Hugging Face's logo

Intel
/
Mistral-7B-Instruct-v0.2-int4-inc

English
Model card Files Community
yintongl commited on
Commit
6e7f14a
•
1 Parent(s): 06096d9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -44,7 +44,7 @@ Install [lm-eval-harness 0.4.2](https://github.com/EleutherAI/lm-evaluation-harn
44
  lm_eval --model hf --model_args pretrained="Intel/Mistral-7B-Instruct-v0.2-int4-inc",autogptq=True,gptq_use_triton=True --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,rte,arc_easy,arc_challenge,mmlu --batch_size 32
45
  ```
46
 
47
- | Metric | BF16 | INT4 |
48
  | -------------- | ------ | ------ |
49
  | Avg. | 0.6591 | 0.6573 |
50
  | mmlu | 0.5877 | 0.5866 |
 
44
  lm_eval --model hf --model_args pretrained="Intel/Mistral-7B-Instruct-v0.2-int4-inc",autogptq=True,gptq_use_triton=True --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,rte,arc_easy,arc_challenge,mmlu --batch_size 32
45
  ```
46
 
47
+ | Metric | FP16 | INT4 |
48
  | -------------- | ------ | ------ |
49
  | Avg. | 0.6591 | 0.6573 |
50
  | mmlu | 0.5877 | 0.5866 |