wangermeng2021 / llm-webui

A Gradio web UI for Large Language Models. Supports LoRA/QLoRA finetuning,RAG(Retrieval-augmented generation) and Chat

llm-webui

A Gradio web UI for Large Language Models(Finetune, RAG, Chat).

Chat UI

Training UI

visualization UI

RAG(Retrieval-augmented generation) UI

Features

• Finetune:lora/qlora
• RAG(Retrieval-augmented generation):
  • Support txt/pdf/docx
  • Show retrieved chunks
  • Support finetuned model
• Training tracking and visualization
• Config prompt template through UI
• Support online and offline model
• Support online and offline dataset

Install

Clone repo and install requirements.txt in a Python>=3.8.0 environment

git clone https://github.com/wangermeng2021/llm-webui
cd llm-webui
pip install -r requirements.txt

Run

  1. python main.py

  2. Set huggingface hub token

if you want to download Llama-2 from huggingface hub , you need to configure token:"Setting"->"Huggingface Hub Token"