Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,7 @@ base_model:
|
|
| 7 |
## Model Details
|
| 8 |
|
| 9 |
This model is an int4 model with group_size 128 and and symmetric quantization of [deepseek-ai/DeepSeek-V2.5-1210](https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. Load the model with `revision="6d3d2cf"` to use AutoGPTQ format. **Please note that loading the model in Transformers can be quite slow. Consider using an alternative serving framework for better performance.**
|
|
|
|
| 10 |
|
| 11 |
## How To Use
|
| 12 |
|
|
|
|
| 7 |
## Model Details
|
| 8 |
|
| 9 |
This model is an int4 model with group_size 128 and and symmetric quantization of [deepseek-ai/DeepSeek-V2.5-1210](https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. Load the model with `revision="6d3d2cf"` to use AutoGPTQ format. **Please note that loading the model in Transformers can be quite slow. Consider using an alternative serving framework for better performance.**
|
| 10 |
+
For other serving framework, you should need the autogptq format, you could run the following cmd "git clone https://huggingface.co/OPEA/DeepSeek-V2.5-1210-int4-sym-inc && cd DeepSeek-V2.5-1210-int4-sym-inc && git checkout 6d3d2cf". Please follow the licence of the origin model.
|
| 11 |
|
| 12 |
## How To Use
|
| 13 |
|