hugging face地址
注意：注册hugging face时选择国籍请选择美国，不要选择中国，否则获取模型时不会被审核通过！

方法一：

在Models模型搜索Meta-Llama-3.1-8B-Instruct并点击“Use this model"，将代码粘贴到本地运行

# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B-Instruct")
pipe(messages)

使用该方法可能会报以下错误：

Cannot access gated repo for url xxx
Access to model meta-llama/Meta-llama-3.1-8B-Instruct is restricted. You must be authenticated to access it.

方法二

1、在设置里面创建access token并保存获取的令牌（注意勾选读写权限）

2、在Models模块搜索Meta-Llama-3.1-8B-Instruct并使用git命令下载该模型

git clone https://huggingface-user-name:ACCESS_TOKEN@huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct

3、运行llama3.1模型

import transformers
import torch

model_id = "D:\\model\\Meta-Llama-3.1-8B-Instruct"

pipeline = transformers.pipeline(
	"text-generation",
	model=model_id,
	model_kwargs={"torch_dtype": torch.bfloat16},
	device_map="auto",
}

messages = [
	{"role": "user", "content": "Who are you?"},
]

outputs = pipeline(
	messages,
	max_new_token=256,
)
print(outputs[0]["generated_text][-1])