Update README.md

README.md

@@ -191,7 +191,7 @@ 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>
@@ -243,6 +243,7 @@ lm_eval \
   --model vllm \
   --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks gsm8k_cot_llama_3.1_instruct \
+  --fewshot_as_multiturn \
   --apply_chat_template \
   --num_fewshot 8 \
   --batch_size auto
@@ -268,12 +269,12 @@ lm_eval \
   --batch_size auto
 ```
 
-#### Hellaswag
+#### TruthfulQA
 ```
 lm_eval \
   --model vllm \
   --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",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
 ```