bartowski/CodeLlama-13B-MORepair-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: bartowski/CodeLlama-13B-MORepair-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-05 12:21:13 +08:00
commit d071b15cab
29 changed files with 301 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
.gitattributes vendored Normal file
View File

@@ -0,0 +1,61 @@
*.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
CodeLlama-13B-MORepair-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair-f16.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-13B-MORepair.imatrix filter=lfs diff=lfs merge=lfs -text

3
CodeLlama-13B-MORepair-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d83b9b84762d0d7fb60df06099461c2bf34977600046ad6bbdfa9ef0b8854e35
size 4517671744

3
CodeLlama-13B-MORepair-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e0e170feabfc1c5d4e522477082f36ad598f132842047c2fe546a07d7a2ab79f
size 4197774144

3
CodeLlama-13B-MORepair-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e19c0e5cde4902cada1da74550a0f38f6016112c03c2d581da56df023e5bd2ba
size 5984613824

3
CodeLlama-13B-MORepair-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:99a89e09a1794eaa29568c3218a7b3b35af2ab83bdebcf58820f57af037f2f4d
size 5361714624

3
CodeLlama-13B-MORepair-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:393930b113ebe1ceac86418da0aa62b42543cdd9d6e74f4aee10081a39698de1
size 6964334144

3
CodeLlama-13B-MORepair-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:63a89884ba44736f7f34c4073d01aaf90f88ee3e86867f29f4ba5fae96afa93c
size 4854365504

3
CodeLlama-13B-MORepair-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f0c2449f03654f11fc135f4e75af76876cd98e687d3d52628c0fad3c90da3cd
size 5014445504

3
CodeLlama-13B-MORepair-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3942e2c104509f56d4846e1708a9bc12cf5637cc109a7d64a9decb0fbd3d62b0
size 6929663424

3
CodeLlama-13B-MORepair-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8cd407ed2f1876786acfbc699d78fc749302bb4157e1a0c47f1f0ef774f37ed6
size 6337873344

3
CodeLlama-13B-MORepair-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2b48d4f36fdc9e4fc2d7b5afd0a9fa4a8080bbdf3922a93a62eb72f7becf652
size 5659084224

3
CodeLlama-13B-MORepair-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64c795e21a23e86eb6ad2e17fa21743544b2889ed93d5b9e89ef523a0cf7e662
size 7073095104

3
CodeLlama-13B-MORepair-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:afa2aa7ca1c7941980b754d7a57bacc1c02f07bc8416222d30f4ec8df0bc5160
size 7388067904

3
CodeLlama-13B-MORepair-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0160810312ba32a042d1452a97427f33c5ce189619e9d7b34289087754d677e8
size 7365949504

3
CodeLlama-13B-MORepair-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e448ec17ecfb57cefd5468a3036179fc609005b277674abf67d25a1741d63698
size 7365949504

3
CodeLlama-13B-MORepair-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78030fc037da7e65f8a3e793d3727b8accd222c859293421a990a6a77f763318
size 7365949504

3
CodeLlama-13B-MORepair-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:04c6a8596e860bb55f68208ec212a982313ba6ae0954115705e52dc1dd008cf2
size 7987731904

3
CodeLlama-13B-MORepair-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ff9f529d654b7ce798b69f6a08782a2c547a52fe0ee3471d9013f78cac64f40
size 7866071104

3
CodeLlama-13B-MORepair-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7508c3f192652711e89cf49ffa8429fb1b91ddffe148d6c04ca951484094c7a6
size 7423293504

3
CodeLlama-13B-MORepair-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd92fb4909d9c38ce61eb16b8af339a170c7f72578839969c402797cb5c6df69
size 9331219904

3
CodeLlama-13B-MORepair-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c2173ac89f9c330ed74b13d81e47b46db575789cbd68cba0dc87b47807a4ce76
size 9230049344

3
CodeLlama-13B-MORepair-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:417af40f95488e7b013dfc73b0dd44742a480784c61c232c0b333292e1c30d39
size 8972410944

3
CodeLlama-13B-MORepair-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6b0c5207e94e1ffce572a5bd6302b4867f080235da1228669350e80387a6896
size 10679276224

3
CodeLlama-13B-MORepair-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e355f38bf8dd59d0ec555f795ee17f38fb0c2750c539dbd109f807f8f87d92ee
size 10758675904

3
CodeLlama-13B-MORepair-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0196da421d811990bdf8a36920738e8fe6d5dfb7f515b5163a272020e69d3446
size 13831495104

3
CodeLlama-13B-MORepair-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a51a0477b73a19db7b2a9ab04afbd4925fb1cfd93eaa1a6e7d806193b9e85d5
size 26033632416

3
CodeLlama-13B-MORepair.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8df46e08f94fa94ed6591df1faa1fe76dd76a3092880951394aaf67551412617
size 7136338

161
README.md Normal file
View File

@@ -0,0 +1,161 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license: llama2
base_model: barty/CodeLlama-13B-MORepair
---
## Llamacpp imatrix Quantizations of CodeLlama-13B-MORepair
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4191">b4191</a> for quantization.
Original model: https://huggingface.co/barty/CodeLlama-13B-MORepair
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
No prompt format found, check original model page
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [CodeLlama-13B-MORepair-f16.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-f16.gguf) | f16 | 26.03GB | false | Full F16 weights. |
| [CodeLlama-13B-MORepair-Q8_0.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q8_0.gguf) | Q8_0 | 13.83GB | false | Extremely high quality, generally unneeded but max available quant. |
| [CodeLlama-13B-MORepair-Q6_K_L.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q6_K_L.gguf) | Q6_K_L | 10.76GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [CodeLlama-13B-MORepair-Q6_K.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q6_K.gguf) | Q6_K | 10.68GB | false | Very high quality, near perfect, *recommended*. |
| [CodeLlama-13B-MORepair-Q5_K_L.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q5_K_L.gguf) | Q5_K_L | 9.33GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [CodeLlama-13B-MORepair-Q5_K_M.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q5_K_M.gguf) | Q5_K_M | 9.23GB | false | High quality, *recommended*. |
| [CodeLlama-13B-MORepair-Q5_K_S.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q5_K_S.gguf) | Q5_K_S | 8.97GB | false | High quality, *recommended*. |
| [CodeLlama-13B-MORepair-Q4_K_L.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_K_L.gguf) | Q4_K_L | 7.99GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [CodeLlama-13B-MORepair-Q4_K_M.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_K_M.gguf) | Q4_K_M | 7.87GB | false | Good quality, default size for most use cases, *recommended*. |
| [CodeLlama-13B-MORepair-Q4_K_S.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_K_S.gguf) | Q4_K_S | 7.42GB | false | Slightly lower quality with more space savings, *recommended*. |
| [CodeLlama-13B-MORepair-Q4_0.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_0.gguf) | Q4_0 | 7.39GB | false | Legacy format, generally not worth using over similarly sized formats |
| [CodeLlama-13B-MORepair-Q4_0_8_8.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_0_8_8.gguf) | Q4_0_8_8 | 7.37GB | false | Optimized for ARM and AVX inference. Requires 'sve' support for ARM (see details below). *Don't use on Mac*. |
| [CodeLlama-13B-MORepair-Q4_0_4_8.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_0_4_8.gguf) | Q4_0_4_8 | 7.37GB | false | Optimized for ARM inference. Requires 'i8mm' support (see details below). *Don't use on Mac*. |
| [CodeLlama-13B-MORepair-Q4_0_4_4.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q4_0_4_4.gguf) | Q4_0_4_4 | 7.37GB | false | Optimized for ARM inference. Should work well on all ARM chips, not for use with GPUs. *Don't use on Mac*. |
| [CodeLlama-13B-MORepair-Q3_K_XL.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q3_K_XL.gguf) | Q3_K_XL | 7.07GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [CodeLlama-13B-MORepair-IQ4_XS.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-IQ4_XS.gguf) | IQ4_XS | 6.96GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [CodeLlama-13B-MORepair-Q3_K_L.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q3_K_L.gguf) | Q3_K_L | 6.93GB | false | Lower quality but usable, good for low RAM availability. |
| [CodeLlama-13B-MORepair-Q3_K_M.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q3_K_M.gguf) | Q3_K_M | 6.34GB | false | Low quality. |
| [CodeLlama-13B-MORepair-IQ3_M.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-IQ3_M.gguf) | IQ3_M | 5.98GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [CodeLlama-13B-MORepair-Q3_K_S.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q3_K_S.gguf) | Q3_K_S | 5.66GB | false | Low quality, not recommended. |
| [CodeLlama-13B-MORepair-IQ3_XS.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-IQ3_XS.gguf) | IQ3_XS | 5.36GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [CodeLlama-13B-MORepair-Q2_K_L.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q2_K_L.gguf) | Q2_K_L | 5.01GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [CodeLlama-13B-MORepair-Q2_K.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-Q2_K.gguf) | Q2_K | 4.85GB | false | Very low quality but surprisingly usable. |
| [CodeLlama-13B-MORepair-IQ2_M.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-IQ2_M.gguf) | IQ2_M | 4.52GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [CodeLlama-13B-MORepair-IQ2_S.gguf](https://huggingface.co/bartowski/CodeLlama-13B-MORepair-GGUF/blob/main/CodeLlama-13B-MORepair-IQ2_S.gguf) | IQ2_S | 4.20GB | false | Low quality, uses SOTA techniques to be usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/CodeLlama-13B-MORepair-GGUF --include "CodeLlama-13B-MORepair-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/CodeLlama-13B-MORepair-GGUF --include "CodeLlama-13B-MORepair-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (CodeLlama-13B-MORepair-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
<details>
<summary>Click to view Q4_0_X_X information</summary>
These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
</details>
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
Thank you ZeroWw for the inspiration to experiment with embed/output.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}