mradermacher/LLaMA-7B-HF-i1-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: mradermacher/LLaMA-7B-HF-i1-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-10 14:13:23 +08:00
commit 8e68bf3084
52 changed files with 292 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
.gitattributes vendored Normal file
View File

@@ -0,0 +1,63 @@
*.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
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
imatrix.dat filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
LLaMA-7B-HF.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
llama-7b-hf.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
llama-7b-hf.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text

3
LLaMA-7B-HF.i1-IQ1_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d0f7d396d4132398ca17cca60dac07e81d850781ea7b0ae4490b67c3c84bcf4d
size 1650971360

3
LLaMA-7B-HF.i1-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:105094f7e49ef4659d4aba5b5e0a2f2ed2a9689e7fa3fc4f5eaedc3500778848
size 1528582880

3
LLaMA-7B-HF.i1-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c189bdae1351c95ac16e831c027a35e0f1d4f1d5da7c804394376b12cba08d5
size 2359751392

3
LLaMA-7B-HF.i1-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c43f4f1ac1593e9920fea421e98bcbad549f0847f20f14f9c5777432a663309d
size 2196566752

3
LLaMA-7B-HF.i1-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e7ba7fce46429282ac8c0852ad48d7698c791aae05d0dabb8d0c994dc09ded0
size 2034914016

3
LLaMA-7B-HF.i1-IQ2_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1b40c4fec3aba7715b29f36e064756270f68be6f9617319f5a4e5df7a79db56
size 1854952160

3
LLaMA-7B-HF.i1-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd52253f8dbac83861a75df7c6b4d99919232de34270c7eba7dbfb910469121c
size 3114865376

3
LLaMA-7B-HF.i1-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c71bcd166ffed35ed41b65f3f8be224a94e0c860927ba7207b728673e5ab0566
size 2948305632

3
LLaMA-7B-HF.i1-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:855d7a1aae2b25b048cc3f8cc8b15e7955c419ed008a9fb962c7df1e650aadf4
size 2796524256

3
LLaMA-7B-HF.i1-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b219104b733d0ff020681d3ac13205793742005f8a9d80bee55c6354568e4c1
size 2585391840

3
LLaMA-7B-HF.i1-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d9ed58394eb93873bf019545f2f1d37861547e7a41795c2914cfafb03daba93
size 3619336928

3
LLaMA-7B-HF.i1-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:23c15fadbf525f6973657553ca1b61d203b2811f15c5b3ea7f54716376e474de
size 2532864736

3
LLaMA-7B-HF.i1-Q2_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e43af7f9d323b1e72b64d9eefad6ffce3dbf5a8fc22cd5717041c708bb5318f4
size 2319545056

3
LLaMA-7B-HF.i1-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13de43eb64f804867fd8d3cf2a635380964214b14063580f1b12fe8d269ac3dd
size 3597112032

3
LLaMA-7B-HF.i1-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0b7aa9834b4fad9f40bead8b2e09214536f3d5ae49af9ab862f6d3ffdfaf2d7
size 3298005728

3
LLaMA-7B-HF.i1-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:951a5b47d12d1e97ef18535aeadb65b2bbaf04542ac02da35f7bd737bbd7e359
size 2948305632

3
LLaMA-7B-HF.i1-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f6ef141a706bd19f4d1a21c2011899de48fe33b1afa26b0f51b4de5f614f653
size 3837080288

3
LLaMA-7B-HF.i1-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a550842b6ad7f02f5e7eacc7adf2e08f460299c426597e3b6b7d2f28f84b3924
size 3825808096

3
LLaMA-7B-HF.i1-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f86460610a119346e94a8c3a89aa0a0f8d3bb60005868c3a45ba09772d78aed
size 3825808096

3
LLaMA-7B-HF.i1-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2302594b1fe180dafb17b2b77fd5619ef1ce5d05f9e1e2bd7379d4e4f1287ab
size 3825808096

3
LLaMA-7B-HF.i1-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8faca34e94c383a73367749ebee92b4bf2bd69a31fe50c6647875d07b3aef379
size 4081005280

3
LLaMA-7B-HF.i1-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4601638b2fd51a2c4448d9303180c76b44668f570a4e4f7f0788c6446d6f2d1
size 3856741088

3
LLaMA-7B-HF.i1-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85b7b0de4d22dc14f67c58d5424d3c9990e54816fdc2f110ea55e179ebc033b9
size 4783157984

3
LLaMA-7B-HF.i1-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e57cdf6baca0fdfaea81e3d664872b5c1349fb84c2e7b5a30c5ec727aa428383
size 4651692768

3
LLaMA-7B-HF.i1-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:794cf687fbe442c1e70bb7dd9c01b590b9850df969436b844ed8a6ff1c18ab7d
size 5529195232

79
README.md Normal file
View File

@@ -0,0 +1,79 @@
---
base_model: Neko-Institute-of-Science/LLaMA-7B-HF
language:
- en
library_name: transformers
license: other
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Neko-Institute-of-Science/LLaMA-7B-HF
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/LLaMA-7B-HF-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ1_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ1_M.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ1_M.gguf) | i1-IQ1_M | 3.4 | mostly desperate |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ2_XXS.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.9 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 3.9 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 3.9 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 3.9 | fast on arm+sve, low quality |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ2_XS.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q4_1.gguf) | i1-Q4_1 | 4.3 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ2_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q2_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.7 | very low quality |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ2_M.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ2_M.gguf) | i1-IQ2_M | 4.8 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q2_K.gguf) | i1-Q2_K | 5.2 | IQ3_XXS probably better |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ3_XXS.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.3 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ3_XS.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.7 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ3_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ3_S.gguf) | i1-IQ3_S | 6.0 | beats Q3_K* |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.0 | IQ3_XS probably better |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ3_M.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 6.3 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.7 | IQ3_S probably better |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.3 | IQ3_M probably better |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.3 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q4_0.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q4_0.gguf) | i1-Q4_0 | 7.8 | fast, low quality |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.8 | optimal size/speed/quality |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.3 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.4 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.7 | |
| [PART 1](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/LLaMA-7B-HF.i1-Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/LLaMA-7B-HF-i1-GGUF/resolve/main/llama-7b-hf.i1-Q6_K.gguf) | i1-Q6_K | 11.2 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->

3
imatrix.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:934dc49951008ccd810a626a25cebfdddd85528fe12b7c5d38dfc34a524b4ca2
size 4562173

3
llama-7b-hf.i1-IQ1_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72e1ca78e4e79c34c0759f96e9bfa6585f81664eea0e4810ab1f0c380d602364
size 1650971200

3
llama-7b-hf.i1-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:954d1fff4a7cddea0574a2db41e1481994f91fa9fd0df96478fb358afa3d9581
size 1528582720

3
llama-7b-hf.i1-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7123f99671bde6a815e916a5c51c0b9ab21f16343347b364eb3265715029be50
size 2359751232

3
llama-7b-hf.i1-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f8d5b0b463a689834f55bdb1a6cf9634f712651d5ec5e581621c2a0d816bd1f8
size 2196566592

3
llama-7b-hf.i1-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5429ecac9885d80122bc47f34dd879d266e6a1cb86a13c9026b2ab910925946
size 2034913856

3
llama-7b-hf.i1-IQ2_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66486050bbcb31595cd0f94544cb43d4059b8e31b2816424a76e7d73a65e0a6d
size 1854952000

3
llama-7b-hf.i1-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d569425a69aa2eb7b4a5613b4bcd7995d91459a7a74679b63307305103ab23f5
size 3114865216

3
llama-7b-hf.i1-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b8dd12284c34a38fa864bde1e6ff3ee8c209d1a919cb354674091057576a9ccd
size 2948305472

3
llama-7b-hf.i1-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1e2bf566949d6d8f908641fecd8e7be1e6918c0a5e194af16dd1b4085b8b07d
size 2796524096

3
llama-7b-hf.i1-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:975fb8512d82dc29a9b1401602002fde77d5ca599d50fe48ffdd1c9810de4450
size 2585391680

3
llama-7b-hf.i1-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28e892ec50a2873c67ea120d390e7e8526ed21979853001aad8b2a4ac5694a75
size 3825807936

3
llama-7b-hf.i1-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fbc435e015fb54f1a1b4c8b547393ae7883050545343ffd2232d62859f50d1d
size 3619336768

3
llama-7b-hf.i1-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c99ba9bf86f426335dc48b851483eea69902340e0e80e297fe7f847fb2f985ff
size 2532864576

3
llama-7b-hf.i1-Q2_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10caa7f230e04e8f44f59433a30a2a96558567407db197c54e2f77f620a85357
size 2319544896

3
llama-7b-hf.i1-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:740ff1ad064ef2d476b68409d7e7237633bc5dad60e92705cf35741eb7cf4cc0
size 3597111872

3
llama-7b-hf.i1-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e58ff3af92a73bd6738b594ff0a8dbf7138db4081c388ba94ed23ef53f15f358
size 3298005568

3
llama-7b-hf.i1-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d834ba1ed7f4c06486228a5bf769461609e333c75060899b009cc62fd9caf192
size 2948305472

3
llama-7b-hf.i1-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd3c2639e9f9c804bca1182d4f24c684761bba3e26d7936bc5ce2ba4c7ce946c
size 3837080128

3
llama-7b-hf.i1-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2929579dcb8879ca4c7128281c7a41b43310087ad3cb874d42352330d120b48
size 4238750272

3
llama-7b-hf.i1-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7dd35bdcea8fbe24e72e0a1b7fe169980c91d0a4d51a5c6e501df4328e28413a
size 4081005120

3
llama-7b-hf.i1-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c73f9161532f33ee6d3220b239d16a314e0f17f934aaaa7636650b7657baefb4
size 3856740928

3
llama-7b-hf.i1-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6fd71327b0d127906304da2a51f076057bcc6f0676c881ba48ff6f3e862040d
size 4783157824

3
llama-7b-hf.i1-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40dcfe60ec3066ad5899e3f6c0e56e827fa2502d1caa6261c8fa311f21e97c3b
size 4651692608

3
llama-7b-hf.i1-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fbe24acebc10b1bba5b1c3b830fbdab1898a1c34de63d6b4b92a5f13b56cb078
size 5529195072