Meta Llama 3本地部署

感谢阅读

环境安装

项目文件

下载完后在根目录进入命令终端(windows下cmd、linux下终端、conda的话activate)

运行

python 复制代码
pip install -e .

不要控制台,因为还要下载模型。这里挂着是节省时间

模型申请链接

复制如图所示的链接

然后在刚才的控制台

python 复制代码
bash download.sh

在验证哪里直接输入刚才链接即可

如果报错没有wget,则点我下载wget

然后放到C:\Windows\System32 下

python 复制代码
torchrun --nproc_per_node 1 example_chat_completion.py \
    --ckpt_dir Meta-Llama-3-8B-Instruct/ \
    --tokenizer_path Meta-Llama-3-8B-Instruct/tokenizer.model \
    --max_seq_len 512 --max_batch_size 6

收尾

创建chat.py脚本

python 复制代码
# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed in accordance with the terms of the Llama 3 Community License Agreement.

from typing import List, Optional

import fire

from llama import Dialog, Llama


def main(
    ckpt_dir: str,
    tokenizer_path: str,
    temperature: float = 0.6,
    top_p: float = 0.9,
    max_seq_len: int = 512,
    max_batch_size: int = 4,
    max_gen_len: Optional[int] = None,
):
    """
    Examples to run with the models finetuned for chat. Prompts correspond of chat
    turns between the user and assistant with the final one always being the user.

    An optional system prompt at the beginning to control how the model should respond
    is also supported.

    The context window of llama3 models is 8192 tokens, so `max_seq_len` needs to be <= 8192.

    `max_gen_len` is optional because finetuned models are able to stop generations naturally.
    """
    generator = Llama.build(
        ckpt_dir=ckpt_dir,
        tokenizer_path=tokenizer_path,
        max_seq_len=max_seq_len,
        max_batch_size=max_batch_size,
    )

    # Modify the dialogs list to only include user inputs
    dialogs: List[Dialog] = [
        [{"role": "user", "content": ""}],  # Initialize with an empty user input
    ]

    # Start the conversation loop
    while True:
        # Get user input
        user_input = input("You: ")
        
        # Exit loop if user inputs 'exit'
        if user_input.lower() == 'exit':
            break
        
        # Append user input to the dialogs list
        dialogs[0][0]["content"] = user_input

        # Use the generator to get model response
        result = generator.chat_completion(
            dialogs,
            max_gen_len=max_gen_len,
            temperature=temperature,
            top_p=top_p,
        )[0]

        # Print model response
        print(f"Model: {result['generation']['content']}")

if __name__ == "__main__":
    fire.Fire(main)

然后运行

python 复制代码
torchrun --nproc_per_node 1 chat.py     --ckpt_dir Meta-Llama-3-8B-Instruct/     --tokenizer_path Meta-Llama-3-8B-Instruct/tokenizer.model     --max_seq_len 512 --max_batch_size 6
相关推荐
blackoon884 小时前
DeepSeek R1大模型微调实战-llama-factory的模型下载与训练
llama
johnny2334 小时前
大模型微调理论、实战:LLaMA-Factory、Unsloth
llama
闲看云起8 小时前
从 GPT 到 LLaMA:解密 LLM 的核心架构——Decoder-Only 模型
gpt·架构·llama
小草cys2 天前
在树莓派集群上部署 Distributed Llama (Qwen 3 14B) 详细指南
python·llama·树莓派·qwen
咕咚-萌西2 天前
联邦学习论文分享:Towards Building the Federated GPT:Federated Instruction Tuning
llama·联邦学习·指令微调
relis3 天前
解密llama.cpp中的batch与ubatch:深度学习推理优化的内存艺术
深度学习·batch·llama
relis3 天前
解密llama.cpp:Prompt Processing如何实现高效推理?
prompt·llama
GEO_JYB4 天前
BERT家族进化史:从BERT到LLaMA,每一次飞跃都源于对“学习”的更深理解
学习·bert·llama
AI大模型5 天前
大模型开发实战:使用 LLaMA Factory 微调与量化模型并部署至 Ollama
程序员·llm·llama
relis5 天前
解密llama.cpp:从Prompt到Response的完整技术流程剖析
prompt·llama