Hugging Face's logo

OPEA
/
DeepSeek-R1-Distill-Qwen-32B-int4-gptq-sym-inc

Safetensors
qwen2
4-bit precision
gptq
Model card Files
xet
 Community
2
cicdatopea commited on
Commit
5c84894
·
verified ·
1 Parent(s): 826d1dd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -161,7 +161,7 @@ pip3 install lm-eval==0.4.7
161
  lm-eval --model hf --model_args pretrained=OPEA/DeepSeek-R1-Distill-Qwen-32B-int4-sym-inc --tasks leaderboard_mmlu_pro,leaderboard_ifeval,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu,gsm8k --batch_size 16
162
  ```
163
  | Metric | BF16 | INT4 |
164
- | :------------------------: | :----------------------: | :---------------: |
165
  | avg | 0.6647 | 0.6639|
166
  | leaderboard_mmlu_pro | - | - |
167
  | mmlu | 0.7964 | 0.7928 |
 
161
  lm-eval --model hf --model_args pretrained=OPEA/DeepSeek-R1-Distill-Qwen-32B-int4-sym-inc --tasks leaderboard_mmlu_pro,leaderboard_ifeval,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu,gsm8k --batch_size 16
162
  ```
163
  | Metric | BF16 | INT4 |
164
+ | :------------------------ | :---------------------- | :--------------- |
165
  | avg | 0.6647 | 0.6639|
166
  | leaderboard_mmlu_pro | - | - |
167
  | mmlu | 0.7964 | 0.7928 |