bartowski/Qwen2.5-Coder-14B-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-14B-Instruct-abliterated-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 22:37:08 +08:00
commit ede9dbfc4e
30 changed files with 282 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
.gitattributes vendored Normal file
View File

@@ -0,0 +1,62 @@
*.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-14B-Instruct-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated-f16.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-14B-Instruct-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text

3
Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf196a07a1f426c1546fa492386f2ab774b8b3f95e7efafc24464587343647fa
size 5356147040

3
Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:87c43238aa4f26a16bf787da00d7bf3f2e22a8bdb97bbe9c96300e309831e00a
size 5003727200

3
Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:71b94a75812f040fff28c40c8f07065f43715460b32e09daa7f3bf795c7510ad
size 4704575840

3
Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c96aeb5fde30bad71c7f95c6c2cbf08931752b1f55a1200eef017a3da8e21a81
size 6916538720

3
Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4449b5a12f7f0989c448e0aa616e6d89995c11ea0c99a42b0516eeaf5c0c06fd
size 6383362400

3
Qwen2.5-Coder-14B-Instruct-abliterated-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0df20e9138dc7a6679f9ab0be6391f68cd30b5f86c633c7d4334e62051ee87ed
size 8119841120

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03ef8e4a9b2a9046e70e881098bc9ec3b70e3c4fd02840b75145748cada5bad1
size 5770498400

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e50ce2751909cd17922c87987d9a4cb93939500d38bde7912f2dce75406032c7
size 6530818400

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:563934b22dd27c1f81265d75bf3a8c06b131f0c1a73919db271e0c2a061fee48
size 7924769120

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7a4c1ca5e9a7e51d9f76a4c5eef4de9dc0b45374df0defe6bdec89187e575b93
size 7339204960

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22f41b1d19a994b7b878c79b50293cc47d1e195fccb21964b934e3157af8e8d6
size 6659596640

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ac0f80d1113b790902e3eec4ca5e3a2669f2f522af117aa2de51ee4700536ab
size 8606015840

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c39da95ac8068f34ed6167e42d536bffba848097b1645f66b67dc8e1471c1241
size 8544268640

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d52a258f66bdca4e2aaead0db711f09e87d4866f377d0e053c0116f52fcfcce
size 8517726560

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97614c40165f74ca3031465bd45f0fde898c8164a2ff613d3eb758304ddef596
size 8517726560

3
Qwen2.5-Coder-14B-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:cae45dd61842592ac49d287d0a09a383716da9956b15675177173770f285e153
size 8517726560

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ab24a52bbfcc5f7cae4f9d57d5134aa140524132b3851519dbe4bf3af6e5db4
size 9565954400

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e89a7ae4e2b456bf33c75cff35664751df20ff273e551d7cf7640aa9e84d3b79
size 8988111200

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d92ad0f3c1ff0db90ca4b8c94b475b261cb2c7a917c94ce2c0a1768059a5db19
size 8573432160

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3804fe5025e045c7bf36c6d4ed76c81fc68bb41a95a35e90f956df425b9a5bf9
size 10989396320

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd5d9d157919fdedacfd42ed7095d818fc5dc76cf8084fb3393f17fbe7cd5038
size 10508874080

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1735797dc7a8eed16fda5233c49256f992074259bf22a05c0c6fc4b4b5d078c1
size 10266554720

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:341f5d4db35978331e7f2bfde3871d76b7c856bb5279ffaed19616092ec79e69
size 12124684640

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b8d708034f69eefbd90fcfe6e566b583b5380d8a445d2e0650aafe58218a25a
size 12501803360

3
Qwen2.5-Coder-14B-Instruct-abliterated-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e4be871399b8a0a820feba76547c42125e71a5435247346d9c7f7cf892e8372
size 15701598560

3
Qwen2.5-Coder-14B-Instruct-abliterated-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6dd5636aa659b60be49f52fb4d364b9748fd0d83051735b9cde0b2bc560c41d5
size 29547716640

3
Qwen2.5-Coder-14B-Instruct-abliterated.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bbfdd1fc8f6609e31d264c1d612fb4d33a8f13078183d816ba249b0727233866
size 8563610

138
README.md Normal file
View File

@@ -0,0 +1,138 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
language:
- en
license_link: https://huggingface.co/huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterate/blob/main/LICENSE
tags:
- code
- codeqwen
- chat
- qwen
- qwen-coder
- abliterated
- uncensored
base_model: huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Qwen2.5-Coder-14B-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-14B-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-14B-Instruct-abliterated-f16.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-f16.gguf) | f16 | 29.55GB | false | Full F16 weights. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q5_K_S.gguf) | Q5_K_S | 10.27GB | false | High quality, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_L.gguf) | Q4_K_L | 9.57GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_M.gguf) | Q4_K_M | 8.99GB | false | Good quality, default size for most use cases, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 8.61GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_8_8.gguf) | Q4_0_8_8 | 8.52GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_8.gguf) | Q4_0_4_8 | 8.52GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q4_0_4_4.gguf) | Q4_0_4_4 | 8.52GB | 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-14B-Instruct-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-IQ4_XS.gguf) | IQ4_XS | 8.12GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_L.gguf) | Q3_K_L | 7.92GB | false | Lower quality but usable, good for low RAM availability. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_M.gguf) | Q3_K_M | 7.34GB | false | Low quality. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_M.gguf) | IQ3_M | 6.92GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K_L.gguf) | Q2_K_L | 6.53GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-Q2_K.gguf) | Q2_K | 5.77GB | false | Very low quality but surprisingly usable. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_M.gguf) | IQ2_M | 5.36GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_S.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_S.gguf) | IQ2_S | 5.00GB | false | Low quality, uses SOTA techniques to be usable. |
| [Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_XS.gguf](https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF/blob/main/Qwen2.5-Coder-14B-Instruct-abliterated-IQ2_XS.gguf) | IQ2_XS | 4.70GB | 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.
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-14B-Instruct-abliterated-GGUF --include "Qwen2.5-Coder-14B-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-14B-Instruct-abliterated-GGUF --include "Qwen2.5-Coder-14B-Instruct-abliterated-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Qwen2.5-Coder-14B-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}