初始化项目，由ModelHub XC社区提供模型
Model: TorpedoSoftware/R1-Distill-Qwen-14B-Roblox-Luau Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
*.gguf 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
|
||||
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
|
||||
173
.gitignore
vendored
Normal file
173
.gitignore
vendored
Normal file
@@ -0,0 +1,173 @@
|
||||
cache/
|
||||
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
cover/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
.pybuilder/
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# UV
|
||||
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
#uv.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
#pdm.lock
|
||||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||||
# in version control.
|
||||
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
||||
.pdm.toml
|
||||
.pdm-python
|
||||
.pdm-build/
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# pytype static type analyzer
|
||||
.pytype/
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
|
||||
# PyPI configuration file
|
||||
.pypirc
|
||||
43
README.md
Normal file
43
README.md
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
license: mit
|
||||
license_link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
base_model_relation: finetune
|
||||
finetuned_by: boatbomber
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- chat
|
||||
- reasoning
|
||||
- roblox
|
||||
- luau
|
||||
language:
|
||||
- en
|
||||
datasets:
|
||||
- boatbomber/roblox-info-dump
|
||||
- boatbomber/the-luau-stack
|
||||
---
|
||||
|
||||
# R1-Distill-Qwen-14B-Roblox-Luau
|
||||
|
||||
A fine tune of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) using [boatbomber/roblox-info-dump](https://huggingface.co/datasets/boatbomber/roblox-info-dump) and [boatbomber/the-luau-stack](https://huggingface.co/datasets/boatbomber/the-luau-stack) for Roblox domain knowledge.
|
||||
|
||||
Recommended inference settings:
|
||||
|
||||
| Parameter | Value | Notes |
|
||||
| --------- | ----- | ----- |
|
||||
| System Prompt | `You are an expert Roblox developer and Luau software engineer.` | Model was fine tuned with this prompt. |
|
||||
| temperature | `0.5-0.7` | Underlying R1 Distill uses this. I've found best results with `0.55`. |
|
||||
| top_p | `0.95` | Underlying R1 Distill uses this. |
|
||||
|
||||
Quantization done using [Unsloth](https://docs.unsloth.ai/).
|
||||
|
||||
Available quants:
|
||||
|
||||
| Quant | Size | Notes |
|
||||
| ----- | ---- | ----- |
|
||||
| F16 | 29.55GB | Retains 100% accuracy. Slow and memory hungry. |
|
||||
| Q8_O | 15.70GB | High resource use, but generally acceptable. Use when accuracy is crucial. |
|
||||
| Q6_K | 12.12GB | Uses Q6_K for all tensors. Good for high end GPUs. |
|
||||
| Q5_K_M | 10.51GB | **Recommended.** Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K |
|
||||
| Q4_K_M | 8.99GB | **Recommended.** Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K |
|
||||
| Q3_K_M | 7.34GB | Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K. Quality is noticeably degraded. |
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 48,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.2",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151646,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.2"
|
||||
}
|
||||
3
model-00001-of-00012.safetensors
Normal file
3
model-00001-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c357ce1cd359dd683499d04df4d7c9a5d228ef4d4877e1bfa9f8b4d79e1a123b
|
||||
size 4750149992
|
||||
3
model-00002-of-00012.safetensors
Normal file
3
model-00002-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1266d3c17664380e4601736454246605b8011054b8a7c0618006dc7a588cfc45
|
||||
size 4970575640
|
||||
3
model-00003-of-00012.safetensors
Normal file
3
model-00003-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ef7e40604dd2fd75a91c2a17f023203bdd8da7df7a1d00b65d5bd24ed35da4ee
|
||||
size 4939106528
|
||||
3
model-00004-of-00012.safetensors
Normal file
3
model-00004-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:51a24085f3ce210335a3005d2602e4549835e9fe1f2a4f2a80c482c07f57926b
|
||||
size 4970575688
|
||||
3
model-00005-of-00012.safetensors
Normal file
3
model-00005-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a7e82230f781366f44669d61106ff4b8a32afabb478e7ce724510777fdaaf3aa
|
||||
size 4939106568
|
||||
3
model-00006-of-00012.safetensors
Normal file
3
model-00006-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a268e287ee76f3b7f4d7100886d70342598ab7c54a88a892dd0009724d8e028
|
||||
size 4970575688
|
||||
3
model-00007-of-00012.safetensors
Normal file
3
model-00007-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:499fb453b5329814c74736b5cb25161be5b06a8f486bdb110f2abded3c91f64a
|
||||
size 4939106568
|
||||
3
model-00008-of-00012.safetensors
Normal file
3
model-00008-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:01327f2869b00013598ac87b6fca356d330d328742a9e7a5bd80ae9c238bca6b
|
||||
size 4970575688
|
||||
3
model-00009-of-00012.safetensors
Normal file
3
model-00009-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:790e1108dfaab921403bdf687e516b9d3886287ecbf9573d72127f2d9d56959b
|
||||
size 4939106568
|
||||
3
model-00010-of-00012.safetensors
Normal file
3
model-00010-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa6322ea1376a3b011b7292c6663b3332b88c9e29b7d22a0bf28b5893d3ce409
|
||||
size 4970575688
|
||||
3
model-00011-of-00012.safetensors
Normal file
3
model-00011-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed7f595063c7e58369666e7e457a0a7a911977bec33d3ef28d65a6acfbb2b0ef
|
||||
size 4939106568
|
||||
3
model-00012-of-00012.safetensors
Normal file
3
model-00012-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bca10d4dff0f817819d525dafe6cc0d08fde71cc85f257829d2febcaecb0064f
|
||||
size 4781639680
|
||||
586
model.safetensors.index.json
Normal file
586
model.safetensors.index.json
Normal file
@@ -0,0 +1,586 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 59080134656
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00012-of-00012.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00012-of-00012.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||
"model.norm.weight": "model-00012-of-00012.safetensors"
|
||||
}
|
||||
}
|
||||
2576
poetry.lock
generated
Normal file
2576
poetry.lock
generated
Normal file
File diff suppressed because it is too large
Load Diff
15
pyproject.toml
Normal file
15
pyproject.toml
Normal file
@@ -0,0 +1,15 @@
|
||||
[project]
|
||||
name = "R1-Distill-Qwen-14B-Roblox-Luau"
|
||||
version = "1.0.0"
|
||||
description = ""
|
||||
authors = [{ name = "boatbomber", email = "zack@boatbomber.com" }]
|
||||
readme = "README.md"
|
||||
requires-python = "3.11.*"
|
||||
dependencies = ["ipywidgets (>=8.1.5,<9.0.0)", "ipykernel (>=6.29.5,<7.0.0)", "together (>=1.5.2,<2.0.0)", "python-dotenv (>=1.1.0,<2.0.0)", "datasets (>=3.4.1,<4.0.0)"]
|
||||
|
||||
[tool.poetry]
|
||||
package-mode = false
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core>=2.0.0,<3.0.0"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
285
run-finetune.ipynb
Normal file
285
run-finetune.ipynb
Normal file
@@ -0,0 +1,285 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import time\n",
|
||||
"import pandas as pd\n",
|
||||
"from datasets import load_dataset, DatasetDict\n",
|
||||
"from together import Together\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"\n",
|
||||
"load_dotenv()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"client = Together(api_key=os.getenv(\"TOGETHER_API_KEY\"))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"BASE_MODEL_ID = \"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B\"\n",
|
||||
"DATASET_ID = \"boatbomber/Roblox-Luau-Reasoning-v1.0\"\n",
|
||||
"SYSTEM_PROMPT = \"You are an expert Roblox developer and Luau software engineer.\"\n",
|
||||
"COMPLETION_TEMPLATE = \"\"\"\\\n",
|
||||
"<think>\n",
|
||||
"{chain_of_thought}\n",
|
||||
"</think>\n",
|
||||
"\n",
|
||||
"```Lua\n",
|
||||
"{code}\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"{explanation}\\\n",
|
||||
"\"\"\"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Build the fine tuning dataset"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "c2561cd4a02f48b6ac71f6e8053e124a",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"train.parquet: 0%| | 0.00/47.3M [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "cef42da3a8644e0bb6561c693e443c75",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"test.parquet: 0%| | 0.00/9.77M [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "c7790de3d6244a2e9baa82c772457099",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Generating train split: 0%| | 0/15341 [00:00<?, ? examples/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "250cc9faca1f40cf83c78cd7d34b872b",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Generating test split: 0%| | 0/3254 [00:00<?, ? examples/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Uploading file luau-reasoning.jsonl: 100%|██████████| 132M/132M [00:11<00:00, 11.5MB/s] \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"DATASET_FILE_ID file-790ced3f-fbb4-46f4-87d7-cb5bf33b1623\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"DATASET_FILE_ID = \"file-790ced3f-fbb4-46f4-87d7-cb5bf33b1623\"\n",
|
||||
"if not DATASET_FILE_ID:\n",
|
||||
" dataset_splits: DatasetDict = load_dataset(DATASET_ID)\n",
|
||||
" combined_df = pd.DataFrame(columns=[\"messages\"])\n",
|
||||
" for split, dataset in dataset_splits.items():\n",
|
||||
" df: pd.DataFrame = dataset.to_pandas()\n",
|
||||
" df[\"messages\"] = df.apply(\n",
|
||||
" lambda row: [\n",
|
||||
" {\n",
|
||||
" \"role\": \"system\",\n",
|
||||
" \"content\": SYSTEM_PROMPT,\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": row[\"prompt\"],\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"role\": \"assistant\",\n",
|
||||
" \"content\": COMPLETION_TEMPLATE.format(\n",
|
||||
" chain_of_thought=row[\"chain_of_thought\"],\n",
|
||||
" code=row[\"code\"],\n",
|
||||
" explanation=row[\"explanation\"],\n",
|
||||
" ),\n",
|
||||
" },\n",
|
||||
" ],\n",
|
||||
" axis=1,\n",
|
||||
" )\n",
|
||||
" df = df[[\"messages\"]]\n",
|
||||
"\n",
|
||||
" # Add prompt, completion from each row to the combined_df\n",
|
||||
" combined_df = pd.concat([combined_df, df], ignore_index=True)\n",
|
||||
"\n",
|
||||
" combined_df.to_json(\"cache/luau-reasoning.jsonl\", orient=\"records\", lines=True)\n",
|
||||
" file_resp = client.files.upload(file=\"cache/luau-reasoning.jsonl\", check=True)\n",
|
||||
"\n",
|
||||
" print(\"DATASET_FILE_ID\", file_resp.id)\n",
|
||||
" DATASET_FILE_ID = file_resp.id\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Trigger fine-tuning job"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"message='Starting from together>=1.3.0, the default batch size is set to the maximum allowed value for each model.'\n",
|
||||
"message='Starting from together>=1.3.0, the default batch size is set to the maximum allowed value for each model.'\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"FT_JOB_ID ft-49dc2cfb-959b\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"FT_JOB_ID = \"ft-49dc2cfb-959b\"\n",
|
||||
"if not FT_JOB_ID:\n",
|
||||
" job_resp = client.fine_tuning.create(\n",
|
||||
" training_file=DATASET_FILE_ID,\n",
|
||||
" model=BASE_MODEL_ID,\n",
|
||||
" lora=True,\n",
|
||||
" lora_r=16,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" print(\"FT_JOB_ID\", job_resp.id)\n",
|
||||
" FT_JOB_ID = job_resp.id\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"status: FinetuneJobStatus.STATUS_PENDING steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_QUEUED steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_QUEUED steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_QUEUED steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_QUEUED steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_QUEUED steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_QUEUED steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 0 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 1 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 10 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 20 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 29 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 39 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 49 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 58 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 68 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 73 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B', 'Epoch completed, at step 73']\n",
|
||||
"status: FinetuneJobStatus.STATUS_RUNNING steps_completed: 73 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B', 'Epoch completed, at step 73', 'Training completed for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:58:05 UTC 2025']\n",
|
||||
"status: FinetuneJobStatus.STATUS_COMPRESSING steps_completed: 73 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B', 'Epoch completed, at step 73', 'Training completed for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:58:05 UTC 2025', 'Uploading output model', 'Compressing output model', 'Model compression complete']\n",
|
||||
"status: FinetuneJobStatus.STATUS_COMPRESSING steps_completed: 73 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B', 'Epoch completed, at step 73', 'Training completed for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:58:05 UTC 2025', 'Uploading output model', 'Compressing output model', 'Model compression complete']\n",
|
||||
"status: FinetuneJobStatus.STATUS_COMPRESSING steps_completed: 73 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B', 'Epoch completed, at step 73', 'Training completed for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:58:05 UTC 2025', 'Uploading output model', 'Compressing output model', 'Model compression complete']\n",
|
||||
"status: FinetuneJobStatus.STATUS_COMPLETED steps_completed: 73 output_name: zackovits/DeepSeek-R1-Distill-Qwen-14B-77124c1f events: ['Fine tune request created', 'Job started at Wed Mar 26 10:43:55 UTC 2025', 'Model data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:43:57 UTC 2025', 'Data downloaded for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at $2025-03-26T10:44:05.779202', 'Training started for model togethercomputer/DeepSeek-R1-Distill-Qwen-14B', 'Epoch completed, at step 73', 'Training completed for togethercomputer/DeepSeek-R1-Distill-Qwen-14B at Wed Mar 26 10:58:05 UTC 2025', 'Uploading output model', 'Compressing output model', 'Model compression complete', 'Model upload complete', 'Job finished at Wed Mar 26 11:03:54 UTC 2025']\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from together.types.finetune import FinetuneJobStatus\n",
|
||||
"\n",
|
||||
"status = None\n",
|
||||
"while status != FinetuneJobStatus.STATUS_COMPLETED:\n",
|
||||
" ft_resp = client.fine_tuning.retrieve(FT_JOB_ID)\n",
|
||||
" status = ft_resp.status\n",
|
||||
" print(\n",
|
||||
" \"status:\",\n",
|
||||
" ft_resp.status,\n",
|
||||
" \"steps_completed:\",\n",
|
||||
" ft_resp.steps_completed,\n",
|
||||
" \"output_name:\",\n",
|
||||
" ft_resp.output_name,\n",
|
||||
" \"events:\",\n",
|
||||
" [event.message for event in ft_resp.events or []],\n",
|
||||
" )\n",
|
||||
" time.sleep(90)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "r1-distill-qwen-14b-roblox-luau-M2w3-kVb-py3.11",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
303331
tokenizer.json
Normal file
303331
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
196
tokenizer_config.json
Normal file
196
tokenizer_config.json
Normal file
@@ -0,0 +1,196 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<｜User｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151645": {
|
||||
"content": "<｜Assistant｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151646": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|EOT|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151648": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151649": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"extra_special_tokens": {},
|
||||
"legacy": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
1308
trainer_state.json
Normal file
1308
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user