bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-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/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-17 01:11:06 +08:00
commit 19e71f327e
28 changed files with 268 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.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
Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated-f16.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-7B-Instruct-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text

3
Qwen2.5-Coder-7B-Instruct-abliterated-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61a52b8cd3ee82eaaa01384d71aea825cdffabfa557ff17005a864bdc9e0e9c7
size 2780343136

3
Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e3c3e6760cb39698e76aded8a8e6984f9167a8535d5054a85e00bfd29501f7e
size 3574012768

3
Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51feeba10633c5d102dfe8fb468ea796d6e39a53e87ea5a86260df5b16e69e84
size 3346256736

3
Qwen2.5-Coder-7B-Instruct-abliterated-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:817eecd198c0270dd4f1ef2fac1ab96cc4a0f92f2830e96e67d177e6f4e2c62e
size 4218473312

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:469810f66a49925ee1a96592979b230fa79223def9ec3450f9d6834daa6ce47f
size 3015940960

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dae6a3ea484043e68e0cccef649227b3eaef4b27d9db9227041cc80d6a087ffb
size 3548164960

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb80a2fad3ee68605dcd90964e3fe21920d509ad639177c6b1c11329ca21faf5
size 4088460128

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:618a975df17046993b865a9981d45bc821fe3409fa8ade08119a33fdce39ac76
size 3808392032

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca328bb73083768f502ca59e58d77eeda1b54e898d5cf639cb234e5d70877735
size 3492369248

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ba33e74f0503ff931c636ef0ba7a468395784c33926f48215ff49c5c1a69eb0
size 4565332832

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44da603c994d48d48ac4f69a530c7c716855e12eed3edb900b84e16acff0308e
size 4444121952

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:48ab37aa8ca8d5a1ccf05dd0a533c54fb30a43dd48bb57216f908af33d383d05
size 4431391584

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:043b2a354377d0e027cd917e7516898385920d441403fbd88dc2875fe1d64fbc
size 4431391584

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f1615e43953589f957a8ba3339ae9e001706ac516b3cb55ed6106317c4586e5
size 4431391584

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b541d2b484d49c9995c94e0b90a4a4fe2eb0b589eb3f302bfeb0bef28fab81b
size 5087564640

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fdf02c16fb654ff60b2c30f1e91573ebc603a7084df3449df89120dca2b18170
size 4683074400

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e56fecf0bb302b917eff5ff09cdf538ae249729e7a2d3a3839e5347efb710a0
size 4457769824

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3d1d417a5467804bebe98982f01daef358ef2a4e7df4830e42543125d189312
size 5781197664

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0e62cdf3348a9f680adae4abd2785508b2a06f009e815271cd512c11d43281b
size 5444832096

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4ae93f290b6c4e601e2adc9ca0fa9b3c2c823c60edf3e6944c33b6d23b74a72
size 5315177312

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:16ba964743fe4bd3b45c5e562039795fa2ead1ae33dbb637632a25316b9e3f7a
size 6254199648

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f0e096733f7dcaddc088373374c55e41cd98e4a638cec63bc6fa225c2bfaf004
size 6518182752

3
Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc1a0cb02f5669e4f7068e9153d75d3239b09f91eb77e7c9ab83ddeef55d2b93
size 8098526048

3
Qwen2.5-Coder-7B-Instruct-abliterated-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75eebb09c766402b6ea41d94f83bc1cb9a457cfe5849692e30ba92913aef8d5f
size 15237853728

3
Qwen2.5-Coder-7B-Instruct-abliterated.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e54d66cd023fc901dfafd44ecc06801f057ad73b4d9fe5e0433631a3d5e7270
size 4536678

132
README.md Normal file
View File

@@ -0,0 +1,132 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
language:
- en
license_link: https://huggingface.co/huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated/blob/main/LICENSE
tags:
- chat
- abliterated
- uncensored
base_model: huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Qwen2.5-Coder-7B-Instruct-abliterated
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4058">b4058</a> for quantization.
Original model: https://huggingface.co/huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated
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
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Qwen2.5-Coder-7B-Instruct-abliterated-f16.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-f16.gguf) | f16 | 15.24GB | false | Full F16 weights. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.43GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.43GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.43GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. *Don't use on Mac or Windows*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. |
| [Qwen2.5-Coder-7B-Instruct-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-7B-Instruct-abliterated-IQ2_M.gguf) | IQ2_M | 2.78GB | false | Relatively low quality, uses SOTA techniques to be surprisingly 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.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Downloading using huggingface-cli
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/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF --include "Qwen2.5-Coder-7B-Instruct-abliterated-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/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF --include "Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
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!).
## Which file should I choose?
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.
## 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}