Update README.md

README.md

@@ -169,7 +169,7 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge and
    </td>
   </tr>
   <tr>
-   <td>GSM-8K-cot (8-shot, strict-match)
+   <td>GSM-8K (CoT, 8-shot, strict-match)
    </td>
    <td>96.44
    </td>
@@ -199,7 +199,7 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge and
    </td>
   </tr>
   <tr>
-   <td>TruthfulQA (0-shot)
+   <td>TruthfulQA (0-shot, mc2)
    </td>
    <td>64.64
    </td>
@@ -253,6 +253,7 @@ lm_eval \
   --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --apply_chat_template \
+  --fewshot_as_multiturn \
   --num_fewshot 8 \
   --batch_size auto
 ```
@@ -282,7 +283,7 @@ lm_eval \
 lm_eval \
   --model vllm \
   --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8 \
-  --tasks truthfulqa_mc \
+  --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto
 ```