Huggingface使用

下载模型：

hf download Qwen/Qwen3-4B-Instruct-2507 --local-dir ./

下载完成后可以用简单的脚本推理:

from transformers import AutoModelForCausalLM, AutoTokenizer

# model_name = "Qwen/Qwen3-4B-Instruct-2507"
model_dir = "/home/xytpai/data/qwen3-4b"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForCausalLM.from_pretrained(
    model_dir,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "世界上最难攀登的山峰是啥？"
messages = [
    {"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)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=16384
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

content = tokenizer.decode(output_ids, skip_special_tokens=True)

print(content)