cicdatopea commited on
Commit
4d2bf1e
·
verified ·
1 Parent(s): 7d61c25

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -1,10 +1,12 @@
1
  ---
2
  datasets:
3
  - NeelNanda/pile-10k
 
 
4
  ---
5
  ## Model Details
6
 
7
- This model is an int4 model with group_size 128 and symmetric quantization of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round). Load the model with `revision="f636d1"` to use AutoGPTQ format
8
 
9
  ## How To Use
10
 
@@ -172,4 +174,4 @@ The license on this model does not constitute legal advice. We are not responsib
172
 
173
  @article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
174
 
175
- [arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
 
1
  ---
2
  datasets:
3
  - NeelNanda/pile-10k
4
+ base_model:
5
+ - Qwen/Qwen2.5-3B-Instruct
6
  ---
7
  ## Model Details
8
 
9
+ This model is an int4 model with group_size 128 and symmetric quantization of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round). Load the model with `revision="f636d1"` to use AutoGPTQ format. Please follow the license of the origin model
10
 
11
  ## How To Use
12
 
 
174
 
175
  @article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
176
 
177
+ [arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)