from transformers import AutoTokenizer,AutoModelForCausalLM

model_id_or_path = "p208p2002/chatglm3-6b-chat-template"
tokenizer = AutoTokenizer.from_pretrained(model_id_or_path,trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id_or_path,device_map="auto",trust_remote_code=True)
inputs = tokenizer.apply_chat_template([
    {"role":"system","content":"你是一位樂於助人、尊重他人且誠實的助理。請始終以最有幫助的方式回答問題。如果你對某個問題不知道答案，請不要提供虛假信息。"},
    {"role":"user","content":"如何減緩地球暖化？"}
],add_generation_prompt=True,tokenize=True,return_tensors="pt")

out = model.generate(inputs,max_new_tokens=256)
print(tokenizer.decode(out[0]))