Update README.md

README.md

@@ -39,14 +39,13 @@ model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, d
 messages = [
     {"role": "user", "content": "推荐5个北京的景点。"},
 ]
-model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
+model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(device)
 
 model_outputs = model.generate(
     model_inputs,
     max_new_tokens=1024,
     top_p=0.7,
-    temperature=0.7,
-    repetition_penalty=1.02
+    temperature=0.7
 )
 
 output_token_ids = [