from modelscope import snapshot_download
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig

model_dir = snapshot_download("qwen/Qwen-1_8B-Chat")

tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_dir, device_map="auto", trust_remote_code=True
).eval()


# 可指定不同的生成长度、top_p等相关超参
model.generation_config = GenerationConfig.from_pretrained(
    model_dir, trust_remote_code=True
)

# 第一轮对话
response, history = model.chat(tokenizer, "你好", history=None)
print(response)
# 你好！很高兴为你提供帮助。

# 第二轮对话
response, history = model.chat(tokenizer, "给我讲一个年轻人奋斗创业最终取得成功的故事。", history=history)
print(response)