Update README.md

README.md

@@ -40,7 +40,7 @@ messages = [
 ]
 inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
 inputs = inputs.to("cuda")
-generate_ids = model.generate(**inputs, eos_token_id=[151643, 151645], max_new_tokens=256, streamer=streamer)
+generate_ids = model.generate(inputs, streamer=streamer)
 ```
 
 You could also alternatively launch a CLI demo by using the script in [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)