Update README.md

README.md

@@ -35,25 +35,24 @@ print(tokenizer.decode(model.generate(**tokenizer("There is a girl who likes adv
 Install [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness.git) from source, we used the git id 96d185fa6232a5ab685ba7c43e45d1dbb3bb906d
 
 ```bash
-lm_eval --model hf --model_args pretrained="Intel/gpt-j-6b-int4-inc",autogptq=True,gptq_use_triton=True --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu --batch_size 32
+lm_eval --model hf --model_args pretrained="Intel/gpt-j-6b-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
 ```
 
 
-
-| Metric         | BF16   | INT4   |
+| Metric         | FP16   | INT4   |
 | -------------- | ------ | ------ |
-| Avg.           | 0. | 0.4993 |
-| mmlu           | 0. | 0.2750 |
-| lambada_openai | 0. | 0.6845 |
-| hellaswag      | 0. | 0.4897 |
-| winogrande     | 0. | 0.6425 |
-| piqa           | 0. | 0.7448 |
-| truthfulqa_mc1 | 0. | 0.2093 |
-| openbookqa     | 0. | 0.2820 |
-| boolq          | 0. | 0.6511 |
-| arc_easy       | 0. | 0.6709 |
-| arc_challenge  | 0. | 0.3430 |
-
+| Avg.           | 0.5039 | 0.5034 |
+| mmlu           | 0.2694 | 0.2793 |
+| lambada_openai | 0.6831 | 0.6790 |
+| hellaswag      | 0.4953 | 0.4902 |
+| winogrande     | 0.6409 | 0.6401 |
+| piqa           | 0.7541 | 0.7465 |
+| truthfulqa_mc1 | 0.2020 | 0.2179 |
+| openbookqa     | 0.2900 | 0.2900 |
+| boolq          | 0.6544 | 0.6554 |
+| rte            | 0.5451 | 0.5271 |
+| arc_easy       | 0.6692 | 0.6734 |
+| arc_challenge  | 0.3396 | 0.3387 |
 
 
 ### Reproduce the model