Update README.md

README.md

@@ -130,9 +130,7 @@ The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Qwen2.5-7B-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
-  --apply_chat_template \
-  --fewshot_as_multiturn \
+  --model_args pretrained="neuralmagic/Qwen2.5-7B-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
   --tasks openllm \
   --batch_size auto
 ```