000 |
| 95 | blk.10.attn_norm.weight | 0x77523720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x77527720 | 0xb00000 |
| 97 | blk.10.attn_q.weight | 0x78027720 | 0x900000 |
| 98 | blk.10.attn_v.weight | 0x78927720 | 0x2c0000 |
| 99 | blk.10.ffn_down.weight | 0x78be7720 | 0x2df0000 |
| 100 | blk.10.ffn_gate.weight | 0x7b9d7720 | 0x1f80000 |
| 101 | blk.10.ffn_norm.weight | 0x7d957720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x7d95b720 | 0x1f80000 |
| 103 | blk.11.attn_k.weight | 0x7f8db720 | 0x240000 |
| 104 | blk.11.attn_norm.weight | 0x7fb1b720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x7fb1f720 | 0xb00000 |
| 106 | blk.11.attn_q.weight | 0x8061f720 | 0x900000 |
| 107 | blk.11.attn_v.weight | 0x80f1f720 | 0x2c0000 |
| 108 | blk.11.ffn_down.weight | 0x811df720 | 0x2df0000 |
| 109 | blk.11.ffn_gate.weight | 0x83fcf720 | 0x1f80000 |
| 110 | blk.11.ffn_norm.weight | 0x85f4f720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x85f53720 | 0x1f80000 |
| 112 | blk.12.attn_k.weight | 0x87ed3720 | 0x240000 |
| 113 | blk.12.attn_norm.weight | 0x88113720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x88117720 | 0xb00000 |
| 115 | blk.12.attn_q.weight | 0x88c17720 | 0x900000 |
| 116 | blk.12.attn_v.weight | 0x89517720 | 0x2c0000 |
| 117 | blk.12.ffn_down.weight | 0x897d7720 | 0x2df0000 |
| 118 | blk.12.ffn_gate.weight | 0x8c5c7720 | 0x1f80000 |
| 119 | blk.12.ffn_norm.weight | 0x8e547720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x8e54b720 | 0x1f80000 |
| 121 | blk.13.attn_k.weight | 0x904cb720 | 0x2c0000 |
| 122 | blk.13.attn_norm.weight | 0x9078b720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x9078f720 | 0xb00000 |
| 124 | blk.13.attn_q.weight | 0x9128f720 | 0xb00000 |
| 125 | blk.13.attn_v.weight | 0x91d8f720 | 0x348000 |
| 126 | blk.13.ffn_down.weight | 0x920d7720 | 0x2df0000 |
| 127 | blk.13.ffn_gate.weight | 0x94ec7720 | 0x1f80000 |
| 128 | blk.13.ffn_norm.weight | 0x96e47720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x96e4b720 | 0x1f80000 |
| 130 | blk.14.attn_k.weight | 0x98dcb720 | 0x2c0000 |
| 131 | blk.14.attn_norm.weight | 0x9908b720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x9908f720 | 0xb00000 |
| 133 | blk.14.attn_q.weight | 0x99b8f720 | 0xb00000 |
| 134 | blk.14.attn_v.weight | 0x9a68f720 | 0x348000 |
| 135 | blk.14.ffn_down.weight | 0x9a9d7720 | 0x2df0000 |
| 136 | blk.14.ffn_gate.weight | 0x9d7c7720 | 0x1f80000 |
| 137 | blk.14.ffn_norm.weight | 0x9f747720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x9f74b720 | 0x1f80000 |
| 139 | blk.15.attn_k.weight | 0xa16cb720 | 0x240000 |
| 140 | blk.15.attn_norm.weight | 0xa190b720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0xa190f720 | 0xb00000 |
| 142 | blk.15.attn_q.weight | 0xa240f720 | 0x900000 |
| 143 | blk.15.attn_v.weight | 0xa2d0f720 | 0x2c0000 |
| 144 | blk.15.ffn_down.weight | 0xa2fcf720 | 0x2df0000 |
| 145 | blk.15.ffn_gate.weight | 0xa5dbf720 | 0x1f80000 |
| 146 | blk.15.ffn_norm.weight | 0xa7d3f720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0xa7d43720 | 0x1f80000 |
| 148 | blk.16.attn_k.weight | 0xa9cc3720 | 0x2c0000 |
| 149 | blk.16.attn_norm.weight | 0xa9f83720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0xa9f87720 | 0xb00000 |
| 151 | blk.16.attn_q.weight | 0xaaa87720 | 0xb00000 |
| 152 | blk.16.attn_v.weight | 0xab587720 | 0x348000 |
| 153 | blk.16.ffn_down.weight | 0xab8cf720 | 0x2df0000 |
| 154 | blk.16.ffn_gate.weight | 0xae6bf720 | 0x2680000 |
| 155 | blk.16.ffn_norm.weight | 0xb0d3f720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0xb0d43720 | 0x2680000 |
| 157 | blk.17.attn_k.weight | 0xb33c3720 | 0x240000 |
| 158 | blk.17.attn_norm.weight | 0xb3603720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0xb3607720 | 0xb00000 |
| 160 | blk.17.attn_q.weight | 0xb4107720 | 0x900000 |
| 161 | blk.17.attn_v.weight | 0xb4a07720 | 0x2c0000 |
| 162 | blk.17.ffn_down.weight | 0xb4cc7720 | 0x2df0000 |
| 163 | blk.17.ffn_gate.weight | 0xb7ab7720 | 0x2680000 |
| 164 | blk.17.ffn_norm.weight | 0xba137720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0xba13b720 | 0x2680000 |
| 166 | blk.18.attn_k.weight | 0xbc7bb720 | 0x2c0000 |
| 167 | blk.18.attn_norm.weight | 0xbca7b720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0xbca7f720 | 0xb00000 |
| 169 | blk.18.attn_q.weight | 0xbd57f720 | 0xb00000 |
| 170 | blk.18.attn_v.weight | 0xbe07f720 | 0x348000 |
| 171 | blk.18.ffn_down.weight | 0xbe3c7720 | 0x2df0000 |
| 172 | blk.18.ffn_gate.weight | 0xc11b7720 | 0x2680000 |
| 173 | blk.18.ffn_norm.weight | 0xc3837720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0xc383b720 | 0x2680000 |
| 175 | blk.19.attn_k.weight | 0xc5ebb720 | 0x2c0000 |
| 176 | blk.19.attn_norm.weight | 0xc617b720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0xc617f720 | 0xb00000 |
| 178 | blk.19.attn_q.weight | 0xc6c7f720 | 0xb00000 |
| 179 | blk.19.attn_v.weight | 0xc777f720 | 0x348000 |
| 180 | blk.19.ffn_down.weight | 0xc7ac7720 | 0x2df0000 |
| 181 | blk.19.ffn_gate.weight | 0xca8b7720 | 0x2680000 |
| 182 | blk.19.ffn_norm.weight | 0xccf37720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0xccf3b720 | 0x2680000 |
| 184 | blk.20.attn_k.weight | 0xcf5bb720 | 0x2c0000 |
| 185 | blk.20.attn_norm.weight | 0xcf87b720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0xcf87f720 | 0xb00000 |
| 187 | blk.20.attn_q.weight | 0xd037f720 | 0xb00000 |
| 188 | blk.20.attn_v.weight | 0xd0e7f720 | 0x348000 |
| 189 | blk.20.ffn_down.weight | 0xd11c7720 | 0x2df0000 |
| 190 | blk.20.ffn_gate.weight | 0xd3fb7720 | 0x2680000 |
| 191 | blk.20.ffn_norm.weight | 0xd6637720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0xd663b720 | 0x2680000 |
| 193 | blk.21.attn_k.weight | 0xd8cbb720 | 0x2c0000 |
| 194 | blk.21.attn_norm.weight | 0xd8f7b720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0xd8f7f720 | 0xb00000 |
| 196 | blk.21.attn_q.weight | 0xd9a7f720 | 0xb00000 |
| 197 | blk.21.attn_v.weight | 0xda57f720 | 0x348000 |
| 198 | blk.21.ffn_down.weight | 0xda8c7720 | 0x2df0000 |
| 199 | blk.21.ffn_gate.weight | 0xdd6b7720 | 0x2680000 |
| 200 | blk.21.ffn_norm.weight | 0xdfd37720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0xdfd3b720 | 0x2680000 |
| 202 | blk.22.attn_k.weight | 0xe23bb720 | 0x2c0000 |
| 203 | blk.22.attn_norm.weight | 0xe267b720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0xe267f720 | 0xb00000 |
| 205 | blk.22.attn_q.weight | 0xe317f720 | 0xb00000 |
| 206 | blk.22.attn_v.weight | 0xe3c7f720 | 0x348000 |
| 207 | blk.22.ffn_down.weight | 0xe3fc7720 | 0x2df0000 |
| 208 | blk.22.ffn_gate.weight | 0xe6db7720 | 0x2680000 |
| 209 | blk.22.ffn_norm.weight | 0xe9437720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xe943b720 | 0x2680000 |
| 211 | blk.23.attn_k.weight | 0xebabb720 | 0x2c0000 |
| 212 | blk.23.attn_norm.weight | 0xebd7b720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xebd7f720 | 0xb00000 |
| 214 | blk.23.attn_q.weight | 0xec87f720 | 0xb00000 |
| 215 | blk.23.attn_v.weight | 0xed37f720 | 0x348000 |
| 216 | blk.23.ffn_down.weight | 0xed6c7720 | 0x2df0000 |
| 217 | blk.23.ffn_gate.weight | 0xf04b7720 | 0x2680000 |
| 218 | blk.23.ffn_norm.weight | 0xf2b37720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xf2b3b720 | 0x2680000 |
| 220 | blk.24.attn_k.weight | 0xf51bb720 | 0x2c0000 |
| 221 | blk.24.attn_norm.weight | 0xf547b720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xf547f720 | 0xb00000 |
| 223 | blk.24.attn_q.weight | 0xf5f7f720 | 0xb00000 |
| 224 | blk.24.attn_v.weight | 0xf6a7f720 | 0x348000 |
| 225 | blk.24.ffn_down.weight | 0xf6dc7720 | 0x2df0000 |
| 226 | blk.24.ffn_gate.weight | 0xf9bb7720 | 0x2680000 |
| 227 | blk.24.ffn_norm.weight | 0xfc237720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xfc23b720 | 0x2680000 |
| 229 | blk.25.attn_k.weight | 0xfe8bb720 | 0x2c0000 |
| 230 | blk.25.attn_norm.weight | 0xfeb7b720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xfeb7f720 | 0xb00000 |
| 232 | blk.25.attn_q.weight | 0xff67f720 | 0xb00000 |
| 233 | blk.25.attn_v.weight | 0x10017f720 | 0x348000 |
| 234 | blk.25.ffn_down.weight | 0x1004c7720 | 0x2df0000 |
| 235 | blk.25.ffn_gate.weight | 0x1032b7720 | 0x2680000 |
| 236 | blk.25.ffn_norm.weight | 0x105937720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0x10593b720 | 0x2680000 |
| 238 | blk.26.attn_k.weight | 0x107fbb720 | 0x2c0000 |
| 239 | blk.26.attn_norm.weight | 0x10827b720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0x10827f720 | 0xb00000 |
| 241 | blk.26.attn_q.weight | 0x108d7f720 | 0xb00000 |
| 242 | blk.26.attn_v.weight | 0x10987f720 | 0x348000 |
| 243 | blk.26.ffn_down.weight | 0x109bc7720 | 0x2df0000 |
| 244 | blk.26.ffn_gate.weight | 0x10c9b7720 | 0x2680000 |
| 245 | blk.26.ffn_norm.weight | 0x10f037720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0x10f03b720 | 0x2680000 |
| 247 | blk.27.attn_k.weight | 0x1116bb720 | 0x2c0000 |
| 248 | blk.27.attn_norm.weight | 0x11197b720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0x11197f720 | 0xb00000 |
| 250 | blk.27.attn_q.weight | 0x11247f720 | 0xb00000 |
| 251 | blk.27.attn_v.weight | 0x112f7f720 | 0x348000 |
| 252 | blk.27.ffn_down.weight | 0x1132c7720 | 0x2df0000 |
| 253 | blk.27.ffn_gate.weight | 0x1160b7720 | 0x2680000 |
| 254 | blk.27.ffn_norm.weight | 0x118737720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0x11873b720 | 0x2680000 |
| 256 | blk.28.attn_k.weight | 0x11adbb720 | 0x2c0000 |
| 257 | blk.28.attn_norm.weight | 0x11b07b720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0x11b07f720 | 0xb00000 |
| 259 | blk.28.attn_q.weight | 0x11bb7f720 | 0xb00000 |
| 260 | blk.28.attn_v.weight | 0x11c67f720 | 0x348000 |
| 261 | blk.28.ffn_down.weight | 0x11c9c7720 | 0x2df0000 |
| 262 | blk.28.ffn_gate.weight | 0x11f7b7720 | 0x2680000 |
| 263 | blk.28.ffn_norm.weight | 0x121e37720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0x121e3b720 | 0x2680000 |
| 265 | blk.29.attn_k.weight | 0x1244bb720 | 0x2c0000 |
| 266 | blk.29.attn_norm.weight | 0x12477b720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0x12477f720 | 0xb00000 |
| 268 | blk.29.attn_q.weight | 0x12527f720 | 0xb00000 |
| 269 | blk.29.attn_v.weight | 0x125d7f720 | 0x348000 |
| 270 | blk.29.ffn_down.weight | 0x1260c7720 | 0x2df0000 |
| 271 | blk.29.ffn_gate.weight | 0x128eb7720 | 0x2680000 |
| 272 | blk.29.ffn_norm.weight | 0x12b537720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0x12b53b720 | 0x2680000 |
| 274 | blk.30.attn_k.weight | 0x12dbbb720 | 0x2c0000 |
| 275 | blk.30.attn_norm.weight | 0x12de7b720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0x12de7f720 | 0xb00000 |
| 277 | blk.30.attn_q.weight | 0x12e97f720 | 0xb00000 |
| 278 | blk.30.attn_v.weight | 0x12f47f720 | 0x348000 |
| 279 | blk.30.ffn_down.weight | 0x12f7c7720 | 0x2df0000 |
| 280 | blk.30.ffn_gate.weight | 0x1325b7720 | 0x2680000 |
| 281 | blk.30.ffn_norm.weight | 0x134c37720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0x134c3b720 | 0x2680000 |
| 283 | blk.31.attn_k.weight | 0x1372bb720 | 0x240000 |
| 284 | blk.31.attn_norm.weight | 0x1374fb720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0x1374ff720 | 0xb00000 |
| 286 | blk.31.attn_q.weight | 0x137fff720 | 0x900000 |
| 287 | blk.31.attn_v.weight | 0x1388ff720 | 0x2c0000 |
| 288 | blk.31.ffn_down.weight | 0x138bbf720 | 0x2df0000 |
| 289 | blk.31.ffn_gate.weight | 0x13b9af720 | 0x2680000 |
| 290 | blk.31.ffn_norm.weight | 0x13e02f720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0x13e033720 | 0x2680000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q5_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q5_K_S.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q5_K_S.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 16 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q5\_K\_S.gguf - GGUF Internal File Dump](#watt-tool-8b-q5_k_sgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x15870000 |
| 1 | output_norm.weight | 0x15fe9620 | 0x4000 |
| 2 | rope_freqs.weight | 0x15fed620 | 0x100 |
| 3 | token_embd.weight | 0x15fed720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x23733720 | 0x240000 |
| 5 | blk.0.attn_norm.weight | 0x23973720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x23977720 | 0xb00000 |
| 7 | blk.0.attn_q.weight | 0x24477720 | 0x900000 |
| 8 | blk.0.attn_v.weight | 0x24d77720 | 0x2c0000 |
| 9 | blk.0.ffn_down.weight | 0x25037720 | 0x2680000 |
| 10 | blk.0.ffn_gate.weight | 0x276b7720 | 0x1f80000 |
| 11 | blk.0.ffn_norm.weight | 0x29637720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x2963b720 | 0x1f80000 |
| 13 | blk.1.attn_k.weight | 0x2b5bb720 | 0x240000 |
| 14 | blk.1.attn_norm.weight | 0x2b7fb720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x2b7ff720 | 0xb00000 |
| 16 | blk.1.attn_q.weight | 0x2c2ff720 | 0x900000 |
| 17 | blk.1.attn_v.weight | 0x2cbff720 | 0x2c0000 |
| 18 | blk.1.ffn_down.weight | 0x2cebf720 | 0x2df0000 |
| 19 | blk.1.ffn_gate.weight | 0x2fcaf720 | 0x1f80000 |
| 20 | blk.1.ffn_norm.weight | 0x31c2f720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x31c33720 | 0x1f80000 |
| 22 | blk.2.attn_k.weight | 0x33bb3720 | 0x240000 |
| 23 | blk.2.attn_norm.weight | 0x33df3720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x33df7720 | 0xb00000 |
| 25 | blk.2.attn_q.weight | 0x348f7720 | 0x900000 |
| 26 | blk.2.attn_v.weight | 0x351f7720 | 0x2c0000 |
| 27 | blk.2.ffn_down.weight | 0x354b7720 | 0x2680000 |
| 28 | blk.2.ffn_gate.weight | 0x37b37720 | 0x1f80000 |
| 29 | blk.2.ffn_norm.weight | 0x39ab7720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x39abb720 | 0x1f80000 |
| 31 | blk.3.attn_k.weight | 0x3ba3b720 | 0x240000 |
| 32 | blk.3.attn_norm.weight | 0x3bc7b720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x3bc7f720 | 0xb00000 |
| 34 | blk.3.attn_q.weight | 0x3c77f720 | 0x900000 |
| 35 | blk.3.attn_v.weight | 0x3d07f720 | 0x2c0000 |
| 36 | blk.3.ffn_down.weight | 0x3d33f720 | 0x2680000 |
| 37 | blk.3.ffn_gate.weight | 0x3f9bf720 | 0x1f80000 |
| 38 | blk.3.ffn_norm.weight | 0x4193f720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x41943720 | 0x1f80000 |
| 40 | blk.4.attn_k.weight | 0x438c3720 | 0x240000 |
| 41 | blk.4.attn_norm.weight | 0x43b03720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x43b07720 | 0xb00000 |
| 43 | blk.4.attn_q.weight | 0x44607720 | 0x900000 |
| 44 | blk.4.attn_v.weight | 0x44f07720 | 0x2c0000 |
| 45 | blk.4.ffn_down.weight | 0x451c7720 | 0x2680000 |
| 46 | blk.4.ffn_gate.weight | 0x47847720 | 0x1f80000 |
| 47 | blk.4.ffn_norm.weight | 0x497c7720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x497cb720 | 0x1f80000 |
| 49 | blk.5.attn_k.weight | 0x4b74b720 | 0x240000 |
| 50 | blk.5.attn_norm.weight | 0x4b98b720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x4b98f720 | 0xb00000 |
| 52 | blk.5.attn_q.weight | 0x4c48f720 | 0x900000 |
| 53 | blk.5.attn_v.weight | 0x4cd8f720 | 0x2c0000 |
| 54 | blk.5.ffn_down.weight | 0x4d04f720 | 0x2680000 |
| 55 | blk.5.ffn_gate.weight | 0x4f6cf720 | 0x1f80000 |
| 56 | blk.5.ffn_norm.weight | 0x5164f720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x51653720 | 0x1f80000 |
| 58 | blk.6.attn_k.weight | 0x535d3720 | 0x240000 |
| 59 | blk.6.attn_norm.weight | 0x53813720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x53817720 | 0xb00000 |
| 61 | blk.6.attn_q.weight | 0x54317720 | 0x900000 |
| 62 | blk.6.attn_v.weight | 0x54c17720 | 0x2c0000 |
| 63 | blk.6.ffn_down.weight | 0x54ed7720 | 0x2680000 |
| 64 | blk.6.ffn_gate.weight | 0x57557720 | 0x1f80000 |
| 65 | blk.6.ffn_norm.weight | 0x594d7720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x594db720 | 0x1f80000 |
| 67 | blk.7.attn_k.weight | 0x5b45b720 | 0x240000 |
| 68 | blk.7.attn_norm.weight | 0x5b69b720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x5b69f720 | 0xb00000 |
| 70 | blk.7.attn_q.weight | 0x5c19f720 | 0x900000 |
| 71 | blk.7.attn_v.weight | 0x5ca9f720 | 0x2c0000 |
| 72 | blk.7.ffn_down.weight | 0x5cd5f720 | 0x2680000 |
| 73 | blk.7.ffn_gate.weight | 0x5f3df720 | 0x1f80000 |
| 74 | blk.7.ffn_norm.weight | 0x6135f720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x61363720 | 0x1f80000 |
| 76 | blk.8.attn_k.weight | 0x632e3720 | 0x240000 |
| 77 | blk.8.attn_norm.weight | 0x63523720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x63527720 | 0xb00000 |
| 79 | blk.8.attn_q.weight | 0x64027720 | 0x900000 |
| 80 | blk.8.attn_v.weight | 0x64927720 | 0x2c0000 |
| 81 | blk.8.ffn_down.weight | 0x64be7720 | 0x2680000 |
| 82 | blk.8.ffn_gate.weight | 0x67267720 | 0x1f80000 |
| 83 | blk.8.ffn_norm.weight | 0x691e7720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x691eb720 | 0x1f80000 |
| 85 | blk.9.attn_k.weight | 0x6b16b720 | 0x240000 |
| 86 | blk.9.attn_norm.weight | 0x6b3ab720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x6b3af720 | 0xb00000 |
| 88 | blk.9.attn_q.weight | 0x6beaf720 | 0x900000 |
| 89 | blk.9.attn_v.weight | 0x6c7af720 | 0x2c0000 |
| 90 | blk.9.ffn_down.weight | 0x6ca6f720 | 0x2680000 |
| 91 | blk.9.ffn_gate.weight | 0x6f0ef720 | 0x1f80000 |
| 92 | blk.9.ffn_norm.weight | 0x7106f720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x71073720 | 0x1f80000 |
| 94 | blk.10.attn_k.weight | 0x72ff3720 | 0x240000 |
| 95 | blk.10.attn_norm.weight | 0x73233720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x73237720 | 0xb00000 |
| 97 | blk.10.attn_q.weight | 0x73d37720 | 0x900000 |
| 98 | blk.10.attn_v.weight | 0x74637720 | 0x2c0000 |
| 99 | blk.10.ffn_down.weight | 0x748f7720 | 0x2680000 |
| 100 | blk.10.ffn_gate.weight | 0x76f77720 | 0x1f80000 |
| 101 | blk.10.ffn_norm.weight | 0x78ef7720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x78efb720 | 0x1f80000 |
| 103 | blk.11.attn_k.weight | 0x7ae7b720 | 0x240000 |
| 104 | blk.11.attn_norm.weight | 0x7b0bb720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x7b0bf720 | 0xb00000 |
| 106 | blk.11.attn_q.weight | 0x7bbbf720 | 0x900000 |
| 107 | blk.11.attn_v.weight | 0x7c4bf720 | 0x2c0000 |
| 108 | blk.11.ffn_down.weight | 0x7c77f720 | 0x2680000 |
| 109 | blk.11.ffn_gate.weight | 0x7edff720 | 0x1f80000 |
| 110 | blk.11.ffn_norm.weight | 0x80d7f720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0x80d83720 | 0x1f80000 |
| 112 | blk.12.attn_k.weight | 0x82d03720 | 0x240000 |
| 113 | blk.12.attn_norm.weight | 0x82f43720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0x82f47720 | 0xb00000 |
| 115 | blk.12.attn_q.weight | 0x83a47720 | 0x900000 |
| 116 | blk.12.attn_v.weight | 0x84347720 | 0x2c0000 |
| 117 | blk.12.ffn_down.weight | 0x84607720 | 0x2680000 |
| 118 | blk.12.ffn_gate.weight | 0x86c87720 | 0x1f80000 |
| 119 | blk.12.ffn_norm.weight | 0x88c07720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0x88c0b720 | 0x1f80000 |
| 121 | blk.13.attn_k.weight | 0x8ab8b720 | 0x2c0000 |
| 122 | blk.13.attn_norm.weight | 0x8ae4b720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0x8ae4f720 | 0xb00000 |
| 124 | blk.13.attn_q.weight | 0x8b94f720 | 0xb00000 |
| 125 | blk.13.attn_v.weight | 0x8c44f720 | 0x2c0000 |
| 126 | blk.13.ffn_down.weight | 0x8c70f720 | 0x2680000 |
| 127 | blk.13.ffn_gate.weight | 0x8ed8f720 | 0x1f80000 |
| 128 | blk.13.ffn_norm.weight | 0x90d0f720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0x90d13720 | 0x1f80000 |
| 130 | blk.14.attn_k.weight | 0x92c93720 | 0x2c0000 |
| 131 | blk.14.attn_norm.weight | 0x92f53720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0x92f57720 | 0xb00000 |
| 133 | blk.14.attn_q.weight | 0x93a57720 | 0xb00000 |
| 134 | blk.14.attn_v.weight | 0x94557720 | 0x2c0000 |
| 135 | blk.14.ffn_down.weight | 0x94817720 | 0x2680000 |
| 136 | blk.14.ffn_gate.weight | 0x96e97720 | 0x1f80000 |
| 137 | blk.14.ffn_norm.weight | 0x98e17720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0x98e1b720 | 0x1f80000 |
| 139 | blk.15.attn_k.weight | 0x9ad9b720 | 0x240000 |
| 140 | blk.15.attn_norm.weight | 0x9afdb720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0x9afdf720 | 0xb00000 |
| 142 | blk.15.attn_q.weight | 0x9badf720 | 0x900000 |
| 143 | blk.15.attn_v.weight | 0x9c3df720 | 0x2c0000 |
| 144 | blk.15.ffn_down.weight | 0x9c69f720 | 0x2680000 |
| 145 | blk.15.ffn_gate.weight | 0x9ed1f720 | 0x1f80000 |
| 146 | blk.15.ffn_norm.weight | 0xa0c9f720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0xa0ca3720 | 0x1f80000 |
| 148 | blk.16.attn_k.weight | 0xa2c23720 | 0x2c0000 |
| 149 | blk.16.attn_norm.weight | 0xa2ee3720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0xa2ee7720 | 0xb00000 |
| 151 | blk.16.attn_q.weight | 0xa39e7720 | 0xb00000 |
| 152 | blk.16.attn_v.weight | 0xa44e7720 | 0x2c0000 |
| 153 | blk.16.ffn_down.weight | 0xa47a7720 | 0x2680000 |
| 154 | blk.16.ffn_gate.weight | 0xa6e27720 | 0x2680000 |
| 155 | blk.16.ffn_norm.weight | 0xa94a7720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0xa94ab720 | 0x2680000 |
| 157 | blk.17.attn_k.weight | 0xabb2b720 | 0x240000 |
| 158 | blk.17.attn_norm.weight | 0xabd6b720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0xabd6f720 | 0xb00000 |
| 160 | blk.17.attn_q.weight | 0xac86f720 | 0x900000 |
| 161 | blk.17.attn_v.weight | 0xad16f720 | 0x2c0000 |
| 162 | blk.17.ffn_down.weight | 0xad42f720 | 0x2df0000 |
| 163 | blk.17.ffn_gate.weight | 0xb021f720 | 0x2680000 |
| 164 | blk.17.ffn_norm.weight | 0xb289f720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0xb28a3720 | 0x2680000 |
| 166 | blk.18.attn_k.weight | 0xb4f23720 | 0x2c0000 |
| 167 | blk.18.attn_norm.weight | 0xb51e3720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0xb51e7720 | 0xb00000 |
| 169 | blk.18.attn_q.weight | 0xb5ce7720 | 0xb00000 |
| 170 | blk.18.attn_v.weight | 0xb67e7720 | 0x2c0000 |
| 171 | blk.18.ffn_down.weight | 0xb6aa7720 | 0x2df0000 |
| 172 | blk.18.ffn_gate.weight | 0xb9897720 | 0x2680000 |
| 173 | blk.18.ffn_norm.weight | 0xbbf17720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0xbbf1b720 | 0x2680000 |
| 175 | blk.19.attn_k.weight | 0xbe59b720 | 0x2c0000 |
| 176 | blk.19.attn_norm.weight | 0xbe85b720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0xbe85f720 | 0xb00000 |
| 178 | blk.19.attn_q.weight | 0xbf35f720 | 0xb00000 |
| 179 | blk.19.attn_v.weight | 0xbfe5f720 | 0x2c0000 |
| 180 | blk.19.ffn_down.weight | 0xc011f720 | 0x2df0000 |
| 181 | blk.19.ffn_gate.weight | 0xc2f0f720 | 0x2680000 |
| 182 | blk.19.ffn_norm.weight | 0xc558f720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0xc5593720 | 0x2680000 |
| 184 | blk.20.attn_k.weight | 0xc7c13720 | 0x2c0000 |
| 185 | blk.20.attn_norm.weight | 0xc7ed3720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0xc7ed7720 | 0xb00000 |
| 187 | blk.20.attn_q.weight | 0xc89d7720 | 0xb00000 |
| 188 | blk.20.attn_v.weight | 0xc94d7720 | 0x2c0000 |
| 189 | blk.20.ffn_down.weight | 0xc9797720 | 0x2df0000 |
| 190 | blk.20.ffn_gate.weight | 0xcc587720 | 0x2680000 |
| 191 | blk.20.ffn_norm.weight | 0xcec07720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0xcec0b720 | 0x2680000 |
| 193 | blk.21.attn_k.weight | 0xd128b720 | 0x2c0000 |
| 194 | blk.21.attn_norm.weight | 0xd154b720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0xd154f720 | 0xb00000 |
| 196 | blk.21.attn_q.weight | 0xd204f720 | 0xb00000 |
| 197 | blk.21.attn_v.weight | 0xd2b4f720 | 0x2c0000 |
| 198 | blk.21.ffn_down.weight | 0xd2e0f720 | 0x2df0000 |
| 199 | blk.21.ffn_gate.weight | 0xd5bff720 | 0x2680000 |
| 200 | blk.21.ffn_norm.weight | 0xd827f720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0xd8283720 | 0x2680000 |
| 202 | blk.22.attn_k.weight | 0xda903720 | 0x2c0000 |
| 203 | blk.22.attn_norm.weight | 0xdabc3720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0xdabc7720 | 0xb00000 |
| 205 | blk.22.attn_q.weight | 0xdb6c7720 | 0xb00000 |
| 206 | blk.22.attn_v.weight | 0xdc1c7720 | 0x2c0000 |
| 207 | blk.22.ffn_down.weight | 0xdc487720 | 0x2df0000 |
| 208 | blk.22.ffn_gate.weight | 0xdf277720 | 0x2680000 |
| 209 | blk.22.ffn_norm.weight | 0xe18f7720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0xe18fb720 | 0x2680000 |
| 211 | blk.23.attn_k.weight | 0xe3f7b720 | 0x2c0000 |
| 212 | blk.23.attn_norm.weight | 0xe423b720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0xe423f720 | 0xb00000 |
| 214 | blk.23.attn_q.weight | 0xe4d3f720 | 0xb00000 |
| 215 | blk.23.attn_v.weight | 0xe583f720 | 0x2c0000 |
| 216 | blk.23.ffn_down.weight | 0xe5aff720 | 0x2df0000 |
| 217 | blk.23.ffn_gate.weight | 0xe88ef720 | 0x2680000 |
| 218 | blk.23.ffn_norm.weight | 0xeaf6f720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0xeaf73720 | 0x2680000 |
| 220 | blk.24.attn_k.weight | 0xed5f3720 | 0x2c0000 |
| 221 | blk.24.attn_norm.weight | 0xed8b3720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0xed8b7720 | 0xb00000 |
| 223 | blk.24.attn_q.weight | 0xee3b7720 | 0xb00000 |
| 224 | blk.24.attn_v.weight | 0xeeeb7720 | 0x2c0000 |
| 225 | blk.24.ffn_down.weight | 0xef177720 | 0x2df0000 |
| 226 | blk.24.ffn_gate.weight | 0xf1f67720 | 0x2680000 |
| 227 | blk.24.ffn_norm.weight | 0xf45e7720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0xf45eb720 | 0x2680000 |
| 229 | blk.25.attn_k.weight | 0xf6c6b720 | 0x2c0000 |
| 230 | blk.25.attn_norm.weight | 0xf6f2b720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0xf6f2f720 | 0xb00000 |
| 232 | blk.25.attn_q.weight | 0xf7a2f720 | 0xb00000 |
| 233 | blk.25.attn_v.weight | 0xf852f720 | 0x2c0000 |
| 234 | blk.25.ffn_down.weight | 0xf87ef720 | 0x2df0000 |
| 235 | blk.25.ffn_gate.weight | 0xfb5df720 | 0x2680000 |
| 236 | blk.25.ffn_norm.weight | 0xfdc5f720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0xfdc63720 | 0x2680000 |
| 238 | blk.26.attn_k.weight | 0x1002e3720 | 0x2c0000 |
| 239 | blk.26.attn_norm.weight | 0x1005a3720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0x1005a7720 | 0xb00000 |
| 241 | blk.26.attn_q.weight | 0x1010a7720 | 0xb00000 |
| 242 | blk.26.attn_v.weight | 0x101ba7720 | 0x2c0000 |
| 243 | blk.26.ffn_down.weight | 0x101e67720 | 0x2df0000 |
| 244 | blk.26.ffn_gate.weight | 0x104c57720 | 0x2680000 |
| 245 | blk.26.ffn_norm.weight | 0x1072d7720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0x1072db720 | 0x2680000 |
| 247 | blk.27.attn_k.weight | 0x10995b720 | 0x2c0000 |
| 248 | blk.27.attn_norm.weight | 0x109c1b720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0x109c1f720 | 0xb00000 |
| 250 | blk.27.attn_q.weight | 0x10a71f720 | 0xb00000 |
| 251 | blk.27.attn_v.weight | 0x10b21f720 | 0x2c0000 |
| 252 | blk.27.ffn_down.weight | 0x10b4df720 | 0x2df0000 |
| 253 | blk.27.ffn_gate.weight | 0x10e2cf720 | 0x2680000 |
| 254 | blk.27.ffn_norm.weight | 0x11094f720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0x110953720 | 0x2680000 |
| 256 | blk.28.attn_k.weight | 0x112fd3720 | 0x2c0000 |
| 257 | blk.28.attn_norm.weight | 0x113293720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0x113297720 | 0xb00000 |
| 259 | blk.28.attn_q.weight | 0x113d97720 | 0xb00000 |
| 260 | blk.28.attn_v.weight | 0x114897720 | 0x2c0000 |
| 261 | blk.28.ffn_down.weight | 0x114b57720 | 0x2df0000 |
| 262 | blk.28.ffn_gate.weight | 0x117947720 | 0x2680000 |
| 263 | blk.28.ffn_norm.weight | 0x119fc7720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0x119fcb720 | 0x2680000 |
| 265 | blk.29.attn_k.weight | 0x11c64b720 | 0x2c0000 |
| 266 | blk.29.attn_norm.weight | 0x11c90b720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0x11c90f720 | 0xb00000 |
| 268 | blk.29.attn_q.weight | 0x11d40f720 | 0xb00000 |
| 269 | blk.29.attn_v.weight | 0x11df0f720 | 0x2c0000 |
| 270 | blk.29.ffn_down.weight | 0x11e1cf720 | 0x2df0000 |
| 271 | blk.29.ffn_gate.weight | 0x120fbf720 | 0x2680000 |
| 272 | blk.29.ffn_norm.weight | 0x12363f720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0x123643720 | 0x2680000 |
| 274 | blk.30.attn_k.weight | 0x125cc3720 | 0x2c0000 |
| 275 | blk.30.attn_norm.weight | 0x125f83720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0x125f87720 | 0xb00000 |
| 277 | blk.30.attn_q.weight | 0x126a87720 | 0xb00000 |
| 278 | blk.30.attn_v.weight | 0x127587720 | 0x2c0000 |
| 279 | blk.30.ffn_down.weight | 0x127847720 | 0x2df0000 |
| 280 | blk.30.ffn_gate.weight | 0x12a637720 | 0x2680000 |
| 281 | blk.30.ffn_norm.weight | 0x12ccb7720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0x12ccbb720 | 0x2680000 |
| 283 | blk.31.attn_k.weight | 0x12f33b720 | 0x240000 |
| 284 | blk.31.attn_norm.weight | 0x12f57b720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0x12f57f720 | 0xb00000 |
| 286 | blk.31.attn_q.weight | 0x13007f720 | 0x900000 |
| 287 | blk.31.attn_v.weight | 0x13097f720 | 0x2c0000 |
| 288 | blk.31.ffn_down.weight | 0x130c3f720 | 0x2df0000 |
| 289 | blk.31.ffn_gate.weight | 0x133a2f720 | 0x2680000 |
| 290 | blk.31.ffn_norm.weight | 0x1360af720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0x1360b3720 | 0x2680000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q5_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q4_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q5_K |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q4_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q4_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q6_K |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q6_K.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q6_K.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 18 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q6\_K.gguf - GGUF Internal File Dump](#watt-tool-8b-q6_kgguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x19afa000 |
| 1 | output_norm.weight | 0x1a273620 | 0x4000 |
| 2 | rope_freqs.weight | 0x1a277620 | 0x100 |
| 3 | token_embd.weight | 0x1a277720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x279bd720 | 0x2c0000 |
| 5 | blk.0.attn_norm.weight | 0x27c7d720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x27c81720 | 0xd20000 |
| 7 | blk.0.attn_q.weight | 0x289a1720 | 0xb00000 |
| 8 | blk.0.attn_v.weight | 0x294a1720 | 0x348000 |
| 9 | blk.0.ffn_down.weight | 0x297e9720 | 0x3b80000 |
| 10 | blk.0.ffn_gate.weight | 0x2d369720 | 0x2680000 |
| 11 | blk.0.ffn_norm.weight | 0x2f9e9720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x2f9ed720 | 0x2680000 |
| 13 | blk.1.attn_k.weight | 0x3206d720 | 0x2c0000 |
| 14 | blk.1.attn_norm.weight | 0x3232d720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x32331720 | 0xd20000 |
| 16 | blk.1.attn_q.weight | 0x33051720 | 0xb00000 |
| 17 | blk.1.attn_v.weight | 0x33b51720 | 0x348000 |
| 18 | blk.1.ffn_down.weight | 0x33e99720 | 0x3b80000 |
| 19 | blk.1.ffn_gate.weight | 0x37a19720 | 0x2680000 |
| 20 | blk.1.ffn_norm.weight | 0x3a099720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x3a09d720 | 0x2680000 |
| 22 | blk.2.attn_k.weight | 0x3c71d720 | 0x2c0000 |
| 23 | blk.2.attn_norm.weight | 0x3c9dd720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x3c9e1720 | 0xd20000 |
| 25 | blk.2.attn_q.weight | 0x3d701720 | 0xb00000 |
| 26 | blk.2.attn_v.weight | 0x3e201720 | 0x348000 |
| 27 | blk.2.ffn_down.weight | 0x3e549720 | 0x3b80000 |
| 28 | blk.2.ffn_gate.weight | 0x420c9720 | 0x2680000 |
| 29 | blk.2.ffn_norm.weight | 0x44749720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x4474d720 | 0x2680000 |
| 31 | blk.3.attn_k.weight | 0x46dcd720 | 0x2c0000 |
| 32 | blk.3.attn_norm.weight | 0x4708d720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x47091720 | 0xd20000 |
| 34 | blk.3.attn_q.weight | 0x47db1720 | 0xb00000 |
| 35 | blk.3.attn_v.weight | 0x488b1720 | 0x348000 |
| 36 | blk.3.ffn_down.weight | 0x48bf9720 | 0x3b80000 |
| 37 | blk.3.ffn_gate.weight | 0x4c779720 | 0x2680000 |
| 38 | blk.3.ffn_norm.weight | 0x4edf9720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x4edfd720 | 0x2680000 |
| 40 | blk.4.attn_k.weight | 0x5147d720 | 0x2c0000 |
| 41 | blk.4.attn_norm.weight | 0x5173d720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x51741720 | 0xd20000 |
| 43 | blk.4.attn_q.weight | 0x52461720 | 0xb00000 |
| 44 | blk.4.attn_v.weight | 0x52f61720 | 0x348000 |
| 45 | blk.4.ffn_down.weight | 0x532a9720 | 0x3b80000 |
| 46 | blk.4.ffn_gate.weight | 0x56e29720 | 0x2680000 |
| 47 | blk.4.ffn_norm.weight | 0x594a9720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x594ad720 | 0x2680000 |
| 49 | blk.5.attn_k.weight | 0x5bb2d720 | 0x2c0000 |
| 50 | blk.5.attn_norm.weight | 0x5bded720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x5bdf1720 | 0xd20000 |
| 52 | blk.5.attn_q.weight | 0x5cb11720 | 0xb00000 |
| 53 | blk.5.attn_v.weight | 0x5d611720 | 0x348000 |
| 54 | blk.5.ffn_down.weight | 0x5d959720 | 0x3b80000 |
| 55 | blk.5.ffn_gate.weight | 0x614d9720 | 0x2680000 |
| 56 | blk.5.ffn_norm.weight | 0x63b59720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x63b5d720 | 0x2680000 |
| 58 | blk.6.attn_k.weight | 0x661dd720 | 0x2c0000 |
| 59 | blk.6.attn_norm.weight | 0x6649d720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x664a1720 | 0xd20000 |
| 61 | blk.6.attn_q.weight | 0x671c1720 | 0xb00000 |
| 62 | blk.6.attn_v.weight | 0x67cc1720 | 0x348000 |
| 63 | blk.6.ffn_down.weight | 0x68009720 | 0x3b80000 |
| 64 | blk.6.ffn_gate.weight | 0x6bb89720 | 0x2680000 |
| 65 | blk.6.ffn_norm.weight | 0x6e209720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x6e20d720 | 0x2680000 |
| 67 | blk.7.attn_k.weight | 0x7088d720 | 0x2c0000 |
| 68 | blk.7.attn_norm.weight | 0x70b4d720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x70b51720 | 0xd20000 |
| 70 | blk.7.attn_q.weight | 0x71871720 | 0xb00000 |
| 71 | blk.7.attn_v.weight | 0x72371720 | 0x348000 |
| 72 | blk.7.ffn_down.weight | 0x726b9720 | 0x3b80000 |
| 73 | blk.7.ffn_gate.weight | 0x76239720 | 0x2680000 |
| 74 | blk.7.ffn_norm.weight | 0x788b9720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x788bd720 | 0x2680000 |
| 76 | blk.8.attn_k.weight | 0x7af3d720 | 0x2c0000 |
| 77 | blk.8.attn_norm.weight | 0x7b1fd720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x7b201720 | 0xd20000 |
| 79 | blk.8.attn_q.weight | 0x7bf21720 | 0xb00000 |
| 80 | blk.8.attn_v.weight | 0x7ca21720 | 0x348000 |
| 81 | blk.8.ffn_down.weight | 0x7cd69720 | 0x3b80000 |
| 82 | blk.8.ffn_gate.weight | 0x808e9720 | 0x2680000 |
| 83 | blk.8.ffn_norm.weight | 0x82f69720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x82f6d720 | 0x2680000 |
| 85 | blk.9.attn_k.weight | 0x855ed720 | 0x2c0000 |
| 86 | blk.9.attn_norm.weight | 0x858ad720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x858b1720 | 0xd20000 |
| 88 | blk.9.attn_q.weight | 0x865d1720 | 0xb00000 |
| 89 | blk.9.attn_v.weight | 0x870d1720 | 0x348000 |
| 90 | blk.9.ffn_down.weight | 0x87419720 | 0x3b80000 |
| 91 | blk.9.ffn_gate.weight | 0x8af99720 | 0x2680000 |
| 92 | blk.9.ffn_norm.weight | 0x8d619720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0x8d61d720 | 0x2680000 |
| 94 | blk.10.attn_k.weight | 0x8fc9d720 | 0x2c0000 |
| 95 | blk.10.attn_norm.weight | 0x8ff5d720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0x8ff61720 | 0xd20000 |
| 97 | blk.10.attn_q.weight | 0x90c81720 | 0xb00000 |
| 98 | blk.10.attn_v.weight | 0x91781720 | 0x348000 |
| 99 | blk.10.ffn_down.weight | 0x91ac9720 | 0x3b80000 |
| 100 | blk.10.ffn_gate.weight | 0x95649720 | 0x2680000 |
| 101 | blk.10.ffn_norm.weight | 0x97cc9720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0x97ccd720 | 0x2680000 |
| 103 | blk.11.attn_k.weight | 0x9a34d720 | 0x2c0000 |
| 104 | blk.11.attn_norm.weight | 0x9a60d720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0x9a611720 | 0xd20000 |
| 106 | blk.11.attn_q.weight | 0x9b331720 | 0xb00000 |
| 107 | blk.11.attn_v.weight | 0x9be31720 | 0x348000 |
| 108 | blk.11.ffn_down.weight | 0x9c179720 | 0x3b80000 |
| 109 | blk.11.ffn_gate.weight | 0x9fcf9720 | 0x2680000 |
| 110 | blk.11.ffn_norm.weight | 0xa2379720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0xa237d720 | 0x2680000 |
| 112 | blk.12.attn_k.weight | 0xa49fd720 | 0x2c0000 |
| 113 | blk.12.attn_norm.weight | 0xa4cbd720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0xa4cc1720 | 0xd20000 |
| 115 | blk.12.attn_q.weight | 0xa59e1720 | 0xb00000 |
| 116 | blk.12.attn_v.weight | 0xa64e1720 | 0x348000 |
| 117 | blk.12.ffn_down.weight | 0xa6829720 | 0x3b80000 |
| 118 | blk.12.ffn_gate.weight | 0xaa3a9720 | 0x2680000 |
| 119 | blk.12.ffn_norm.weight | 0xaca29720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0xaca2d720 | 0x2680000 |
| 121 | blk.13.attn_k.weight | 0xaf0ad720 | 0x348000 |
| 122 | blk.13.attn_norm.weight | 0xaf3f5720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0xaf3f9720 | 0xd20000 |
| 124 | blk.13.attn_q.weight | 0xb0119720 | 0xd20000 |
| 125 | blk.13.attn_v.weight | 0xb0e39720 | 0x440000 |
| 126 | blk.13.ffn_down.weight | 0xb1279720 | 0x3b80000 |
| 127 | blk.13.ffn_gate.weight | 0xb4df9720 | 0x2680000 |
| 128 | blk.13.ffn_norm.weight | 0xb7479720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0xb747d720 | 0x2680000 |
| 130 | blk.14.attn_k.weight | 0xb9afd720 | 0x348000 |
| 131 | blk.14.attn_norm.weight | 0xb9e45720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0xb9e49720 | 0xd20000 |
| 133 | blk.14.attn_q.weight | 0xbab69720 | 0xd20000 |
| 134 | blk.14.attn_v.weight | 0xbb889720 | 0x440000 |
| 135 | blk.14.ffn_down.weight | 0xbbcc9720 | 0x3b80000 |
| 136 | blk.14.ffn_gate.weight | 0xbf849720 | 0x2680000 |
| 137 | blk.14.ffn_norm.weight | 0xc1ec9720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0xc1ecd720 | 0x2680000 |
| 139 | blk.15.attn_k.weight | 0xc454d720 | 0x2c0000 |
| 140 | blk.15.attn_norm.weight | 0xc480d720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0xc4811720 | 0xd20000 |
| 142 | blk.15.attn_q.weight | 0xc5531720 | 0xb00000 |
| 143 | blk.15.attn_v.weight | 0xc6031720 | 0x348000 |
| 144 | blk.15.ffn_down.weight | 0xc6379720 | 0x3b80000 |
| 145 | blk.15.ffn_gate.weight | 0xc9ef9720 | 0x2680000 |
| 146 | blk.15.ffn_norm.weight | 0xcc579720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0xcc57d720 | 0x2680000 |
| 148 | blk.16.attn_k.weight | 0xcebfd720 | 0x348000 |
| 149 | blk.16.attn_norm.weight | 0xcef45720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0xcef49720 | 0xd20000 |
| 151 | blk.16.attn_q.weight | 0xcfc69720 | 0xd20000 |
| 152 | blk.16.attn_v.weight | 0xd0989720 | 0x440000 |
| 153 | blk.16.ffn_down.weight | 0xd0dc9720 | 0x3b80000 |
| 154 | blk.16.ffn_gate.weight | 0xd4949720 | 0x2df0000 |
| 155 | blk.16.ffn_norm.weight | 0xd7739720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0xd773d720 | 0x2df0000 |
| 157 | blk.17.attn_k.weight | 0xda52d720 | 0x2c0000 |
| 158 | blk.17.attn_norm.weight | 0xda7ed720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0xda7f1720 | 0xd20000 |
| 160 | blk.17.attn_q.weight | 0xdb511720 | 0xb00000 |
| 161 | blk.17.attn_v.weight | 0xdc011720 | 0x348000 |
| 162 | blk.17.ffn_down.weight | 0xdc359720 | 0x3b80000 |
| 163 | blk.17.ffn_gate.weight | 0xdfed9720 | 0x2df0000 |
| 164 | blk.17.ffn_norm.weight | 0xe2cc9720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0xe2ccd720 | 0x2df0000 |
| 166 | blk.18.attn_k.weight | 0xe5abd720 | 0x348000 |
| 167 | blk.18.attn_norm.weight | 0xe5e05720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0xe5e09720 | 0xd20000 |
| 169 | blk.18.attn_q.weight | 0xe6b29720 | 0xd20000 |
| 170 | blk.18.attn_v.weight | 0xe7849720 | 0x440000 |
| 171 | blk.18.ffn_down.weight | 0xe7c89720 | 0x3b80000 |
| 172 | blk.18.ffn_gate.weight | 0xeb809720 | 0x2df0000 |
| 173 | blk.18.ffn_norm.weight | 0xee5f9720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0xee5fd720 | 0x2df0000 |
| 175 | blk.19.attn_k.weight | 0xf13ed720 | 0x348000 |
| 176 | blk.19.attn_norm.weight | 0xf1735720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0xf1739720 | 0xd20000 |
| 178 | blk.19.attn_q.weight | 0xf2459720 | 0xd20000 |
| 179 | blk.19.attn_v.weight | 0xf3179720 | 0x440000 |
| 180 | blk.19.ffn_down.weight | 0xf35b9720 | 0x3b80000 |
| 181 | blk.19.ffn_gate.weight | 0xf7139720 | 0x2df0000 |
| 182 | blk.19.ffn_norm.weight | 0xf9f29720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0xf9f2d720 | 0x2df0000 |
| 184 | blk.20.attn_k.weight | 0xfcd1d720 | 0x348000 |
| 185 | blk.20.attn_norm.weight | 0xfd065720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0xfd069720 | 0xd20000 |
| 187 | blk.20.attn_q.weight | 0xfdd89720 | 0xd20000 |
| 188 | blk.20.attn_v.weight | 0xfeaa9720 | 0x440000 |
| 189 | blk.20.ffn_down.weight | 0xfeee9720 | 0x3b80000 |
| 190 | blk.20.ffn_gate.weight | 0x102a69720 | 0x2df0000 |
| 191 | blk.20.ffn_norm.weight | 0x105859720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x10585d720 | 0x2df0000 |
| 193 | blk.21.attn_k.weight | 0x10864d720 | 0x348000 |
| 194 | blk.21.attn_norm.weight | 0x108995720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x108999720 | 0xd20000 |
| 196 | blk.21.attn_q.weight | 0x1096b9720 | 0xd20000 |
| 197 | blk.21.attn_v.weight | 0x10a3d9720 | 0x440000 |
| 198 | blk.21.ffn_down.weight | 0x10a819720 | 0x3b80000 |
| 199 | blk.21.ffn_gate.weight | 0x10e399720 | 0x2df0000 |
| 200 | blk.21.ffn_norm.weight | 0x111189720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x11118d720 | 0x2df0000 |
| 202 | blk.22.attn_k.weight | 0x113f7d720 | 0x348000 |
| 203 | blk.22.attn_norm.weight | 0x1142c5720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x1142c9720 | 0xd20000 |
| 205 | blk.22.attn_q.weight | 0x114fe9720 | 0xd20000 |
| 206 | blk.22.attn_v.weight | 0x115d09720 | 0x440000 |
| 207 | blk.22.ffn_down.weight | 0x116149720 | 0x3b80000 |
| 208 | blk.22.ffn_gate.weight | 0x119cc9720 | 0x2df0000 |
| 209 | blk.22.ffn_norm.weight | 0x11cab9720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0x11cabd720 | 0x2df0000 |
| 211 | blk.23.attn_k.weight | 0x11f8ad720 | 0x348000 |
| 212 | blk.23.attn_norm.weight | 0x11fbf5720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0x11fbf9720 | 0xd20000 |
| 214 | blk.23.attn_q.weight | 0x120919720 | 0xd20000 |
| 215 | blk.23.attn_v.weight | 0x121639720 | 0x440000 |
| 216 | blk.23.ffn_down.weight | 0x121a79720 | 0x3b80000 |
| 217 | blk.23.ffn_gate.weight | 0x1255f9720 | 0x2df0000 |
| 218 | blk.23.ffn_norm.weight | 0x1283e9720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0x1283ed720 | 0x2df0000 |
| 220 | blk.24.attn_k.weight | 0x12b1dd720 | 0x348000 |
| 221 | blk.24.attn_norm.weight | 0x12b525720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0x12b529720 | 0xd20000 |
| 223 | blk.24.attn_q.weight | 0x12c249720 | 0xd20000 |
| 224 | blk.24.attn_v.weight | 0x12cf69720 | 0x440000 |
| 225 | blk.24.ffn_down.weight | 0x12d3a9720 | 0x3b80000 |
| 226 | blk.24.ffn_gate.weight | 0x130f29720 | 0x2df0000 |
| 227 | blk.24.ffn_norm.weight | 0x133d19720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0x133d1d720 | 0x2df0000 |
| 229 | blk.25.attn_k.weight | 0x136b0d720 | 0x348000 |
| 230 | blk.25.attn_norm.weight | 0x136e55720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0x136e59720 | 0xd20000 |
| 232 | blk.25.attn_q.weight | 0x137b79720 | 0xd20000 |
| 233 | blk.25.attn_v.weight | 0x138899720 | 0x440000 |
| 234 | blk.25.ffn_down.weight | 0x138cd9720 | 0x3b80000 |
| 235 | blk.25.ffn_gate.weight | 0x13c859720 | 0x2df0000 |
| 236 | blk.25.ffn_norm.weight | 0x13f649720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0x13f64d720 | 0x2df0000 |
| 238 | blk.26.attn_k.weight | 0x14243d720 | 0x348000 |
| 239 | blk.26.attn_norm.weight | 0x142785720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0x142789720 | 0xd20000 |
| 241 | blk.26.attn_q.weight | 0x1434a9720 | 0xd20000 |
| 242 | blk.26.attn_v.weight | 0x1441c9720 | 0x440000 |
| 243 | blk.26.ffn_down.weight | 0x144609720 | 0x3b80000 |
| 244 | blk.26.ffn_gate.weight | 0x148189720 | 0x2df0000 |
| 245 | blk.26.ffn_norm.weight | 0x14af79720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0x14af7d720 | 0x2df0000 |
| 247 | blk.27.attn_k.weight | 0x14dd6d720 | 0x348000 |
| 248 | blk.27.attn_norm.weight | 0x14e0b5720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0x14e0b9720 | 0xd20000 |
| 250 | blk.27.attn_q.weight | 0x14edd9720 | 0xd20000 |
| 251 | blk.27.attn_v.weight | 0x14faf9720 | 0x440000 |
| 252 | blk.27.ffn_down.weight | 0x14ff39720 | 0x3b80000 |
| 253 | blk.27.ffn_gate.weight | 0x153ab9720 | 0x2df0000 |
| 254 | blk.27.ffn_norm.weight | 0x1568a9720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0x1568ad720 | 0x2df0000 |
| 256 | blk.28.attn_k.weight | 0x15969d720 | 0x348000 |
| 257 | blk.28.attn_norm.weight | 0x1599e5720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0x1599e9720 | 0xd20000 |
| 259 | blk.28.attn_q.weight | 0x15a709720 | 0xd20000 |
| 260 | blk.28.attn_v.weight | 0x15b429720 | 0x440000 |
| 261 | blk.28.ffn_down.weight | 0x15b869720 | 0x3b80000 |
| 262 | blk.28.ffn_gate.weight | 0x15f3e9720 | 0x2df0000 |
| 263 | blk.28.ffn_norm.weight | 0x1621d9720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0x1621dd720 | 0x2df0000 |
| 265 | blk.29.attn_k.weight | 0x164fcd720 | 0x348000 |
| 266 | blk.29.attn_norm.weight | 0x165315720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0x165319720 | 0xd20000 |
| 268 | blk.29.attn_q.weight | 0x166039720 | 0xd20000 |
| 269 | blk.29.attn_v.weight | 0x166d59720 | 0x440000 |
| 270 | blk.29.ffn_down.weight | 0x167199720 | 0x3b80000 |
| 271 | blk.29.ffn_gate.weight | 0x16ad19720 | 0x2df0000 |
| 272 | blk.29.ffn_norm.weight | 0x16db09720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0x16db0d720 | 0x2df0000 |
| 274 | blk.30.attn_k.weight | 0x1708fd720 | 0x348000 |
| 275 | blk.30.attn_norm.weight | 0x170c45720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0x170c49720 | 0xd20000 |
| 277 | blk.30.attn_q.weight | 0x171969720 | 0xd20000 |
| 278 | blk.30.attn_v.weight | 0x172689720 | 0x440000 |
| 279 | blk.30.ffn_down.weight | 0x172ac9720 | 0x3b80000 |
| 280 | blk.30.ffn_gate.weight | 0x176649720 | 0x2df0000 |
| 281 | blk.30.ffn_norm.weight | 0x179439720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0x17943d720 | 0x2df0000 |
| 283 | blk.31.attn_k.weight | 0x17c22d720 | 0x2c0000 |
| 284 | blk.31.attn_norm.weight | 0x17c4ed720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0x17c4f1720 | 0xd20000 |
| 286 | blk.31.attn_q.weight | 0x17d211720 | 0xb00000 |
| 287 | blk.31.attn_v.weight | 0x17dd11720 | 0x348000 |
| 288 | blk.31.ffn_down.weight | 0x17e059720 | 0x3b80000 |
| 289 | blk.31.ffn_gate.weight | 0x181bd9720 | 0x2df0000 |
| 290 | blk.31.ffn_norm.weight | 0x1849c9720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0x1849cd720 | 0x2df0000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q6_K |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q5_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q5_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q5_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

982
scores/Watt-Tool-8B-Q8_0.md Normal file
View File

@@ -0,0 +1,982 @@
# Watt-Tool-8B-Q8_0.gguf - GGUF Internal File Dump
- Endian: LITTLE endian
## Key Value Metadata Store
There are 43 key-value pairs in this file
| POS | TYPE | Count | Key | Value |
|----:|:---------|-------:|:---------------------------------------|:--------------------------------------------------------------------|
| 1 | UINT32 | 1 | GGUF.version | 3 |
| 2 | UINT64 | 1 | GGUF.tensor_count | 292 |
| 3 | UINT64 | 1 | GGUF.kv_count | 40 |
| 4 | STRING | 1 | general.architecture | `llama` |
| 5 | STRING | 1 | general.type | `model` |
| 6 | STRING | 1 | general.name | `Watt Tool 8B GGUF` |
| 7 | STRING | 1 | general.finetune | `GGUF` |
| 8 | STRING | 1 | general.basename | `Watt-Tool` |
| 9 | STRING | 1 | general.size_label | `8B` |
| 10 | STRING | 1 | general.license | `apache-2.0` |
| 11 | UINT32 | 1 | general.base_model.count | 1 |
| 12 | STRING | 1 | general.base_model.0.name | `Llama 3.1 8B Instruct` |
| 13 | STRING | 1 | general.base_model.0.organization | `Meta Llama` |
| 14 | STRING | 1 | general.base_model.0.repo_url | `https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct` |
| 15 | [STRING] | 4 | general.tags | [ `function-calling`, `tool-use`, `llama`, `bfcl` ] |
| 16 | [STRING] | 1 | general.languages | [ `en` ] |
| 17 | UINT32 | 1 | llama.block_count | 32 |
| 18 | UINT32 | 1 | llama.context_length | 131072 |
| 19 | UINT32 | 1 | llama.embedding_length | 4096 |
| 20 | UINT32 | 1 | llama.feed_forward_length | 14336 |
| 21 | UINT32 | 1 | llama.attention.head_count | 32 |
| 22 | UINT32 | 1 | llama.attention.head_count_kv | 8 |
| 23 | FLOAT32 | 1 | llama.rope.freq_base | 500000.0 |
| 24 | FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon | 1e-05 |
| 25 | UINT32 | 1 | llama.attention.key_length | 128 |
| 26 | UINT32 | 1 | llama.attention.value_length | 128 |
| 27 | UINT32 | 1 | llama.vocab_size | 128256 |
| 28 | UINT32 | 1 | llama.rope.dimension_count | 128 |
| 29 | STRING | 1 | tokenizer.ggml.model | `gpt2` |
| 30 | STRING | 1 | tokenizer.ggml.pre | `llama-bpe` |
| 31 | [STRING] | 128256 | tokenizer.ggml.tokens | [ `!`, `"`, `#`, `$`, `%`, ... ] |
| 32 | [INT32] | 128256 | tokenizer.ggml.token_type | [ 1, 1, 1, 1, 1, 1, 1, ... ] |
| 33 | [STRING] | 280147 | tokenizer.ggml.merges | [ `Ġ Ġ`, `Ġ ĠĠĠ`, `ĠĠ ĠĠ`, `ĠĠĠ Ġ`, `i n`, ... ] |
| 34 | UINT32 | 1 | tokenizer.ggml.bos_token_id | 128000 |
| 35 | UINT32 | 1 | tokenizer.ggml.eos_token_id | 128009 |
| 36 | UINT32 | 1 | tokenizer.ggml.padding_token_id | 128009 |
| 37 | STRING | 1 | tokenizer.chat_template | `{{ '<|begin_of_text|>' }}{% if`...`d|>' }}{% endif %}{% endfor %}` |
| 38 | UINT32 | 1 | general.quantization_version | 2 |
| 39 | UINT32 | 1 | general.file_type | 7 |
| 40 | STRING | 1 | quantize.imatrix.file | `./imatrix/imatrix-Watt-Tool-8B-small.dat` |
| 41 | STRING | 1 | quantize.imatrix.dataset | `../../datasets/imatrix/calibration_eur_small.txt` |
| 42 | INT32 | 1 | quantize.imatrix.entries_count | 225 |
| 43 | INT32 | 1 | quantize.imatrix.chunks_count | 962 |
## Tensors Overview ~8B Elements
Total number of elements in all tensors: 8030261312 Elements
- [Watt-Tool-8B-Q8\_0.gguf - GGUF Internal File Dump](#watt-tool-8b-q8_0gguf---gguf-internal-file-dump)
- [Key Value Metadata Store](#key-value-metadata-store)
- [Tensors Overview ~8B Elements](#tensors-overview-8b-elements)
- [Tensor Data Offset](#tensor-data-offset)
- [Base Tensor Group : ~1B Elements](#base-tensor-group--1b-elements)
- [Block 0 Tensor Group : ~218M Elements](#block-0-tensor-group--218m-elements)
- [Block 1 Tensor Group : ~218M Elements](#block-1-tensor-group--218m-elements)
- [Block 2 Tensor Group : ~218M Elements](#block-2-tensor-group--218m-elements)
- [Block 3 Tensor Group : ~218M Elements](#block-3-tensor-group--218m-elements)
- [Block 4 Tensor Group : ~218M Elements](#block-4-tensor-group--218m-elements)
- [Block 5 Tensor Group : ~218M Elements](#block-5-tensor-group--218m-elements)
- [Block 6 Tensor Group : ~218M Elements](#block-6-tensor-group--218m-elements)
- [Block 7 Tensor Group : ~218M Elements](#block-7-tensor-group--218m-elements)
- [Block 8 Tensor Group : ~218M Elements](#block-8-tensor-group--218m-elements)
- [Block 9 Tensor Group : ~218M Elements](#block-9-tensor-group--218m-elements)
- [Block 10 Tensor Group : ~218M Elements](#block-10-tensor-group--218m-elements)
- [Block 11 Tensor Group : ~218M Elements](#block-11-tensor-group--218m-elements)
- [Block 12 Tensor Group : ~218M Elements](#block-12-tensor-group--218m-elements)
- [Block 13 Tensor Group : ~218M Elements](#block-13-tensor-group--218m-elements)
- [Block 14 Tensor Group : ~218M Elements](#block-14-tensor-group--218m-elements)
- [Block 15 Tensor Group : ~218M Elements](#block-15-tensor-group--218m-elements)
- [Block 16 Tensor Group : ~218M Elements](#block-16-tensor-group--218m-elements)
- [Block 17 Tensor Group : ~218M Elements](#block-17-tensor-group--218m-elements)
- [Block 18 Tensor Group : ~218M Elements](#block-18-tensor-group--218m-elements)
- [Block 19 Tensor Group : ~218M Elements](#block-19-tensor-group--218m-elements)
- [Block 20 Tensor Group : ~218M Elements](#block-20-tensor-group--218m-elements)
- [Block 21 Tensor Group : ~218M Elements](#block-21-tensor-group--218m-elements)
- [Block 22 Tensor Group : ~218M Elements](#block-22-tensor-group--218m-elements)
- [Block 23 Tensor Group : ~218M Elements](#block-23-tensor-group--218m-elements)
- [Block 24 Tensor Group : ~218M Elements](#block-24-tensor-group--218m-elements)
- [Block 25 Tensor Group : ~218M Elements](#block-25-tensor-group--218m-elements)
- [Block 26 Tensor Group : ~218M Elements](#block-26-tensor-group--218m-elements)
- [Block 27 Tensor Group : ~218M Elements](#block-27-tensor-group--218m-elements)
- [Block 28 Tensor Group : ~218M Elements](#block-28-tensor-group--218m-elements)
- [Block 29 Tensor Group : ~218M Elements](#block-29-tensor-group--218m-elements)
- [Block 30 Tensor Group : ~218M Elements](#block-30-tensor-group--218m-elements)
- [Block 31 Tensor Group : ~218M Elements](#block-31-tensor-group--218m-elements)
### Tensor Data Offset
This table contains the offset and data segment relative to start of file
| T_ID | Tensor Layer Name | Data Offset (B) | Data Size (B) |
|-----:|:--------------------------|-----------------:|-----------------:|
| 0 | output.weight | 0x779620 | 0x21450000 |
| 1 | output_norm.weight | 0x21bc9620 | 0x4000 |
| 2 | rope_freqs.weight | 0x21bcd620 | 0x100 |
| 3 | token_embd.weight | 0x21bcd720 | 0xd746000 |
| 4 | blk.0.attn_k.weight | 0x2f313720 | 0x348000 |
| 5 | blk.0.attn_norm.weight | 0x2f65b720 | 0x4000 |
| 6 | blk.0.attn_output.weight | 0x2f65f720 | 0x1100000 |
| 7 | blk.0.attn_q.weight | 0x3075f720 | 0xd20000 |
| 8 | blk.0.attn_v.weight | 0x3147f720 | 0x440000 |
| 9 | blk.0.ffn_down.weight | 0x318bf720 | 0x3b80000 |
| 10 | blk.0.ffn_gate.weight | 0x3543f720 | 0x2df0000 |
| 11 | blk.0.ffn_norm.weight | 0x3822f720 | 0x4000 |
| 12 | blk.0.ffn_up.weight | 0x38233720 | 0x2df0000 |
| 13 | blk.1.attn_k.weight | 0x3b023720 | 0x348000 |
| 14 | blk.1.attn_norm.weight | 0x3b36b720 | 0x4000 |
| 15 | blk.1.attn_output.weight | 0x3b36f720 | 0x1100000 |
| 16 | blk.1.attn_q.weight | 0x3c46f720 | 0xd20000 |
| 17 | blk.1.attn_v.weight | 0x3d18f720 | 0x440000 |
| 18 | blk.1.ffn_down.weight | 0x3d5cf720 | 0x3b80000 |
| 19 | blk.1.ffn_gate.weight | 0x4114f720 | 0x2df0000 |
| 20 | blk.1.ffn_norm.weight | 0x43f3f720 | 0x4000 |
| 21 | blk.1.ffn_up.weight | 0x43f43720 | 0x2df0000 |
| 22 | blk.2.attn_k.weight | 0x46d33720 | 0x348000 |
| 23 | blk.2.attn_norm.weight | 0x4707b720 | 0x4000 |
| 24 | blk.2.attn_output.weight | 0x4707f720 | 0x1100000 |
| 25 | blk.2.attn_q.weight | 0x4817f720 | 0xd20000 |
| 26 | blk.2.attn_v.weight | 0x48e9f720 | 0x440000 |
| 27 | blk.2.ffn_down.weight | 0x492df720 | 0x3b80000 |
| 28 | blk.2.ffn_gate.weight | 0x4ce5f720 | 0x2df0000 |
| 29 | blk.2.ffn_norm.weight | 0x4fc4f720 | 0x4000 |
| 30 | blk.2.ffn_up.weight | 0x4fc53720 | 0x2df0000 |
| 31 | blk.3.attn_k.weight | 0x52a43720 | 0x348000 |
| 32 | blk.3.attn_norm.weight | 0x52d8b720 | 0x4000 |
| 33 | blk.3.attn_output.weight | 0x52d8f720 | 0x1100000 |
| 34 | blk.3.attn_q.weight | 0x53e8f720 | 0xd20000 |
| 35 | blk.3.attn_v.weight | 0x54baf720 | 0x440000 |
| 36 | blk.3.ffn_down.weight | 0x54fef720 | 0x3b80000 |
| 37 | blk.3.ffn_gate.weight | 0x58b6f720 | 0x2df0000 |
| 38 | blk.3.ffn_norm.weight | 0x5b95f720 | 0x4000 |
| 39 | blk.3.ffn_up.weight | 0x5b963720 | 0x2df0000 |
| 40 | blk.4.attn_k.weight | 0x5e753720 | 0x348000 |
| 41 | blk.4.attn_norm.weight | 0x5ea9b720 | 0x4000 |
| 42 | blk.4.attn_output.weight | 0x5ea9f720 | 0x1100000 |
| 43 | blk.4.attn_q.weight | 0x5fb9f720 | 0xd20000 |
| 44 | blk.4.attn_v.weight | 0x608bf720 | 0x440000 |
| 45 | blk.4.ffn_down.weight | 0x60cff720 | 0x3b80000 |
| 46 | blk.4.ffn_gate.weight | 0x6487f720 | 0x2df0000 |
| 47 | blk.4.ffn_norm.weight | 0x6766f720 | 0x4000 |
| 48 | blk.4.ffn_up.weight | 0x67673720 | 0x2df0000 |
| 49 | blk.5.attn_k.weight | 0x6a463720 | 0x348000 |
| 50 | blk.5.attn_norm.weight | 0x6a7ab720 | 0x4000 |
| 51 | blk.5.attn_output.weight | 0x6a7af720 | 0x1100000 |
| 52 | blk.5.attn_q.weight | 0x6b8af720 | 0xd20000 |
| 53 | blk.5.attn_v.weight | 0x6c5cf720 | 0x440000 |
| 54 | blk.5.ffn_down.weight | 0x6ca0f720 | 0x3b80000 |
| 55 | blk.5.ffn_gate.weight | 0x7058f720 | 0x2df0000 |
| 56 | blk.5.ffn_norm.weight | 0x7337f720 | 0x4000 |
| 57 | blk.5.ffn_up.weight | 0x73383720 | 0x2df0000 |
| 58 | blk.6.attn_k.weight | 0x76173720 | 0x348000 |
| 59 | blk.6.attn_norm.weight | 0x764bb720 | 0x4000 |
| 60 | blk.6.attn_output.weight | 0x764bf720 | 0x1100000 |
| 61 | blk.6.attn_q.weight | 0x775bf720 | 0xd20000 |
| 62 | blk.6.attn_v.weight | 0x782df720 | 0x440000 |
| 63 | blk.6.ffn_down.weight | 0x7871f720 | 0x3b80000 |
| 64 | blk.6.ffn_gate.weight | 0x7c29f720 | 0x2df0000 |
| 65 | blk.6.ffn_norm.weight | 0x7f08f720 | 0x4000 |
| 66 | blk.6.ffn_up.weight | 0x7f093720 | 0x2df0000 |
| 67 | blk.7.attn_k.weight | 0x81e83720 | 0x348000 |
| 68 | blk.7.attn_norm.weight | 0x821cb720 | 0x4000 |
| 69 | blk.7.attn_output.weight | 0x821cf720 | 0x1100000 |
| 70 | blk.7.attn_q.weight | 0x832cf720 | 0xd20000 |
| 71 | blk.7.attn_v.weight | 0x83fef720 | 0x440000 |
| 72 | blk.7.ffn_down.weight | 0x8442f720 | 0x3b80000 |
| 73 | blk.7.ffn_gate.weight | 0x87faf720 | 0x2df0000 |
| 74 | blk.7.ffn_norm.weight | 0x8ad9f720 | 0x4000 |
| 75 | blk.7.ffn_up.weight | 0x8ada3720 | 0x2df0000 |
| 76 | blk.8.attn_k.weight | 0x8db93720 | 0x348000 |
| 77 | blk.8.attn_norm.weight | 0x8dedb720 | 0x4000 |
| 78 | blk.8.attn_output.weight | 0x8dedf720 | 0x1100000 |
| 79 | blk.8.attn_q.weight | 0x8efdf720 | 0xd20000 |
| 80 | blk.8.attn_v.weight | 0x8fcff720 | 0x440000 |
| 81 | blk.8.ffn_down.weight | 0x9013f720 | 0x3b80000 |
| 82 | blk.8.ffn_gate.weight | 0x93cbf720 | 0x2df0000 |
| 83 | blk.8.ffn_norm.weight | 0x96aaf720 | 0x4000 |
| 84 | blk.8.ffn_up.weight | 0x96ab3720 | 0x2df0000 |
| 85 | blk.9.attn_k.weight | 0x998a3720 | 0x348000 |
| 86 | blk.9.attn_norm.weight | 0x99beb720 | 0x4000 |
| 87 | blk.9.attn_output.weight | 0x99bef720 | 0x1100000 |
| 88 | blk.9.attn_q.weight | 0x9acef720 | 0xd20000 |
| 89 | blk.9.attn_v.weight | 0x9ba0f720 | 0x440000 |
| 90 | blk.9.ffn_down.weight | 0x9be4f720 | 0x3b80000 |
| 91 | blk.9.ffn_gate.weight | 0x9f9cf720 | 0x2df0000 |
| 92 | blk.9.ffn_norm.weight | 0xa27bf720 | 0x4000 |
| 93 | blk.9.ffn_up.weight | 0xa27c3720 | 0x2df0000 |
| 94 | blk.10.attn_k.weight | 0xa55b3720 | 0x348000 |
| 95 | blk.10.attn_norm.weight | 0xa58fb720 | 0x4000 |
| 96 | blk.10.attn_output.weight | 0xa58ff720 | 0x1100000 |
| 97 | blk.10.attn_q.weight | 0xa69ff720 | 0xd20000 |
| 98 | blk.10.attn_v.weight | 0xa771f720 | 0x440000 |
| 99 | blk.10.ffn_down.weight | 0xa7b5f720 | 0x3b80000 |
| 100 | blk.10.ffn_gate.weight | 0xab6df720 | 0x2df0000 |
| 101 | blk.10.ffn_norm.weight | 0xae4cf720 | 0x4000 |
| 102 | blk.10.ffn_up.weight | 0xae4d3720 | 0x2df0000 |
| 103 | blk.11.attn_k.weight | 0xb12c3720 | 0x348000 |
| 104 | blk.11.attn_norm.weight | 0xb160b720 | 0x4000 |
| 105 | blk.11.attn_output.weight | 0xb160f720 | 0x1100000 |
| 106 | blk.11.attn_q.weight | 0xb270f720 | 0xd20000 |
| 107 | blk.11.attn_v.weight | 0xb342f720 | 0x440000 |
| 108 | blk.11.ffn_down.weight | 0xb386f720 | 0x3b80000 |
| 109 | blk.11.ffn_gate.weight | 0xb73ef720 | 0x2df0000 |
| 110 | blk.11.ffn_norm.weight | 0xba1df720 | 0x4000 |
| 111 | blk.11.ffn_up.weight | 0xba1e3720 | 0x2df0000 |
| 112 | blk.12.attn_k.weight | 0xbcfd3720 | 0x348000 |
| 113 | blk.12.attn_norm.weight | 0xbd31b720 | 0x4000 |
| 114 | blk.12.attn_output.weight | 0xbd31f720 | 0x1100000 |
| 115 | blk.12.attn_q.weight | 0xbe41f720 | 0xd20000 |
| 116 | blk.12.attn_v.weight | 0xbf13f720 | 0x440000 |
| 117 | blk.12.ffn_down.weight | 0xbf57f720 | 0x3b80000 |
| 118 | blk.12.ffn_gate.weight | 0xc30ff720 | 0x2df0000 |
| 119 | blk.12.ffn_norm.weight | 0xc5eef720 | 0x4000 |
| 120 | blk.12.ffn_up.weight | 0xc5ef3720 | 0x2df0000 |
| 121 | blk.13.attn_k.weight | 0xc8ce3720 | 0x440000 |
| 122 | blk.13.attn_norm.weight | 0xc9123720 | 0x4000 |
| 123 | blk.13.attn_output.weight | 0xc9127720 | 0x1100000 |
| 124 | blk.13.attn_q.weight | 0xca227720 | 0x1100000 |
| 125 | blk.13.attn_v.weight | 0xcb327720 | 0x800000 |
| 126 | blk.13.ffn_down.weight | 0xcbb27720 | 0x3b80000 |
| 127 | blk.13.ffn_gate.weight | 0xcf6a7720 | 0x2df0000 |
| 128 | blk.13.ffn_norm.weight | 0xd2497720 | 0x4000 |
| 129 | blk.13.ffn_up.weight | 0xd249b720 | 0x2df0000 |
| 130 | blk.14.attn_k.weight | 0xd528b720 | 0x440000 |
| 131 | blk.14.attn_norm.weight | 0xd56cb720 | 0x4000 |
| 132 | blk.14.attn_output.weight | 0xd56cf720 | 0x1100000 |
| 133 | blk.14.attn_q.weight | 0xd67cf720 | 0x1100000 |
| 134 | blk.14.attn_v.weight | 0xd78cf720 | 0x800000 |
| 135 | blk.14.ffn_down.weight | 0xd80cf720 | 0x3b80000 |
| 136 | blk.14.ffn_gate.weight | 0xdbc4f720 | 0x2df0000 |
| 137 | blk.14.ffn_norm.weight | 0xdea3f720 | 0x4000 |
| 138 | blk.14.ffn_up.weight | 0xdea43720 | 0x2df0000 |
| 139 | blk.15.attn_k.weight | 0xe1833720 | 0x348000 |
| 140 | blk.15.attn_norm.weight | 0xe1b7b720 | 0x4000 |
| 141 | blk.15.attn_output.weight | 0xe1b7f720 | 0x1100000 |
| 142 | blk.15.attn_q.weight | 0xe2c7f720 | 0xd20000 |
| 143 | blk.15.attn_v.weight | 0xe399f720 | 0x440000 |
| 144 | blk.15.ffn_down.weight | 0xe3ddf720 | 0x3b80000 |
| 145 | blk.15.ffn_gate.weight | 0xe795f720 | 0x2df0000 |
| 146 | blk.15.ffn_norm.weight | 0xea74f720 | 0x4000 |
| 147 | blk.15.ffn_up.weight | 0xea753720 | 0x2df0000 |
| 148 | blk.16.attn_k.weight | 0xed543720 | 0x440000 |
| 149 | blk.16.attn_norm.weight | 0xed983720 | 0x4000 |
| 150 | blk.16.attn_output.weight | 0xed987720 | 0x1100000 |
| 151 | blk.16.attn_q.weight | 0xeea87720 | 0x1100000 |
| 152 | blk.16.attn_v.weight | 0xefb87720 | 0x800000 |
| 153 | blk.16.ffn_down.weight | 0xf0387720 | 0x3b80000 |
| 154 | blk.16.ffn_gate.weight | 0xf3f07720 | 0x3b80000 |
| 155 | blk.16.ffn_norm.weight | 0xf7a87720 | 0x4000 |
| 156 | blk.16.ffn_up.weight | 0xf7a8b720 | 0x3b80000 |
| 157 | blk.17.attn_k.weight | 0xfb60b720 | 0x348000 |
| 158 | blk.17.attn_norm.weight | 0xfb953720 | 0x4000 |
| 159 | blk.17.attn_output.weight | 0xfb957720 | 0x1100000 |
| 160 | blk.17.attn_q.weight | 0xfca57720 | 0xd20000 |
| 161 | blk.17.attn_v.weight | 0xfd777720 | 0x440000 |
| 162 | blk.17.ffn_down.weight | 0xfdbb7720 | 0x3b80000 |
| 163 | blk.17.ffn_gate.weight | 0x101737720 | 0x3b80000 |
| 164 | blk.17.ffn_norm.weight | 0x1052b7720 | 0x4000 |
| 165 | blk.17.ffn_up.weight | 0x1052bb720 | 0x3b80000 |
| 166 | blk.18.attn_k.weight | 0x108e3b720 | 0x440000 |
| 167 | blk.18.attn_norm.weight | 0x10927b720 | 0x4000 |
| 168 | blk.18.attn_output.weight | 0x10927f720 | 0x1100000 |
| 169 | blk.18.attn_q.weight | 0x10a37f720 | 0x1100000 |
| 170 | blk.18.attn_v.weight | 0x10b47f720 | 0x800000 |
| 171 | blk.18.ffn_down.weight | 0x10bc7f720 | 0x3b80000 |
| 172 | blk.18.ffn_gate.weight | 0x10f7ff720 | 0x3b80000 |
| 173 | blk.18.ffn_norm.weight | 0x11337f720 | 0x4000 |
| 174 | blk.18.ffn_up.weight | 0x113383720 | 0x3b80000 |
| 175 | blk.19.attn_k.weight | 0x116f03720 | 0x440000 |
| 176 | blk.19.attn_norm.weight | 0x117343720 | 0x4000 |
| 177 | blk.19.attn_output.weight | 0x117347720 | 0x1100000 |
| 178 | blk.19.attn_q.weight | 0x118447720 | 0x1100000 |
| 179 | blk.19.attn_v.weight | 0x119547720 | 0x800000 |
| 180 | blk.19.ffn_down.weight | 0x119d47720 | 0x3b80000 |
| 181 | blk.19.ffn_gate.weight | 0x11d8c7720 | 0x3b80000 |
| 182 | blk.19.ffn_norm.weight | 0x121447720 | 0x4000 |
| 183 | blk.19.ffn_up.weight | 0x12144b720 | 0x3b80000 |
| 184 | blk.20.attn_k.weight | 0x124fcb720 | 0x440000 |
| 185 | blk.20.attn_norm.weight | 0x12540b720 | 0x4000 |
| 186 | blk.20.attn_output.weight | 0x12540f720 | 0x1100000 |
| 187 | blk.20.attn_q.weight | 0x12650f720 | 0x1100000 |
| 188 | blk.20.attn_v.weight | 0x12760f720 | 0x800000 |
| 189 | blk.20.ffn_down.weight | 0x127e0f720 | 0x3b80000 |
| 190 | blk.20.ffn_gate.weight | 0x12b98f720 | 0x3b80000 |
| 191 | blk.20.ffn_norm.weight | 0x12f50f720 | 0x4000 |
| 192 | blk.20.ffn_up.weight | 0x12f513720 | 0x3b80000 |
| 193 | blk.21.attn_k.weight | 0x133093720 | 0x440000 |
| 194 | blk.21.attn_norm.weight | 0x1334d3720 | 0x4000 |
| 195 | blk.21.attn_output.weight | 0x1334d7720 | 0x1100000 |
| 196 | blk.21.attn_q.weight | 0x1345d7720 | 0x1100000 |
| 197 | blk.21.attn_v.weight | 0x1356d7720 | 0x800000 |
| 198 | blk.21.ffn_down.weight | 0x135ed7720 | 0x3b80000 |
| 199 | blk.21.ffn_gate.weight | 0x139a57720 | 0x3b80000 |
| 200 | blk.21.ffn_norm.weight | 0x13d5d7720 | 0x4000 |
| 201 | blk.21.ffn_up.weight | 0x13d5db720 | 0x3b80000 |
| 202 | blk.22.attn_k.weight | 0x14115b720 | 0x440000 |
| 203 | blk.22.attn_norm.weight | 0x14159b720 | 0x4000 |
| 204 | blk.22.attn_output.weight | 0x14159f720 | 0x1100000 |
| 205 | blk.22.attn_q.weight | 0x14269f720 | 0x1100000 |
| 206 | blk.22.attn_v.weight | 0x14379f720 | 0x800000 |
| 207 | blk.22.ffn_down.weight | 0x143f9f720 | 0x3b80000 |
| 208 | blk.22.ffn_gate.weight | 0x147b1f720 | 0x3b80000 |
| 209 | blk.22.ffn_norm.weight | 0x14b69f720 | 0x4000 |
| 210 | blk.22.ffn_up.weight | 0x14b6a3720 | 0x3b80000 |
| 211 | blk.23.attn_k.weight | 0x14f223720 | 0x440000 |
| 212 | blk.23.attn_norm.weight | 0x14f663720 | 0x4000 |
| 213 | blk.23.attn_output.weight | 0x14f667720 | 0x1100000 |
| 214 | blk.23.attn_q.weight | 0x150767720 | 0x1100000 |
| 215 | blk.23.attn_v.weight | 0x151867720 | 0x800000 |
| 216 | blk.23.ffn_down.weight | 0x152067720 | 0x3b80000 |
| 217 | blk.23.ffn_gate.weight | 0x155be7720 | 0x3b80000 |
| 218 | blk.23.ffn_norm.weight | 0x159767720 | 0x4000 |
| 219 | blk.23.ffn_up.weight | 0x15976b720 | 0x3b80000 |
| 220 | blk.24.attn_k.weight | 0x15d2eb720 | 0x440000 |
| 221 | blk.24.attn_norm.weight | 0x15d72b720 | 0x4000 |
| 222 | blk.24.attn_output.weight | 0x15d72f720 | 0x1100000 |
| 223 | blk.24.attn_q.weight | 0x15e82f720 | 0x1100000 |
| 224 | blk.24.attn_v.weight | 0x15f92f720 | 0x800000 |
| 225 | blk.24.ffn_down.weight | 0x16012f720 | 0x3b80000 |
| 226 | blk.24.ffn_gate.weight | 0x163caf720 | 0x3b80000 |
| 227 | blk.24.ffn_norm.weight | 0x16782f720 | 0x4000 |
| 228 | blk.24.ffn_up.weight | 0x167833720 | 0x3b80000 |
| 229 | blk.25.attn_k.weight | 0x16b3b3720 | 0x440000 |
| 230 | blk.25.attn_norm.weight | 0x16b7f3720 | 0x4000 |
| 231 | blk.25.attn_output.weight | 0x16b7f7720 | 0x1100000 |
| 232 | blk.25.attn_q.weight | 0x16c8f7720 | 0x1100000 |
| 233 | blk.25.attn_v.weight | 0x16d9f7720 | 0x800000 |
| 234 | blk.25.ffn_down.weight | 0x16e1f7720 | 0x3b80000 |
| 235 | blk.25.ffn_gate.weight | 0x171d77720 | 0x3b80000 |
| 236 | blk.25.ffn_norm.weight | 0x1758f7720 | 0x4000 |
| 237 | blk.25.ffn_up.weight | 0x1758fb720 | 0x3b80000 |
| 238 | blk.26.attn_k.weight | 0x17947b720 | 0x440000 |
| 239 | blk.26.attn_norm.weight | 0x1798bb720 | 0x4000 |
| 240 | blk.26.attn_output.weight | 0x1798bf720 | 0x1100000 |
| 241 | blk.26.attn_q.weight | 0x17a9bf720 | 0x1100000 |
| 242 | blk.26.attn_v.weight | 0x17babf720 | 0x800000 |
| 243 | blk.26.ffn_down.weight | 0x17c2bf720 | 0x3b80000 |
| 244 | blk.26.ffn_gate.weight | 0x17fe3f720 | 0x3b80000 |
| 245 | blk.26.ffn_norm.weight | 0x1839bf720 | 0x4000 |
| 246 | blk.26.ffn_up.weight | 0x1839c3720 | 0x3b80000 |
| 247 | blk.27.attn_k.weight | 0x187543720 | 0x440000 |
| 248 | blk.27.attn_norm.weight | 0x187983720 | 0x4000 |
| 249 | blk.27.attn_output.weight | 0x187987720 | 0x1100000 |
| 250 | blk.27.attn_q.weight | 0x188a87720 | 0x1100000 |
| 251 | blk.27.attn_v.weight | 0x189b87720 | 0x800000 |
| 252 | blk.27.ffn_down.weight | 0x18a387720 | 0x3b80000 |
| 253 | blk.27.ffn_gate.weight | 0x18df07720 | 0x3b80000 |
| 254 | blk.27.ffn_norm.weight | 0x191a87720 | 0x4000 |
| 255 | blk.27.ffn_up.weight | 0x191a8b720 | 0x3b80000 |
| 256 | blk.28.attn_k.weight | 0x19560b720 | 0x440000 |
| 257 | blk.28.attn_norm.weight | 0x195a4b720 | 0x4000 |
| 258 | blk.28.attn_output.weight | 0x195a4f720 | 0x1100000 |
| 259 | blk.28.attn_q.weight | 0x196b4f720 | 0x1100000 |
| 260 | blk.28.attn_v.weight | 0x197c4f720 | 0x800000 |
| 261 | blk.28.ffn_down.weight | 0x19844f720 | 0x3b80000 |
| 262 | blk.28.ffn_gate.weight | 0x19bfcf720 | 0x3b80000 |
| 263 | blk.28.ffn_norm.weight | 0x19fb4f720 | 0x4000 |
| 264 | blk.28.ffn_up.weight | 0x19fb53720 | 0x3b80000 |
| 265 | blk.29.attn_k.weight | 0x1a36d3720 | 0x440000 |
| 266 | blk.29.attn_norm.weight | 0x1a3b13720 | 0x4000 |
| 267 | blk.29.attn_output.weight | 0x1a3b17720 | 0x1100000 |
| 268 | blk.29.attn_q.weight | 0x1a4c17720 | 0x1100000 |
| 269 | blk.29.attn_v.weight | 0x1a5d17720 | 0x800000 |
| 270 | blk.29.ffn_down.weight | 0x1a6517720 | 0x3b80000 |
| 271 | blk.29.ffn_gate.weight | 0x1aa097720 | 0x3b80000 |
| 272 | blk.29.ffn_norm.weight | 0x1adc17720 | 0x4000 |
| 273 | blk.29.ffn_up.weight | 0x1adc1b720 | 0x3b80000 |
| 274 | blk.30.attn_k.weight | 0x1b179b720 | 0x440000 |
| 275 | blk.30.attn_norm.weight | 0x1b1bdb720 | 0x4000 |
| 276 | blk.30.attn_output.weight | 0x1b1bdf720 | 0x1100000 |
| 277 | blk.30.attn_q.weight | 0x1b2cdf720 | 0x1100000 |
| 278 | blk.30.attn_v.weight | 0x1b3ddf720 | 0x800000 |
| 279 | blk.30.ffn_down.weight | 0x1b45df720 | 0x3b80000 |
| 280 | blk.30.ffn_gate.weight | 0x1b815f720 | 0x3b80000 |
| 281 | blk.30.ffn_norm.weight | 0x1bbcdf720 | 0x4000 |
| 282 | blk.30.ffn_up.weight | 0x1bbce3720 | 0x3b80000 |
| 283 | blk.31.attn_k.weight | 0x1bf863720 | 0x348000 |
| 284 | blk.31.attn_norm.weight | 0x1bfbab720 | 0x4000 |
| 285 | blk.31.attn_output.weight | 0x1bfbaf720 | 0x1100000 |
| 286 | blk.31.attn_q.weight | 0x1c0caf720 | 0xd20000 |
| 287 | blk.31.attn_v.weight | 0x1c19cf720 | 0x440000 |
| 288 | blk.31.ffn_down.weight | 0x1c1e0f720 | 0x3b80000 |
| 289 | blk.31.ffn_gate.weight | 0x1c598f720 | 0x3b80000 |
| 290 | blk.31.ffn_norm.weight | 0x1c950f720 | 0x4000 |
| 291 | blk.31.ffn_up.weight | 0x1c9513720 | 0x3b80000 |
### <a name="base">Base Tensor Group : ~1B Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------|:---------------------------------|:------------------|:----------------------|:-----|
| 0 | output.weight | Output (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q8_0 |
| 1 | output_norm.weight | Output Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 2 | rope_freqs.weight | Rope_Freqs (W) | ( 64) 64 | 64 x 1 x 1 x 1 | F32 |
| 3 | token_embd.weight | Token Embedding (W) | (~525M) 525336576 | 4096 x 128256 x 1 x 1 | Q3_K |
- Total elements in base: ( ~1B) 1050677312
- Percentage of total elements: 13.08%
### <a name="blk_0">Block 0 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 4 | blk.0.attn_k.weight | Block 0 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 5 | blk.0.attn_norm.weight | Block 0 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 6 | blk.0.attn_output.weight | Block 0 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 7 | blk.0.attn_q.weight | Block 0 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 8 | blk.0.attn_v.weight | Block 0 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 9 | blk.0.ffn_down.weight | Block 0 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 10 | blk.0.ffn_gate.weight | Block 0 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 11 | blk.0.ffn_norm.weight | Block 0 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 12 | blk.0.ffn_up.weight | Block 0 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.0: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_1">Block 1 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 13 | blk.1.attn_k.weight | Block 1 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 14 | blk.1.attn_norm.weight | Block 1 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 15 | blk.1.attn_output.weight | Block 1 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 16 | blk.1.attn_q.weight | Block 1 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 17 | blk.1.attn_v.weight | Block 1 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 18 | blk.1.ffn_down.weight | Block 1 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 19 | blk.1.ffn_gate.weight | Block 1 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 20 | blk.1.ffn_norm.weight | Block 1 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 21 | blk.1.ffn_up.weight | Block 1 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.1: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_2">Block 2 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 22 | blk.2.attn_k.weight | Block 2 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 23 | blk.2.attn_norm.weight | Block 2 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 24 | blk.2.attn_output.weight | Block 2 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 25 | blk.2.attn_q.weight | Block 2 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 26 | blk.2.attn_v.weight | Block 2 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 27 | blk.2.ffn_down.weight | Block 2 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 28 | blk.2.ffn_gate.weight | Block 2 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 29 | blk.2.ffn_norm.weight | Block 2 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 30 | blk.2.ffn_up.weight | Block 2 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.2: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_3">Block 3 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 31 | blk.3.attn_k.weight | Block 3 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 32 | blk.3.attn_norm.weight | Block 3 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 33 | blk.3.attn_output.weight | Block 3 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 34 | blk.3.attn_q.weight | Block 3 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 35 | blk.3.attn_v.weight | Block 3 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 36 | blk.3.ffn_down.weight | Block 3 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 37 | blk.3.ffn_gate.weight | Block 3 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 38 | blk.3.ffn_norm.weight | Block 3 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 39 | blk.3.ffn_up.weight | Block 3 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.3: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_4">Block 4 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 40 | blk.4.attn_k.weight | Block 4 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 41 | blk.4.attn_norm.weight | Block 4 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 42 | blk.4.attn_output.weight | Block 4 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 43 | blk.4.attn_q.weight | Block 4 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 44 | blk.4.attn_v.weight | Block 4 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 45 | blk.4.ffn_down.weight | Block 4 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 46 | blk.4.ffn_gate.weight | Block 4 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 47 | blk.4.ffn_norm.weight | Block 4 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 48 | blk.4.ffn_up.weight | Block 4 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.4: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_5">Block 5 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 49 | blk.5.attn_k.weight | Block 5 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 50 | blk.5.attn_norm.weight | Block 5 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 51 | blk.5.attn_output.weight | Block 5 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 52 | blk.5.attn_q.weight | Block 5 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 53 | blk.5.attn_v.weight | Block 5 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 54 | blk.5.ffn_down.weight | Block 5 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 55 | blk.5.ffn_gate.weight | Block 5 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 56 | blk.5.ffn_norm.weight | Block 5 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 57 | blk.5.ffn_up.weight | Block 5 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.5: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_6">Block 6 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 58 | blk.6.attn_k.weight | Block 6 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 59 | blk.6.attn_norm.weight | Block 6 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 60 | blk.6.attn_output.weight | Block 6 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 61 | blk.6.attn_q.weight | Block 6 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 62 | blk.6.attn_v.weight | Block 6 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 63 | blk.6.ffn_down.weight | Block 6 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 64 | blk.6.ffn_gate.weight | Block 6 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 65 | blk.6.ffn_norm.weight | Block 6 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 66 | blk.6.ffn_up.weight | Block 6 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.6: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_7">Block 7 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 67 | blk.7.attn_k.weight | Block 7 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 68 | blk.7.attn_norm.weight | Block 7 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 69 | blk.7.attn_output.weight | Block 7 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 70 | blk.7.attn_q.weight | Block 7 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 71 | blk.7.attn_v.weight | Block 7 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 72 | blk.7.ffn_down.weight | Block 7 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 73 | blk.7.ffn_gate.weight | Block 7 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 74 | blk.7.ffn_norm.weight | Block 7 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 75 | blk.7.ffn_up.weight | Block 7 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.7: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_8">Block 8 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 76 | blk.8.attn_k.weight | Block 8 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 77 | blk.8.attn_norm.weight | Block 8 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 78 | blk.8.attn_output.weight | Block 8 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 79 | blk.8.attn_q.weight | Block 8 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 80 | blk.8.attn_v.weight | Block 8 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 81 | blk.8.ffn_down.weight | Block 8 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 82 | blk.8.ffn_gate.weight | Block 8 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 83 | blk.8.ffn_norm.weight | Block 8 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 84 | blk.8.ffn_up.weight | Block 8 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.8: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_9">Block 9 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:-------------------------|:-----------------------------------------------|:----------------|:----------------------|:-----|
| 85 | blk.9.attn_k.weight | Block 9 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 86 | blk.9.attn_norm.weight | Block 9 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 87 | blk.9.attn_output.weight | Block 9 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 88 | blk.9.attn_q.weight | Block 9 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 89 | blk.9.attn_v.weight | Block 9 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 90 | blk.9.ffn_down.weight | Block 9 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 91 | blk.9.ffn_gate.weight | Block 9 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 92 | blk.9.ffn_norm.weight | Block 9 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 93 | blk.9.ffn_up.weight | Block 9 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.9: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_10">Block 10 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 94 | blk.10.attn_k.weight | Block 10 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 95 | blk.10.attn_norm.weight | Block 10 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 96 | blk.10.attn_output.weight | Block 10 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 97 | blk.10.attn_q.weight | Block 10 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 98 | blk.10.attn_v.weight | Block 10 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 99 | blk.10.ffn_down.weight | Block 10 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 100 | blk.10.ffn_gate.weight | Block 10 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 101 | blk.10.ffn_norm.weight | Block 10 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 102 | blk.10.ffn_up.weight | Block 10 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.10: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_11">Block 11 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 103 | blk.11.attn_k.weight | Block 11 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 104 | blk.11.attn_norm.weight | Block 11 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 105 | blk.11.attn_output.weight | Block 11 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 106 | blk.11.attn_q.weight | Block 11 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 107 | blk.11.attn_v.weight | Block 11 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 108 | blk.11.ffn_down.weight | Block 11 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 109 | blk.11.ffn_gate.weight | Block 11 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 110 | blk.11.ffn_norm.weight | Block 11 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 111 | blk.11.ffn_up.weight | Block 11 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.11: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_12">Block 12 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 112 | blk.12.attn_k.weight | Block 12 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 113 | blk.12.attn_norm.weight | Block 12 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 114 | blk.12.attn_output.weight | Block 12 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 115 | blk.12.attn_q.weight | Block 12 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 116 | blk.12.attn_v.weight | Block 12 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 117 | blk.12.ffn_down.weight | Block 12 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 118 | blk.12.ffn_gate.weight | Block 12 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 119 | blk.12.ffn_norm.weight | Block 12 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 120 | blk.12.ffn_up.weight | Block 12 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.12: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_13">Block 13 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 121 | blk.13.attn_k.weight | Block 13 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 122 | blk.13.attn_norm.weight | Block 13 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 123 | blk.13.attn_output.weight | Block 13 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 124 | blk.13.attn_q.weight | Block 13 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 125 | blk.13.attn_v.weight | Block 13 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 126 | blk.13.ffn_down.weight | Block 13 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 127 | blk.13.ffn_gate.weight | Block 13 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 128 | blk.13.ffn_norm.weight | Block 13 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 129 | blk.13.ffn_up.weight | Block 13 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.13: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_14">Block 14 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 130 | blk.14.attn_k.weight | Block 14 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 131 | blk.14.attn_norm.weight | Block 14 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 132 | blk.14.attn_output.weight | Block 14 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 133 | blk.14.attn_q.weight | Block 14 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 134 | blk.14.attn_v.weight | Block 14 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 135 | blk.14.ffn_down.weight | Block 14 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 136 | blk.14.ffn_gate.weight | Block 14 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 137 | blk.14.ffn_norm.weight | Block 14 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 138 | blk.14.ffn_up.weight | Block 14 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.14: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_15">Block 15 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 139 | blk.15.attn_k.weight | Block 15 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 140 | blk.15.attn_norm.weight | Block 15 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 141 | blk.15.attn_output.weight | Block 15 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 142 | blk.15.attn_q.weight | Block 15 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 143 | blk.15.attn_v.weight | Block 15 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 144 | blk.15.ffn_down.weight | Block 15 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 145 | blk.15.ffn_gate.weight | Block 15 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
| 146 | blk.15.ffn_norm.weight | Block 15 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 147 | blk.15.ffn_up.weight | Block 15 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q6_K |
- Total elements in blk.15: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_16">Block 16 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 148 | blk.16.attn_k.weight | Block 16 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 149 | blk.16.attn_norm.weight | Block 16 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 150 | blk.16.attn_output.weight | Block 16 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 151 | blk.16.attn_q.weight | Block 16 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 152 | blk.16.attn_v.weight | Block 16 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 153 | blk.16.ffn_down.weight | Block 16 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 154 | blk.16.ffn_gate.weight | Block 16 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 155 | blk.16.ffn_norm.weight | Block 16 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 156 | blk.16.ffn_up.weight | Block 16 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.16: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_17">Block 17 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 157 | blk.17.attn_k.weight | Block 17 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 158 | blk.17.attn_norm.weight | Block 17 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 159 | blk.17.attn_output.weight | Block 17 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 160 | blk.17.attn_q.weight | Block 17 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 161 | blk.17.attn_v.weight | Block 17 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 162 | blk.17.ffn_down.weight | Block 17 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 163 | blk.17.ffn_gate.weight | Block 17 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 164 | blk.17.ffn_norm.weight | Block 17 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 165 | blk.17.ffn_up.weight | Block 17 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.17: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_18">Block 18 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 166 | blk.18.attn_k.weight | Block 18 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 167 | blk.18.attn_norm.weight | Block 18 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 168 | blk.18.attn_output.weight | Block 18 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 169 | blk.18.attn_q.weight | Block 18 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 170 | blk.18.attn_v.weight | Block 18 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 171 | blk.18.ffn_down.weight | Block 18 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 172 | blk.18.ffn_gate.weight | Block 18 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 173 | blk.18.ffn_norm.weight | Block 18 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 174 | blk.18.ffn_up.weight | Block 18 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.18: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_19">Block 19 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 175 | blk.19.attn_k.weight | Block 19 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 176 | blk.19.attn_norm.weight | Block 19 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 177 | blk.19.attn_output.weight | Block 19 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 178 | blk.19.attn_q.weight | Block 19 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 179 | blk.19.attn_v.weight | Block 19 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 180 | blk.19.ffn_down.weight | Block 19 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 181 | blk.19.ffn_gate.weight | Block 19 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 182 | blk.19.ffn_norm.weight | Block 19 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 183 | blk.19.ffn_up.weight | Block 19 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.19: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_20">Block 20 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 184 | blk.20.attn_k.weight | Block 20 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 185 | blk.20.attn_norm.weight | Block 20 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 186 | blk.20.attn_output.weight | Block 20 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 187 | blk.20.attn_q.weight | Block 20 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 188 | blk.20.attn_v.weight | Block 20 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 189 | blk.20.ffn_down.weight | Block 20 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 190 | blk.20.ffn_gate.weight | Block 20 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 191 | blk.20.ffn_norm.weight | Block 20 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 192 | blk.20.ffn_up.weight | Block 20 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.20: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_21">Block 21 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 193 | blk.21.attn_k.weight | Block 21 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 194 | blk.21.attn_norm.weight | Block 21 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 195 | blk.21.attn_output.weight | Block 21 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 196 | blk.21.attn_q.weight | Block 21 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 197 | blk.21.attn_v.weight | Block 21 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 198 | blk.21.ffn_down.weight | Block 21 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 199 | blk.21.ffn_gate.weight | Block 21 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 200 | blk.21.ffn_norm.weight | Block 21 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 201 | blk.21.ffn_up.weight | Block 21 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.21: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_22">Block 22 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 202 | blk.22.attn_k.weight | Block 22 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 203 | blk.22.attn_norm.weight | Block 22 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 204 | blk.22.attn_output.weight | Block 22 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 205 | blk.22.attn_q.weight | Block 22 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 206 | blk.22.attn_v.weight | Block 22 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 207 | blk.22.ffn_down.weight | Block 22 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 208 | blk.22.ffn_gate.weight | Block 22 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 209 | blk.22.ffn_norm.weight | Block 22 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 210 | blk.22.ffn_up.weight | Block 22 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.22: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_23">Block 23 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 211 | blk.23.attn_k.weight | Block 23 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 212 | blk.23.attn_norm.weight | Block 23 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 213 | blk.23.attn_output.weight | Block 23 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 214 | blk.23.attn_q.weight | Block 23 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 215 | blk.23.attn_v.weight | Block 23 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 216 | blk.23.ffn_down.weight | Block 23 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 217 | blk.23.ffn_gate.weight | Block 23 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 218 | blk.23.ffn_norm.weight | Block 23 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 219 | blk.23.ffn_up.weight | Block 23 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.23: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_24">Block 24 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 220 | blk.24.attn_k.weight | Block 24 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 221 | blk.24.attn_norm.weight | Block 24 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 222 | blk.24.attn_output.weight | Block 24 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 223 | blk.24.attn_q.weight | Block 24 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 224 | blk.24.attn_v.weight | Block 24 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 225 | blk.24.ffn_down.weight | Block 24 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 226 | blk.24.ffn_gate.weight | Block 24 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 227 | blk.24.ffn_norm.weight | Block 24 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 228 | blk.24.ffn_up.weight | Block 24 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.24: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_25">Block 25 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 229 | blk.25.attn_k.weight | Block 25 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 230 | blk.25.attn_norm.weight | Block 25 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 231 | blk.25.attn_output.weight | Block 25 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 232 | blk.25.attn_q.weight | Block 25 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 233 | blk.25.attn_v.weight | Block 25 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 234 | blk.25.ffn_down.weight | Block 25 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 235 | blk.25.ffn_gate.weight | Block 25 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 236 | blk.25.ffn_norm.weight | Block 25 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 237 | blk.25.ffn_up.weight | Block 25 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.25: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_26">Block 26 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 238 | blk.26.attn_k.weight | Block 26 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 239 | blk.26.attn_norm.weight | Block 26 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 240 | blk.26.attn_output.weight | Block 26 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 241 | blk.26.attn_q.weight | Block 26 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 242 | blk.26.attn_v.weight | Block 26 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 243 | blk.26.ffn_down.weight | Block 26 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 244 | blk.26.ffn_gate.weight | Block 26 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 245 | blk.26.ffn_norm.weight | Block 26 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 246 | blk.26.ffn_up.weight | Block 26 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.26: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_27">Block 27 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 247 | blk.27.attn_k.weight | Block 27 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 248 | blk.27.attn_norm.weight | Block 27 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 249 | blk.27.attn_output.weight | Block 27 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 250 | blk.27.attn_q.weight | Block 27 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 251 | blk.27.attn_v.weight | Block 27 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 252 | blk.27.ffn_down.weight | Block 27 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 253 | blk.27.ffn_gate.weight | Block 27 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 254 | blk.27.ffn_norm.weight | Block 27 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 255 | blk.27.ffn_up.weight | Block 27 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.27: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_28">Block 28 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 256 | blk.28.attn_k.weight | Block 28 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 257 | blk.28.attn_norm.weight | Block 28 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 258 | blk.28.attn_output.weight | Block 28 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 259 | blk.28.attn_q.weight | Block 28 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 260 | blk.28.attn_v.weight | Block 28 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 261 | blk.28.ffn_down.weight | Block 28 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 262 | blk.28.ffn_gate.weight | Block 28 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 263 | blk.28.ffn_norm.weight | Block 28 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 264 | blk.28.ffn_up.weight | Block 28 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.28: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_29">Block 29 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 265 | blk.29.attn_k.weight | Block 29 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 266 | blk.29.attn_norm.weight | Block 29 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 267 | blk.29.attn_output.weight | Block 29 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 268 | blk.29.attn_q.weight | Block 29 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 269 | blk.29.attn_v.weight | Block 29 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 270 | blk.29.ffn_down.weight | Block 29 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 271 | blk.29.ffn_gate.weight | Block 29 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 272 | blk.29.ffn_norm.weight | Block 29 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 273 | blk.29.ffn_up.weight | Block 29 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.29: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_30">Block 30 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 274 | blk.30.attn_k.weight | Block 30 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 275 | blk.30.attn_norm.weight | Block 30 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 276 | blk.30.attn_output.weight | Block 30 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 277 | blk.30.attn_q.weight | Block 30 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 278 | blk.30.attn_v.weight | Block 30 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | F16 |
| 279 | blk.30.ffn_down.weight | Block 30 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 280 | blk.30.ffn_gate.weight | Block 30 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 281 | blk.30.ffn_norm.weight | Block 30 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 282 | blk.30.ffn_up.weight | Block 30 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.30: (~218M) 218112000
- Percentage of total elements: 2.72%
### <a name="blk_31">Block 31 Tensor Group : ~218M Elements</a>
| T_ID | Tensor Layer Name | Human Friendly Tensor Layer Name | Elements | Shape | Type |
|-----:|:--------------------------|:------------------------------------------------|:----------------|:----------------------|:-----|
| 283 | blk.31.attn_k.weight | Block 31 Attention Key (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q6_K |
| 284 | blk.31.attn_norm.weight | Block 31 Attention Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 285 | blk.31.attn_output.weight | Block 31 Attention Output (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q8_0 |
| 286 | blk.31.attn_q.weight | Block 31 Attention Query (W) | (~17M) 16777216 | 4096 x 4096 x 1 x 1 | Q6_K |
| 287 | blk.31.attn_v.weight | Block 31 Attention Value (W) | ( ~4M) 4194304 | 4096 x 1024 x 1 x 1 | Q8_0 |
| 288 | blk.31.ffn_down.weight | Block 31 Feed-Forward Network "Down" (W) | (~59M) 58720256 | 14336 x 4096 x 1 x 1 | Q8_0 |
| 289 | blk.31.ffn_gate.weight | Block 31 Feed-Forward Network "Gate" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
| 290 | blk.31.ffn_norm.weight | Block 31 Feed-Forward Network Normalization (W) | ( ~4K) 4096 | 4096 x 1 x 1 x 1 | F32 |
| 291 | blk.31.ffn_up.weight | Block 31 Feed-Forward Network "Up" (W) | (~59M) 58720256 | 4096 x 14336 x 1 x 1 | Q8_0 |
- Total elements in blk.31: (~218M) 218112000
- Percentage of total elements: 2.72%

13
scores/Watt-Tool-8B-iq3_m.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_M.gguf (version GGUF V3 (latest))
Final result: 62.8000 +/- 1.7661
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 1734.01 ms
llama_perf_context_print: prompt eval time = 115043.84 ms / 36600 tokens ( 3.14 ms per token, 318.14 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 115943.71 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-iq3_m.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_M.gguf (version GGUF V3 (latest))
750 78.00000000% [74.8968%, 80.8179%]
llama_perf_context_print: load time = 291.01 ms
llama_perf_context_print: prompt eval time = 400031.71 ms / 126448 tokens ( 3.16 ms per token, 316.09 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 404305.75 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-iq3_m.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_M.gguf (version GGUF V3 (latest))
Final result: 37.7333 +/- 1.7711
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 289.89 ms
llama_perf_context_print: prompt eval time = 206632.46 ms / 67195 tokens ( 3.08 ms per token, 325.19 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 208049.33 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-iq3_m.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 7.841948 ± 0.049502
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 98.36%
Mean ln(PPL(Q)/PPL(base)) : 0.080268 ± 0.001143
Mean PPL(Q)/PPL(base) : 1.083578 ± 0.001238
Mean PPL(Q)-PPL(base) : 0.604858 ± 0.009476
====== KL divergence statistics ======
Mean KLD: 0.081774 ± 0.000354
Maximum KLD: 7.690053
99.9% KLD: 1.654508
99.0% KLD: 0.555790
99.0% KLD: 0.555790
Median KLD: 0.056256
10.0% KLD: 0.003426
5.0% KLD: 0.001063
1.0% KLD: 0.000157
Minimum KLD: 0.000000
====== Token probability statistics ======
Mean Δp: -2.133 ± 0.021 %
Maximum Δp: 73.495%
99.9% Δp: 32.336%
99.0% Δp: 17.093%
95.0% Δp: 7.846%
90.0% Δp: 4.045%
75.0% Δp: 0.372%
Median Δp: -0.301%
25.0% Δp: -3.967%
10.0% Δp: -10.805%
5.0% Δp: -16.007%
1.0% Δp: -30.015%
0.1% Δp: -62.256%
Minimum Δp: -96.763%
RMS Δp : 8.316 ± 0.043 %
Same top p: 85.224 ± 0.094 %

13
scores/Watt-Tool-8B-iq3_m.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_M.gguf (version GGUF V3 (latest))
Final result: 32.1333 +/- 1.7063
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 288.09 ms
llama_perf_context_print: prompt eval time = 161368.09 ms / 50072 tokens ( 3.22 ms per token, 310.30 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 163199.21 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-iq3_m.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_M.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 73.6000 +/- 1.6106
llama_perf_context_print: load time = 288.50 ms
llama_perf_context_print: prompt eval time = 70143.95 ms / 22192 tokens ( 3.16 ms per token, 316.38 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 70631.06 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-iq3_s.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_S.gguf (version GGUF V3 (latest))
Final result: 62.0000 +/- 1.7736
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 1662.56 ms
llama_perf_context_print: prompt eval time = 115280.42 ms / 36600 tokens ( 3.15 ms per token, 317.49 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 116185.54 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-iq3_s.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_S.gguf (version GGUF V3 (latest))
750 76.26666667% [73.0928%, 79.1728%]
llama_perf_context_print: load time = 286.42 ms
llama_perf_context_print: prompt eval time = 400735.90 ms / 126448 tokens ( 3.17 ms per token, 315.54 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 405023.75 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-iq3_s.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_S.gguf (version GGUF V3 (latest))
Final result: 37.3333 +/- 1.7674
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 293.04 ms
llama_perf_context_print: prompt eval time = 207055.09 ms / 67195 tokens ( 3.08 ms per token, 324.53 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 208462.26 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-iq3_s.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 8.253598 ± 0.051864
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 97.71%
Mean ln(PPL(Q)/PPL(base)) : 0.131430 ± 0.001346
Mean PPL(Q)/PPL(base) : 1.140458 ± 0.001535
Mean PPL(Q)-PPL(base) : 1.016508 ± 0.012175
====== KL divergence statistics ======
Mean KLD: 0.117565 ± 0.000433
Maximum KLD: 7.079286
99.9% KLD: 1.966468
99.0% KLD: 0.726076
99.0% KLD: 0.726076
Median KLD: 0.084699
10.0% KLD: 0.006988
5.0% KLD: 0.002383
1.0% KLD: 0.000330
Minimum KLD: -0.000001
====== Token probability statistics ======
Mean Δp: -3.685 ± 0.026 %
Maximum Δp: 69.513%
99.9% Δp: 34.570%
99.0% Δp: 17.585%
95.0% Δp: 7.273%
90.0% Δp: 3.369%
75.0% Δp: 0.113%
Median Δp: -0.833%
25.0% Δp: -6.212%
10.0% Δp: -15.079%
5.0% Δp: -21.666%
1.0% Δp: -38.754%
0.1% Δp: -69.188%
Minimum Δp: -97.122%
RMS Δp : 10.385 ± 0.045 %
Same top p: 82.770 ± 0.100 %

13
scores/Watt-Tool-8B-iq3_s.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_S.gguf (version GGUF V3 (latest))
Final result: 30.4000 +/- 1.6807
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 284.74 ms
llama_perf_context_print: prompt eval time = 161670.39 ms / 50072 tokens ( 3.23 ms per token, 309.72 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 163511.55 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-iq3_s.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ3_S.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 72.9333 +/- 1.6235
llama_perf_context_print: load time = 291.13 ms
llama_perf_context_print: prompt eval time = 70279.68 ms / 22192 tokens ( 3.17 ms per token, 315.77 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 70763.82 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-iq4_nl.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ4_NL.gguf (version GGUF V3 (latest))
Final result: 63.4667 +/- 1.7594
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 2048.98 ms
llama_perf_context_print: prompt eval time = 119074.35 ms / 36600 tokens ( 3.25 ms per token, 307.37 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 119972.06 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-iq4_nl.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ4_NL.gguf (version GGUF V3 (latest))
750 77.73333333% [74.6188%, 80.5653%]
llama_perf_context_print: load time = 297.65 ms
llama_perf_context_print: prompt eval time = 413170.51 ms / 126448 tokens ( 3.27 ms per token, 306.04 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 417435.80 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-iq4_nl.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ4_NL.gguf (version GGUF V3 (latest))
Final result: 39.6000 +/- 1.7870
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 304.48 ms
llama_perf_context_print: prompt eval time = 213794.40 ms / 67195 tokens ( 3.18 ms per token, 314.30 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 215197.82 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-iq4_nl.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 7.516430 ± 0.047275
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 99.30%
Mean ln(PPL(Q)/PPL(base)) : 0.037872 ± 0.000742
Mean PPL(Q)/PPL(base) : 1.038599 ± 0.000771
Mean PPL(Q)-PPL(base) : 0.279341 ± 0.005741
====== KL divergence statistics ======
Mean KLD: 0.034545 ± 0.000172
Maximum KLD: 4.479205
99.9% KLD: 0.809954
99.0% KLD: 0.243338
99.0% KLD: 0.243338
Median KLD: 0.022288
10.0% KLD: 0.001467
5.0% KLD: 0.000485
1.0% KLD: 0.000067
Minimum KLD: -0.000025
====== Token probability statistics ======
Mean Δp: -0.984 ± 0.014 %
Maximum Δp: 60.862%
99.9% Δp: 23.910%
99.0% Δp: 11.795%
95.0% Δp: 5.549%
90.0% Δp: 3.027%
75.0% Δp: 0.404%
Median Δp: -0.103%
25.0% Δp: -2.015%
10.0% Δp: -6.046%
5.0% Δp: -9.267%
1.0% Δp: -18.431%
0.1% Δp: -42.825%
Minimum Δp: -93.056%
RMS Δp : 5.270 ± 0.035 %
Same top p: 90.812 ± 0.076 %

13
scores/Watt-Tool-8B-iq4_nl.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ4_NL.gguf (version GGUF V3 (latest))
Final result: 31.4667 +/- 1.6968
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 311.22 ms
llama_perf_context_print: prompt eval time = 166835.67 ms / 50072 tokens ( 3.33 ms per token, 300.13 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 168685.42 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-iq4_nl.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-IQ4_NL.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 75.4667 +/- 1.5722
llama_perf_context_print: load time = 302.51 ms
llama_perf_context_print: prompt eval time = 72558.29 ms / 22192 tokens ( 3.27 ms per token, 305.85 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 73039.49 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q3_k_l.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_L.gguf (version GGUF V3 (latest))
Final result: 61.7333 +/- 1.7759
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 1803.05 ms
llama_perf_context_print: prompt eval time = 123314.10 ms / 36600 tokens ( 3.37 ms per token, 296.80 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 124217.22 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q3_k_l.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_L.gguf (version GGUF V3 (latest))
750 77.20000000% [74.0633%, 80.0595%]
llama_perf_context_print: load time = 293.80 ms
llama_perf_context_print: prompt eval time = 428872.85 ms / 126448 tokens ( 3.39 ms per token, 294.84 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 433161.99 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q3_k_l.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_L.gguf (version GGUF V3 (latest))
Final result: 38.5333 +/- 1.7783
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 293.76 ms
llama_perf_context_print: prompt eval time = 221450.17 ms / 67195 tokens ( 3.30 ms per token, 303.43 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 222861.86 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q3_k_l.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 8.274172 ± 0.052402
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 97.60%
Mean ln(PPL(Q)/PPL(base)) : 0.133920 ± 0.001382
Mean PPL(Q)/PPL(base) : 1.143301 ± 0.001580
Mean PPL(Q)-PPL(base) : 1.037082 ± 0.012706
====== KL divergence statistics ======
Mean KLD: 0.114738 ± 0.000483
Maximum KLD: 9.999102
99.9% KLD: 2.236693
99.0% KLD: 0.781076
99.0% KLD: 0.781076
Median KLD: 0.077728
10.0% KLD: 0.005170
5.0% KLD: 0.001727
1.0% KLD: 0.000289
Minimum KLD: -0.000055
====== Token probability statistics ======
Mean Δp: -3.288 ± 0.025 %
Maximum Δp: 65.548%
99.9% Δp: 32.662%
99.0% Δp: 17.193%
95.0% Δp: 7.509%
90.0% Δp: 3.610%
75.0% Δp: 0.176%
Median Δp: -0.636%
25.0% Δp: -5.421%
10.0% Δp: -13.956%
5.0% Δp: -20.435%
1.0% Δp: -38.546%
0.1% Δp: -71.826%
Minimum Δp: -98.746%
RMS Δp : 10.050 ± 0.048 %
Same top p: 83.354 ± 0.098 %

13
scores/Watt-Tool-8B-q3_k_l.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_L.gguf (version GGUF V3 (latest))
Final result: 32.4000 +/- 1.7100
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 303.59 ms
llama_perf_context_print: prompt eval time = 173066.86 ms / 50072 tokens ( 3.46 ms per token, 289.32 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 174906.65 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q3_k_l.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_L.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 71.8667 +/- 1.6430
llama_perf_context_print: load time = 282.54 ms
llama_perf_context_print: prompt eval time = 75214.17 ms / 22192 tokens ( 3.39 ms per token, 295.05 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 75700.49 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q3_k_m.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_M.gguf (version GGUF V3 (latest))
Final result: 61.0667 +/- 1.7816
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 1677.48 ms
llama_perf_context_print: prompt eval time = 120638.17 ms / 36600 tokens ( 3.30 ms per token, 303.39 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 121534.75 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q3_k_m.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_M.gguf (version GGUF V3 (latest))
750 77.20000000% [74.0633%, 80.0595%]
llama_perf_context_print: load time = 283.76 ms
llama_perf_context_print: prompt eval time = 419917.27 ms / 126448 tokens ( 3.32 ms per token, 301.13 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 424216.79 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q3_k_m.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_M.gguf (version GGUF V3 (latest))
Final result: 38.5333 +/- 1.7783
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 285.00 ms
llama_perf_context_print: prompt eval time = 216659.18 ms / 67195 tokens ( 3.22 ms per token, 310.14 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 218063.84 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q3_k_m.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 8.459379 ± 0.053550
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 97.26%
Mean ln(PPL(Q)/PPL(base)) : 0.156057 ± 0.001477
Mean PPL(Q)/PPL(base) : 1.168892 ± 0.001727
Mean PPL(Q)-PPL(base) : 1.222289 ± 0.014061
====== KL divergence statistics ======
Mean KLD: 0.131196 ± 0.000539
Maximum KLD: 7.898368
99.9% KLD: 2.475934
99.0% KLD: 0.894390
99.0% KLD: 0.894390
Median KLD: 0.089346
10.0% KLD: 0.006670
5.0% KLD: 0.002250
1.0% KLD: 0.000392
Minimum KLD: 0.000001
====== Token probability statistics ======
Mean Δp: -3.913 ± 0.027 %
Maximum Δp: 64.023%
99.9% Δp: 33.075%
99.0% Δp: 17.214%
95.0% Δp: 7.245%
90.0% Δp: 3.301%
75.0% Δp: 0.096%
Median Δp: -0.875%
25.0% Δp: -6.342%
10.0% Δp: -15.578%
5.0% Δp: -22.649%
1.0% Δp: -41.943%
0.1% Δp: -75.852%
Minimum Δp: -98.926%
RMS Δp : 10.892 ± 0.050 %
Same top p: 82.438 ± 0.100 %

13
scores/Watt-Tool-8B-q3_k_m.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_M.gguf (version GGUF V3 (latest))
Final result: 33.3333 +/- 1.7225
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 294.56 ms
llama_perf_context_print: prompt eval time = 169427.06 ms / 50072 tokens ( 3.38 ms per token, 295.54 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 171263.15 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q3_k_m.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_M.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 73.0667 +/- 1.6209
llama_perf_context_print: load time = 286.93 ms
llama_perf_context_print: prompt eval time = 73604.03 ms / 22192 tokens ( 3.32 ms per token, 301.51 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 74091.88 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q3_k_s.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_S.gguf (version GGUF V3 (latest))
Final result: 58.2667 +/- 1.8018
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 1653.99 ms
llama_perf_context_print: prompt eval time = 123080.79 ms / 36600 tokens ( 3.36 ms per token, 297.37 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 123982.14 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q3_k_s.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_S.gguf (version GGUF V3 (latest))
750 75.60000000% [72.4008%, 78.5383%]
llama_perf_context_print: load time = 285.75 ms
llama_perf_context_print: prompt eval time = 427986.37 ms / 126448 tokens ( 3.38 ms per token, 295.45 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 432278.94 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q3_k_s.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_S.gguf (version GGUF V3 (latest))
Final result: 38.1333 +/- 1.7748
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 283.79 ms
llama_perf_context_print: prompt eval time = 221006.99 ms / 67195 tokens ( 3.29 ms per token, 304.04 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 222418.23 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q3_k_s.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 8.869361 ± 0.056188
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 96.40%
Mean ln(PPL(Q)/PPL(base)) : 0.203384 ± 0.001694
Mean PPL(Q)/PPL(base) : 1.225543 ± 0.002076
Mean PPL(Q)-PPL(base) : 1.632272 ± 0.017247
====== KL divergence statistics ======
Mean KLD: 0.171689 ± 0.000675
Maximum KLD: 8.647476
99.9% KLD: 3.093943
99.0% KLD: 1.167801
99.0% KLD: 1.167801
Median KLD: 0.116922
10.0% KLD: 0.009604
5.0% KLD: 0.003321
1.0% KLD: 0.000607
Minimum KLD: 0.000004
====== Token probability statistics ======
Mean Δp: -5.020 ± 0.030 %
Maximum Δp: 68.248%
99.9% Δp: 34.217%
99.0% Δp: 17.833%
95.0% Δp: 7.053%
90.0% Δp: 2.939%
75.0% Δp: 0.031%
Median Δp: -1.308%
25.0% Δp: -7.961%
10.0% Δp: -18.717%
5.0% Δp: -26.619%
1.0% Δp: -49.119%
0.1% Δp: -82.457%
Minimum Δp: -99.092%
RMS Δp : 12.587 ± 0.055 %
Same top p: 80.614 ± 0.104 %

13
scores/Watt-Tool-8B-q3_k_s.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_S.gguf (version GGUF V3 (latest))
Final result: 33.2000 +/- 1.7207
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 290.87 ms
llama_perf_context_print: prompt eval time = 172697.11 ms / 50072 tokens ( 3.45 ms per token, 289.94 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 174519.26 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q3_k_s.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q3_K_S.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 73.6000 +/- 1.6106
llama_perf_context_print: load time = 290.68 ms
llama_perf_context_print: prompt eval time = 75062.12 ms / 22192 tokens ( 3.38 ms per token, 295.65 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 75536.06 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q4_k_m.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_M.gguf (version GGUF V3 (latest))
Final result: 65.7333 +/- 1.7342
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 2082.07 ms
llama_perf_context_print: prompt eval time = 124311.12 ms / 36600 tokens ( 3.40 ms per token, 294.42 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 125214.84 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q4_k_m.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_M.gguf (version GGUF V3 (latest))
750 77.73333333% [74.6188%, 80.5653%]
llama_perf_context_print: load time = 309.44 ms
llama_perf_context_print: prompt eval time = 431270.97 ms / 126448 tokens ( 3.41 ms per token, 293.20 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 435567.98 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q4_k_m.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_M.gguf (version GGUF V3 (latest))
Final result: 39.4667 +/- 1.7860
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 297.51 ms
llama_perf_context_print: prompt eval time = 223210.15 ms / 67195 tokens ( 3.32 ms per token, 301.04 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 224621.22 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q4_k_m.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 7.553687 ± 0.047468
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 99.32%
Mean ln(PPL(Q)/PPL(base)) : 0.042817 ± 0.000732
Mean PPL(Q)/PPL(base) : 1.043747 ± 0.000764
Mean PPL(Q)-PPL(base) : 0.316598 ± 0.005745
====== KL divergence statistics ======
Mean KLD: 0.033370 ± 0.000164
Maximum KLD: 4.041112
99.9% KLD: 0.772030
99.0% KLD: 0.234367
99.0% KLD: 0.234367
Median KLD: 0.021457
10.0% KLD: 0.001426
5.0% KLD: 0.000473
1.0% KLD: 0.000068
Minimum KLD: -0.000210
====== Token probability statistics ======
Mean Δp: -1.218 ± 0.013 %
Maximum Δp: 57.472%
99.9% Δp: 21.825%
99.0% Δp: 10.690%
95.0% Δp: 4.844%
90.0% Δp: 2.564%
75.0% Δp: 0.260%
Median Δp: -0.171%
25.0% Δp: -2.265%
10.0% Δp: -6.360%
5.0% Δp: -9.509%
1.0% Δp: -18.642%
0.1% Δp: -41.385%
Minimum Δp: -86.813%
RMS Δp : 5.188 ± 0.033 %
Same top p: 91.003 ± 0.075 %

13
scores/Watt-Tool-8B-q4_k_m.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_M.gguf (version GGUF V3 (latest))
Final result: 30.9333 +/- 1.6889
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 345.88 ms
llama_perf_context_print: prompt eval time = 174128.81 ms / 50072 tokens ( 3.48 ms per token, 287.56 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 175962.73 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q4_k_m.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_M.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 74.0000 +/- 1.6027
llama_perf_context_print: load time = 297.22 ms
llama_perf_context_print: prompt eval time = 75766.44 ms / 22192 tokens ( 3.41 ms per token, 292.90 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 76251.82 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q4_k_s.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_S.gguf (version GGUF V3 (latest))
Final result: 65.8667 +/- 1.7325
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 1990.78 ms
llama_perf_context_print: prompt eval time = 122336.24 ms / 36600 tokens ( 3.34 ms per token, 299.18 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 123231.47 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q4_k_s.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_S.gguf (version GGUF V3 (latest))
750 78.00000000% [74.8968%, 80.8179%]
llama_perf_context_print: load time = 302.60 ms
llama_perf_context_print: prompt eval time = 424697.12 ms / 126448 tokens ( 3.36 ms per token, 297.74 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 429004.86 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q4_k_s.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_S.gguf (version GGUF V3 (latest))
Final result: 39.4667 +/- 1.7860
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 301.52 ms
llama_perf_context_print: prompt eval time = 219698.58 ms / 67195 tokens ( 3.27 ms per token, 305.85 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 221106.96 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q4_k_s.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 7.570386 ± 0.047455
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 99.27%
Mean ln(PPL(Q)/PPL(base)) : 0.045025 ± 0.000759
Mean PPL(Q)/PPL(base) : 1.046054 ± 0.000794
Mean PPL(Q)-PPL(base) : 0.333296 ± 0.005934
====== KL divergence statistics ======
Mean KLD: 0.036155 ± 0.000172
Maximum KLD: 3.950742
99.9% KLD: 0.799789
99.0% KLD: 0.253352
99.0% KLD: 0.253352
Median KLD: 0.023291
10.0% KLD: 0.001614
5.0% KLD: 0.000535
1.0% KLD: 0.000079
Minimum KLD: -0.000198
====== Token probability statistics ======
Mean Δp: -1.387 ± 0.014 %
Maximum Δp: 59.331%
99.9% Δp: 22.210%
99.0% Δp: 10.808%
95.0% Δp: 4.768%
90.0% Δp: 2.461%
75.0% Δp: 0.216%
Median Δp: -0.219%
25.0% Δp: -2.513%
10.0% Δp: -6.790%
5.0% Δp: -10.102%
1.0% Δp: -19.543%
0.1% Δp: -42.826%
Minimum Δp: -87.885%
RMS Δp : 5.421 ± 0.034 %
Same top p: 90.686 ± 0.077 %

13
scores/Watt-Tool-8B-q4_k_s.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_S.gguf (version GGUF V3 (latest))
Final result: 30.5333 +/- 1.6828
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 298.94 ms
llama_perf_context_print: prompt eval time = 171448.09 ms / 50072 tokens ( 3.42 ms per token, 292.05 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 173294.83 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q4_k_s.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_S.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 73.2000 +/- 1.6184
llama_perf_context_print: load time = 298.89 ms
llama_perf_context_print: prompt eval time = 74567.46 ms / 22192 tokens ( 3.36 ms per token, 297.61 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 75053.76 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q5_k_m.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_M.gguf (version GGUF V3 (latest))
Final result: 65.7333 +/- 1.7342
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 2467.31 ms
llama_perf_context_print: prompt eval time = 123882.16 ms / 36600 tokens ( 3.38 ms per token, 295.44 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 124783.95 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q5_k_m.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_M.gguf (version GGUF V3 (latest))
750 78.66666667% [75.5926%, 81.4486%]
llama_perf_context_print: load time = 328.50 ms
llama_perf_context_print: prompt eval time = 430862.60 ms / 126448 tokens ( 3.41 ms per token, 293.48 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 435145.62 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q5_k_m.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_M.gguf (version GGUF V3 (latest))
Final result: 40.9333 +/- 1.7967
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 322.35 ms
llama_perf_context_print: prompt eval time = 222308.09 ms / 67195 tokens ( 3.31 ms per token, 302.26 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 223709.27 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q5_k_m.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 7.337057 ± 0.046220
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 99.81%
Mean ln(PPL(Q)/PPL(base)) : 0.013719 ± 0.000386
Mean PPL(Q)/PPL(base) : 1.013813 ± 0.000391
Mean PPL(Q)-PPL(base) : 0.099967 ± 0.002893
====== KL divergence statistics ======
Mean KLD: 0.009155 ± 0.000052
Maximum KLD: 2.029761
99.9% KLD: 0.235197
99.0% KLD: 0.070048
99.0% KLD: 0.070048
Median KLD: 0.005494
10.0% KLD: 0.000351
5.0% KLD: 0.000113
1.0% KLD: 0.000014
Minimum KLD: -0.000066
====== Token probability statistics ======
Mean Δp: -0.318 ± 0.007 %
Maximum Δp: 56.530%
99.9% Δp: 14.003%
99.0% Δp: 6.553%
95.0% Δp: 3.083%
90.0% Δp: 1.762%
75.0% Δp: 0.311%
Median Δp: -0.019%
25.0% Δp: -0.801%
10.0% Δp: -2.703%
5.0% Δp: -4.299%
1.0% Δp: -8.935%
0.1% Δp: -20.874%
Minimum Δp: -84.208%
RMS Δp : 2.680 ± 0.024 %
Same top p: 95.302 ± 0.056 %

13
scores/Watt-Tool-8B-q5_k_m.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_M.gguf (version GGUF V3 (latest))
Final result: 33.7333 +/- 1.7276
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 326.22 ms
llama_perf_context_print: prompt eval time = 173932.63 ms / 50072 tokens ( 3.47 ms per token, 287.88 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 175766.98 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q5_k_m.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_M.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 75.0667 +/- 1.5808
llama_perf_context_print: load time = 321.29 ms
llama_perf_context_print: prompt eval time = 75568.44 ms / 22192 tokens ( 3.41 ms per token, 293.67 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 76053.93 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q5_k_s.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_S.gguf (version GGUF V3 (latest))
Final result: 65.7333 +/- 1.7342
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 2387.53 ms
llama_perf_context_print: prompt eval time = 125483.18 ms / 36600 tokens ( 3.43 ms per token, 291.67 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 126384.32 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q5_k_s.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_S.gguf (version GGUF V3 (latest))
750 78.66666667% [75.5926%, 81.4486%]
llama_perf_context_print: load time = 315.67 ms
llama_perf_context_print: prompt eval time = 436378.26 ms / 126448 tokens ( 3.45 ms per token, 289.77 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 440675.86 ms / 126449 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q5_k_s.mmlu Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_S.gguf (version GGUF V3 (latest))
Final result: 41.6000 +/- 1.8010
Random chance: 25.0000 +/- 1.5822
llama_perf_context_print: load time = 313.17 ms
llama_perf_context_print: prompt eval time = 225223.26 ms / 67195 tokens ( 3.35 ms per token, 298.35 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 226635.79 ms / 67196 tokens
ggml_metal_free: deallocating

37
scores/Watt-Tool-8B-q5_k_s.ppx Normal file
View File

@@ -0,0 +1,37 @@
====== Perplexity statistics ======
Mean PPL(Q) : 7.347298 ± 0.046298
Mean PPL(base) : 7.237090 ± 0.045539
Cor(ln(PPL(Q)), ln(PPL(base))): 99.80%
Mean ln(PPL(Q)/PPL(base)) : 0.015114 ± 0.000397
Mean PPL(Q)/PPL(base) : 1.015228 ± 0.000403
Mean PPL(Q)-PPL(base) : 0.110209 ± 0.002994
====== KL divergence statistics ======
Mean KLD: 0.009763 ± 0.000056
Maximum KLD: 1.979661
99.9% KLD: 0.248941
99.0% KLD: 0.074428
99.0% KLD: 0.074428
Median KLD: 0.005853
10.0% KLD: 0.000390
5.0% KLD: 0.000129
1.0% KLD: 0.000017
Minimum KLD: -0.000066
====== Token probability statistics ======
Mean Δp: -0.342 ± 0.007 %
Maximum Δp: 55.623%
99.9% Δp: 13.960%
99.0% Δp: 6.651%
95.0% Δp: 3.167%
90.0% Δp: 1.790%
75.0% Δp: 0.310%
Median Δp: -0.024%
25.0% Δp: -0.832%
10.0% Δp: -2.797%
5.0% Δp: -4.458%
1.0% Δp: -9.272%
0.1% Δp: -21.545%
Minimum Δp: -83.712%
RMS Δp : 2.763 ± 0.024 %
Same top p: 95.200 ± 0.056 %

13
scores/Watt-Tool-8B-q5_k_s.tqa Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_S.gguf (version GGUF V3 (latest))
Final result: 33.6000 +/- 1.7259
Random chance: 19.8992 +/- 1.4588
llama_perf_context_print: load time = 314.16 ms
llama_perf_context_print: prompt eval time = 176127.32 ms / 50072 tokens ( 3.52 ms per token, 284.29 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 177964.05 ms / 50073 tokens
ggml_metal_free: deallocating

11
scores/Watt-Tool-8B-q5_k_s.wng Normal file
View File

@@ -0,0 +1,11 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q5_K_S.gguf (version GGUF V3 (latest))
Final Winogrande score(750 tasks): 74.5333 +/- 1.5919
llama_perf_context_print: load time = 316.82 ms
llama_perf_context_print: prompt eval time = 76522.16 ms / 22192 tokens ( 3.45 ms per token, 290.01 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 77002.38 ms / 22193 tokens
ggml_metal_free: deallocating

13
scores/Watt-Tool-8B-q6_k.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q6_K.gguf (version GGUF V3 (latest))
Final result: 66.1333 +/- 1.7292
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 2966.80 ms
llama_perf_context_print: prompt eval time = 121882.40 ms / 36600 tokens ( 3.33 ms per token, 300.29 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 122783.42 ms / 36601 tokens
ggml_metal_free: deallocating

12
scores/Watt-Tool-8B-q6_k.hsw Normal file
View File

@@ -0,0 +1,12 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q6_K.gguf (version GGUF V3 (latest))
750 79.33333333% [76.2895%, 82.0782%]
llama_perf_context_print: load time = 345.57 ms
llama_perf_context_print: prompt eval time = 423180.15 ms / 126448 tokens ( 3.35 ms per token, 298.80 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 427478.09 ms / 126449 tokens
ggml_metal_free: deallocating

Some files were not shown because too many files have changed in this diff Show More