大模型笔记之-llava（多模态大语言模型）

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

---

前言

LLaVA：大型语言和视觉助手
针对具有 GPT-4 级功能的大型语言和视觉模型进行视觉教学调整。

一、安装

git clone https://github.com/haotian-liu/LLaVA.git
cd LLaVA

#必须升级pip 至24.0版本否则在构建时会报错
#ERROR: Project file:///home/user/netdisk/data/llava/LLaVA-main has a 'pyproject.toml' and its build backend is missing the 'build_editable' hook. Since it does not have a 'setup.py' nor a 'setup.cfg', it cannot be installed in editable mode. Consider using a build backend that supports PEP 660.

pip install --upgrade pip   # enable PEP 660 support
pip install -e .

二、启动

python3 -m llava.serve.controller --host 0.0.0.0 --port 4006

python3 -m llava.serve.gradio_web_server --controller http://localhost:4006 --model-list-mode reload --share

python3 -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:4006 --port 8000 --worker http://localhost:8000 --model-path ./models/llava-v1.5-7b

启动报错

2024-03-19 13:29:27 | ERROR | stderr | installation page of its repo: https://github.com/protocolbuffers/protobuf/tree/master/python#installation and follow the ones
2024-03-19 13:29:27 | ERROR | stderr | that match your environment. Please note that you may need to restart your runtime after installation.
2024-03-19 13:29:27 | ERROR | stderr | 

解决

pip install protobuf

再次启动 默认页面

写在最后

欢迎移步我的Github仓库，https://github.com/Jun-Howie/erniebot-openai-api
本仓库使用飞桨星河社区接入ernie-4.0联网功能，如果你需要可以Fork我的仓库，还请给个Star让我知道