初始化项目，由ModelHub XC社区提供模型
Model: bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
64
.gitattributes
vendored
Normal file
64
.gitattributes
vendored
Normal file
@@ -0,0 +1,64 @@
|
||||
*.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
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
168
README.md
Normal file
168
README.md
Normal file
@@ -0,0 +1,168 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: text-generation
|
||||
base_model_relation: quantized
|
||||
base_model: huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of Huihui-gpt-oss-20b-BF16-abliterated by huihui-ai
|
||||
|
||||
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b6115">b6115</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/huihui-ai/Huihui-gpt-oss-20b-BF16-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/)
|
||||
|
||||
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
|
||||
|
||||
## 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 |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-bf16.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-bf16.gguf) | bf16 | 41.86GB | false | Full BF16 weights. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q8_0.gguf) | Q8_0 | 22.26GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf) | MXFP4_MOE | 12.11GB | false | Special format for OpenAI's gpt-oss models, see: https://github.com/ggml-org/llama.cpp/pull/15091 |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q6_K_L.gguf) | Q6_K_L | 12.04GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q6_K.gguf) | Q6_K | 12.04GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_L.gguf) | Q5_K_L | 11.91GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_L.gguf) | Q4_K_L | 11.89GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q2_K_L.gguf) | Q2_K_L | 11.85GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 11.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_M.gguf) | Q5_K_M | 11.73GB | false | High quality, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q5_K_S.gguf) | Q5_K_S | 11.72GB | false | High quality, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_M.gguf) | Q4_K_M | 11.67GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_K_S.gguf) | Q4_K_S | 11.67GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q4_1.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_1.gguf) | Q4_1 | 11.59GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ4_NL.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ4_NL.gguf) | IQ4_NL | 11.56GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ4_XS.gguf) | IQ4_XS | 11.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_M.gguf) | Q3_K_M | 11.56GB | false | Low quality. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_M.gguf) | IQ3_M | 11.56GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_XS.gguf) | IQ3_XS | 11.56GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ3_XXS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_XXS.gguf) | IQ3_XXS | 11.56GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q2_K.gguf) | Q2_K | 11.56GB | false | Very low quality but surprisingly usable. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_S.gguf) | Q3_K_S | 11.55GB | false | Low quality, not recommended. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_M.gguf) | IQ2_M | 11.55GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ2_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_S.gguf) | IQ2_S | 11.55GB | false | Low quality, uses SOTA techniques to be usable. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_0.gguf) | Q4_0 | 11.52GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ2_XS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_XS.gguf) | IQ2_XS | 11.51GB | false | Low quality, uses SOTA techniques to be usable. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-IQ2_XXS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_XXS.gguf) | IQ2_XXS | 11.51GB | false | Very low quality, uses SOTA techniques to be usable. |
|
||||
| [Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q3_K_L.gguf) | Q3_K_L | 11.49GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
|
||||
## 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/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF --include "huihui-ai_Huihui-gpt-oss-20b-BF16-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/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF --include "huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q8_0) or download them all in place (./)
|
||||
|
||||
</details>
|
||||
|
||||
## ARM/AVX information
|
||||
|
||||
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
|
||||
|
||||
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
|
||||
|
||||
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
|
||||
|
||||
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
|
||||
|
||||
<details>
|
||||
<summary>Click to view Q4_0_X_X information (deprecated</summary>
|
||||
|
||||
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
|
||||
|
||||
<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, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
||||
|
||||
</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.
|
||||
|
||||
Thank you to LM Studio for sponsoring my work.
|
||||
|
||||
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_M.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6295073d986cb73b72a5132ec55e5bde5465818320701eebdee63ab2d14910b8
|
||||
size 11545730720
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_S.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fd5c9eb8a0da8d3b861a97dba4ee45765e12765454577c32b7d00afe2206630
|
||||
size 11545730720
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b97134849de5fae1838da20a2e51c91b3862ffa4ed2569a949876f8df223bfde
|
||||
size 11510341280
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:76535bfb3b58862b0317993806198c0b372eda6cf80ebc2c42a7980c0487475e
|
||||
size 11510341280
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_M.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ed7990c1900d82d6dafef252e69319b37db6d28a710f6adfdf72e5ad307aae3
|
||||
size 11559001760
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:58f2f72a9e89bee6c45e0c722a1d2556e62916bedad1e46625fc759e822209a4
|
||||
size 11559001760
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:936bf2c953d9182d78c0e1307a37af56d7ce549447980ef0f3bf86daa07ad0af
|
||||
size 11559001760
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e9aca89ae5e34ca32fddf4d99bf50e0f23c9906a47cc281477ed71d50e223c5
|
||||
size 11561213600
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:99d4f575c9346a2a4efcbaec7f2761f87ebcb5fc41d92df35dcd2b6a37d57e15
|
||||
size 11561213600
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:abca50d1bd95c49d71db36aad0f38090ea5465ce148634c496a48bc87030bdd9
|
||||
size 12109565600
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q2_K.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c1e1e8708d40a30452f3a9317f1c7a9d763415ae58e6a91fff447f7a752291b9
|
||||
size 11559001760
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e25d983af6cf3f5b041eeb1fb8aaf1e043797efa5d6334b425c7fd342e421ec0
|
||||
size 11848568480
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:962536f2d29f1af1581b69c5685d202c8e60bbf0ae1a4d5d9d8be43e9d30ad78
|
||||
size 11488222880
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f633b5110a1d0b1484e5b0ebc25e6ad0784e61fa6b21239456e65ad6bfdacdb
|
||||
size 11559186080
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b1b36ba6c219de6913acc130ae590ffa0e336414d9163a546f2d0d17cbfc6de7
|
||||
size 11554578080
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92b70cc35e19f9b039c2d4c26f3973c47e74aa9ae351386f97fe29f59ecac6e5
|
||||
size 11777789600
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_0.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6b1e8408a83d5619082703797282399dc40a1100336f72704dbd0b208742b307
|
||||
size 11519188640
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_1.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:910fdd48be64c11fd04a16a8912e51bb8efc4f0e5e539530a2f369eb86fe1086
|
||||
size 11592985760
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:201577fe1c7a8bb17c311455cd56215e81fb1cb1ad8c5318de290e6526c1301c
|
||||
size 11890593440
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e3dfaacc1b7131c9790f5240ecbfca70a449ef8da6f68cf04577de89c55eea7b
|
||||
size 11673418400
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:550d00994093580749a63a6038f41351e290d40beff0bd0f3fbb541a46f0b111
|
||||
size 11667151520
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3297956cc17472dfe000c16f7fd9ac1c79ce187ab059d624ce9dac99882bd757
|
||||
size 11909394080
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b900354893d7ac55c5c889ebd0bc6726be352293b5fb07bb4bc7e2b2d6480819
|
||||
size 11728414880
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:578829605005ef68c8a423809df9267b437b02ca37551e4bd37c61eca9f785e3
|
||||
size 11722885280
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q6_K.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24f679be856db154e4d106de5d25627fe68c96aff2a7072f6bcc9e7b66d0faf8
|
||||
size 12040998560
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24f679be856db154e4d106de5d25627fe68c96aff2a7072f6bcc9e7b66d0faf8
|
||||
size 12040998560
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q8_0.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:341f05face523f6fbc9b5563234d1c57911be49726a46d07111ab9c30d72e6d6
|
||||
size 22261911200
|
||||
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-bf16.gguf
Normal file
3
huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1cd29875637894d48006545ef3ca20110633a136f06bd236de0bf3878af74f6f
|
||||
size 41860886880
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:277129922edfabadefb2428a13829198d867f83578657a5cd45b238d16da75f7
|
||||
size 28079776
|
||||
Reference in New Issue
Block a user