Hugging Face's logo

kaitchup
/
Qwen2.5-1.5B-AutoRound-GPTQ-asym-4bit

Text Generation
Transformers
Safetensors
English
qwen2
auto-gptq
AutoRound
conversational
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Model card Files Community
bnjmnmarie commited on
Commit
4aab9a8
•
1 Parent(s): 2df5a65

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ output_dir = "./tmp_autoround"
31
  autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
32
  ```
33
 
34
- Evaluation results:
35
 
36
  ![arc_challenge, musr, gpqa, mmlu_pro, mmlu….png](https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/ExiQHtJf981JcUsHcbZW9.png)
37
 
 
31
  autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
32
  ```
33
 
34
+ Evaluation results (zero-shot evaluation with lm_eval):
35
 
36
  ![arc_challenge, musr, gpqa, mmlu_pro, mmlu….png](https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/ExiQHtJf981JcUsHcbZW9.png)
37