model = FastLanguageModel.for_inference(model)messages = [    {"from": "human", "value": "Is 9.11 larger than 9.9?"},]inputs = tokenizer.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    return_tensors="pt",).to("cuda")text_streamer = TextStreamer(tokenizer)_ = model.generate(input_ids=inputs, streamer=text_streamer, max_new_tokens=128, use_cache=True)