Hugging Face's logo

Intel
/
Qwen2-0.5B-Instuct-int4-inc

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Model card Files Community
lvkaokao commited on
Commit
cdff310
•
1 Parent(s): 893a3e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -39,7 +39,7 @@ pip3 install lm-eval==0.4.2
39
  lm_eval --model hf --model_args pretrained="Intel/Qwen2-0.5B-Instuct-int4-inc" --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu --batch_size 16
40
  ```
41
 
42
- | Metric0.5B-instruct | BF16 | W4G32 sym |
43
  | ------------------- | ------ | ---------- |
44
  | Avg | 0.4562 | 0.4506 |
45
  | mmlu | 0.4342 | 0.4205 |
 
39
  lm_eval --model hf --model_args pretrained="Intel/Qwen2-0.5B-Instuct-int4-inc" --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu --batch_size 16
40
  ```
41
 
42
+ | Metric0.5B-instruct | BF16 | INT4 |
43
  | ------------------- | ------ | ---------- |
44
  | Avg | 0.4562 | 0.4506 |
45
  | mmlu | 0.4342 | 0.4205 |