# 升级pip
python -m pip install --upgrade pip

# 更换 pypi 源加速库的安装
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
pip install fastapi==0.111.1
pip install uvicorn==0.30.3
pip install modelscope==1.16.1
pip install transformers==4.42.4
pip install accelerate==0.32.1

• 1.
• 2.
• 3.
• 4.
• 5.
• 6.
• 7.
• 8.
• 9.
• 10.

import torch
from modelscope import snapshot_download, AutoModel, AutoTokenizer
import os
model_dir = snapshot_download('LLM-Research/Meta-Llama-3.1-8B-Instruct', cache_dir='/root/autodl-tmp', revision='master')

• 1.
• 2.
• 3.
• 4.

# 导入所需的库
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
# 加载预训练的分词器和模型
model_name_or_path = '/root/autodl-tmp/LLM-Research/Meta-Llama-3___1-8B-Instruct'
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", torch_dtype=torch.bfloat16)
# 定义对话消息列表，包含系统角色和用户角色的消息
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who are you?"}
]
# 使用分词器将对话消息转换为模型输入格式
input_ids = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
# 将输入转换为PyTorch张量并移动到GPU设备上
model_inputs = tokenizer([input_ids], return_tensors="pt").to('cuda')
# 使用模型生成回复
generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
# 从生成的ID中提取回复部分
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
# 使用分词器将生成的ID解码为文本
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

• 1.
• 2.
• 3.
• 4.
• 5.
• 6.
• 7.
• 8.
• 9.
• 10.
• 11.
• 12.
• 13.
• 14.
• 15.
• 16.
• 17.
• 18.
• 19.
• 20.
• 21.
• 22.
• 23.
• 24.

response

• 1.

"I'm an artificial intelligence model designed to assist and communicate with users in a helpful and informative way. I'm a type of chatbot, and my primary function is to provide information, answer questions, and engage in conversation to the best of my abilities.\n\nI don't have a personal identity or emotions, but I'm here to help you with any questions or topics you'd like to discuss. I can provide information on a wide range of subjects, from science and history to entertainment and culture. I can also help with tasks such as language translation, text summarization, and even creative writing.\n\nHow can I assist you today?"

• 1.

# 定义对话消息列表，包含系统角色和用户角色的消息
messages = [
{"role": "user", "content": "你会讲中文么?"}
]
# 使用分词器将对话消息转换为模型输入格式
input_ids = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
# 将输入转换为PyTorch张量并移动到GPU设备上
model_inputs = tokenizer([input_ids], return_tensors="pt").to('cuda')
# 使用模型生成回复
generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
# 从生成的ID中提取回复部分
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
# 使用分词器将生成的ID解码为文本
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
response

• 1.
• 2.
• 3.
• 4.
• 5.
• 6.
• 7.
• 8.
• 9.
• 10.
• 11.
• 12.
• 13.
• 14.
• 15.
• 16.
• 17.

# 定义对话消息列表，包含系统角色和用户角色的消息
messages = [
{"role": "user", "content": "请以“夜晚”为题写一首诗"}
]
# 使用分词器将对话消息转换为模型输入格式
input_ids = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
# 将输入转换为PyTorch张量并移动到GPU设备上
model_inputs = tokenizer([input_ids], return_tensors="pt").to('cuda')
# 使用模型生成回复
generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
# 从生成的ID中提取回复部分
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
# 使用分词器将生成的ID解码为文本
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
response

• 1.
• 2.
• 3.
• 4.
• 5.
• 6.
• 7.
• 8.
• 9.
• 10.
• 11.
• 12.
• 13.
• 14.
• 15.
• 16.
• 17.

File ~/miniconda3/lib/python3.10/site-packages/transformers/models/llama/configuration_llama.py:182, in LlamaConfig._rope_scaling_validation(self)    179     return    181 if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:--> 182     raise ValueError(    183         "`rope_scaling` must be a dictionary with two fields, `type` and `factor`, " f"got {self.rope_scaling}"    184     )    185 rope_scaling_type = self.rope_scaling.get("type", None)    186 rope_scaling_factor = self.rope_scaling.get("factor", None)
ValueError: `rope_scaling` must be a dictionary with two fields, `type` and `factor`, got {'factor': 8.0, 'low_freq_factor': 1.0, 'high_freq_factor': 4.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}

• 1.
• 2.

pip install --upgrade transformers

• 1.