apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(device) generated_ids = model.generate( **model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids...
prompt="Give me a short introduction to large language model."messages=[ {"role":"system","content":"You are a helpful assistant."}, {"role":"user","content":prompt} ]text=tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True)model_inputs=tokenizer([text],...