chat模型推理有问题

[yawzhe]

使用官方代码推理多轮对话的时候报这个问题

Using sep token, but it is not set yet.Using cls token, but it is not set yet .Using mask token, but it is not set yet.Keyword arguments ['add generation prompt': True] not recognized.

推理代码

from transformers import AutoModelForCausalLM, AutoTokenizer
 
model_path = '01-ai/Yi-34b-Chat'
 
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
 
# Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM.
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()
 
# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]
 
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

[findmyway]

能先确保依赖和我们推荐的是一致的么？