Update README.md

README.md

@@ -148,9 +148,19 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge and
   <tr>
    <td>MMLU (5-shot)
    </td>
-   <td>67.94
+   <td>69.43
    </td>
-   <td>67.58
+   <td>69.37
+   </td>
+   <td>99.9%
+   </td>
+  </tr>
+  <tr>
+   <td>MMLU (CoT, 0-shot)
+   </td>
+   <td>72.56
+   </td>
+   <td>72.14
    </td>
    <td>99.4%
    </td>
@@ -158,11 +168,11 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge and
   <tr>
    <td>ARC Challenge (0-shot)
    </td>
-   <td>83.19
+   <td>81.57
    </td>
-   <td>82.08
+   <td>81.48
    </td>
-   <td>98.7%
+   <td>99.9%
    </td>
   </tr>
   <tr>
@@ -208,11 +218,11 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge and
   <tr>
    <td><strong>Average</strong>
    </td>
-   <td><strong>74.31</strong>
+   <td><strong>74.04</strong>
    </td>
-   <td><strong>73.79</strong>
+   <td><strong>73.89</strong>
    </td>
-   <td><strong>99.3%</strong>
+   <td><strong>99.8%</strong>
    </td>
   </tr>
 </table>
@@ -225,17 +235,30 @@ The results were obtained using the following commands:
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
-  --tasks mmlu \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+  --tasks mmlu_llama_3.1_instruct \
+  --fewshot_as_multiturn \
+  --apply_chat_template \
   --num_fewshot 5 \
   --batch_size auto
 ```
 
+#### MMLU-CoT
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
+  --tasks mmlu_cot_0shot_llama_3.1_instruct \
+  --apply_chat_template \
+  --num_fewshot 0 \
+  --batch_size auto
+```
+
 #### ARC-Challenge
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
   --tasks arc_challenge_llama_3.1_instruct \
   --apply_chat_template \
   --num_fewshot 0 \
@@ -246,7 +269,7 @@ lm_eval \
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --fewshot_as_multiturn \
   --apply_chat_template \