lm-sys/FastChat

[Feature] Do you have plan to support multimodal mode?

Open

#2,216 创建于 2023年8月14日

在 GitHub 查看
 (1 评论) (1 反应) (0 负责人)Python (38,959 star) (4,736 fork)batch import
good first issue

描述

On UI, basically just add an upload image button in the chat box. On backend side, need to integrate with multimodal models, e.g. LLaVa, MiniGPT4.

贡献者指南

技术栈
python
领域
full stackaibackend
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
PythonLLM basicsFrontend developmentMultimodal models
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
20
研究方向
Start by examining the existing frontend code in the FastChat repository to understand how the chat interface is built and where an upload button could be added. On the backend, review how current models are integrated and how multimodal models like LLaVa or MiniGPT4 can be loaded and used. Look for any existing issues or PRs related to multimodal support for additional context.