一、安装依赖

pip install transformers
pip install torch

二、下载到目录

C:\Users\用户\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B\snapshots\060db6499f32faf8b98477b0a26969ef7d8b9987

测试让它写一下md5加密算法：

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2.5-0.5B"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token_id = tokenizer.eos_token_id

prompt = "write a quick md5 algorithm."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. 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], return_tensors="pt").to(model.device)



generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512,
    pad_token_id=tokenizer.pad_token_id  # 设置 pad_token_id
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)

结果：