Update Qwen2-7B_inference.py

inference_vllm/Qwen2-7B_inference.py

@@ -11,7 +11,7 @@ prompts = [
 sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 
 # Create an LLM.
-llm = LLM(model="/data/model/Qwen2-0.5B-Instruct/",trust_remote_code=True, dtype="float16", enforce_eager=True)
+llm = LLM(model="/data/model/Qwen2-7B-Instruct/",trust_remote_code=True, dtype="float16", enforce_eager=True)
 # Generate texts from the prompts. The output is a list of RequestOutput objects
 # that contain the prompt, generated text, and other information.
 outputs = llm.generate(prompts, sampling_params)