OPEA
/

Safetensors
llama
4-bit precision
intel/auto-round
cicdatopea commited on
Commit
5f98568
·
verified ·
1 Parent(s): ded5a6c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -91,7 +91,7 @@ prompt = "How many r in strawberry."
91
  pip3 install lm-eval==0.4.5
92
 
93
  ```bash
94
- auto-round --eval --model_name "OPEA/Meta-Llama-3.1-70B-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
95
  ```
96
 
97
  | Metric | BF16 | INT4 |
 
91
  pip3 install lm-eval==0.4.5
92
 
93
  ```bash
94
+ auto-round --eval --model "OPEA/Meta-Llama-3.1-70B-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
95
  ```
96
 
97
  | Metric | BF16 | INT4 |