project-baize/baize-chatbot

How project-baize/baize-chatbot works

Baize’s repository supports a model-building workflow: collect self-chat dialogs from question datasets, preprocess them into training JSON, fine-tune a LoRA adapter, and optionally merge that adapter into a standalone model. A separate Gradio demo serves chat using a base model and optional adapter. The graph preserves both collection versions and the released dialog datasets. Demo internals are represented at the app entry point because its source was not sampled; links based on documented behavior cite the README.

Main entry points: merge_lora.py Adapter merger · app.py Gradio chat demo · collect.py Self-chat v1 · collect_v2.py Self-chat v2

Components 17

Dialog data

Question datasets
Self-chat v1 collect.py
Self-chat v2 collect_v2.py
Collected dialogs
Dialog formatter preprocess.py
Released dialogs data

Model training

Training inputs data
LoRA fine-tuning finetune.py
LLaMA base model

Model release

LoRA adapter
Adapter merger merge_lora.py
Merged model

Chat demo

Hugging Face hub
Gradio chat demo demo/app.py
Loaded chat model demo/app.py

Other components

Project operator
Chat user

Connections 20

Project operator → Self-chat v1: starts collection README.md
Project operator → Self-chat v2: starts collection README.md
Self-chat v1 → Question datasets: loads questions collect.py
Self-chat v2 → Question datasets: loads questions collect_v2.py
Self-chat v1 → Collected dialogs: writes dialogs collect.py
Self-chat v2 → Collected dialogs: writes dialogs collect_v2.py
Collected dialogs → Dialog formatter: reads dialogs preprocess.py
Dialog formatter → Released dialogs: writes JSON preprocess.py
Released dialogs → Training inputs: provides examples
Project operator → LoRA fine-tuning: starts training README.md
LoRA fine-tuning → LLaMA base model: loads weights finetune.py
LoRA fine-tuning → LoRA adapter: saves adapter finetune.py
Project operator → Adapter merger: runs merge README.md
Adapter merger → LLaMA base model: loads weights merge_lora.py
Adapter merger → LoRA adapter: loads adapter merge_lora.py
Adapter merger → Merged model: saves model merge_lora.py
Chat user → Gradio chat demo: submits chat README.md
Hugging Face hub → Gradio chat demo: provides weights README.md
Gradio chat demo → Loaded chat model: runs inference README.md
Loaded chat model → Gradio chat demo: returns response README.md

Drawn by GitDiagram on November 14, 2026 from the repository's file tree, README and source files. Read as Markdown ·