Update README.md

README.md

@@ -41,6 +41,7 @@ from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
 
 model_id = "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a16"
+number_gpus = 1
 
 sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
 
@@ -51,9 +52,9 @@ messages = [
     {"role": "user", "content": "Who are you?"},
 ]
 
-prompts = tokenizer.apply_chat_template(messages, tokenize=False)
+prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
 
-llm = LLM(model=model_id)
+llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
 
 outputs = llm.generate(prompts, sampling_params)
 
@@ -161,7 +162,7 @@ The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a16",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096 \
+  --model_args pretrained="neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a16",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
   --tasks openllm \
   --batch_size auto
 ```