Update README.md

README.md

@@ -168,7 +168,7 @@ 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>82.03
    </td>
@@ -198,7 +198,7 @@ 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>54.04
    </td>
@@ -251,6 +251,7 @@ lm_eval \
   --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks gsm8k_cot_llama_3.1_instruct \
   --apply_chat_template \
+  --fewshot_as_multiturn \
   --num_fewshot 8 \
   --batch_size auto
 ```
@@ -280,7 +281,7 @@ lm_eval \
 lm_eval \
   --model vllm \
   --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
-  --tasks truthfulqa_mc \
+  --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto
 ```