OPEA
/

Safetensors
llama
4-bit precision
intel/auto-round
cicdatopea commited on
Commit
743cc86
·
verified ·
1 Parent(s): 1281e2f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -83,7 +83,7 @@ prompt = "How many r in strawberry."
83
  pip3 install lm-eval==0.4.5. We have no enough resource to evaluate the bf16 model.
84
 
85
  ```bash
86
- auto-round --eval --model_name "OPEA/Meta-Llama-3.1-405B-Instruct-int4-sym-inc" --eval_bs 16 --tasks leaderboard_mmlu_pro,leaderboard_ifeval,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu,gsm8k
87
  ```
88
 
89
  | Metric | INT4 |
 
83
  pip3 install lm-eval==0.4.5. We have no enough resource to evaluate the bf16 model.
84
 
85
  ```bash
86
+ auto-round --eval --model_name "OPEA/Meta-Llama-3.1-405B-Instruct-int4-sym-inc" --device 0,1,2,3 --eval_bs 16 --tasks leaderboard_mmlu_pro,leaderboard_ifeval,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu,gsm8k
87
  ```
88
 
89
  | Metric | INT4 |