# Bolin97/GongBU

Paper accepted by CIKM 2024. Codes of GongBU, a LLM fine-tuning platform for domain-specific adaptation.

Repository: https://github.com/Bolin97/GongBU
Canonical: https://ross.abutalabs.com/products/gongbu
Language: Svelte
License: MIT
License Family: permissive
Last push: 2026-01-22T10:29:06+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 35, longevity 59
- inputs: {"age_days": 832, "days_push": 223, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1225, forks 90 (observed 2026-08-28T04:04:02.949536+00:00)

## What it is
GongBU is a self-hosted, no-code web platform for fine-tuning, evaluating, and deploying large language models, built on Transformers and PEFT. It is deployed via docker-compose on Linux with NVIDIA GPUs and accessed through a browser by non-technical users.

## Use cases
- fine-tune an LLM on my own domain data without writing code
- run a local no-code LLM fine-tuning platform on my GPU server
- let non-technical teammates fine-tune models through a web UI
- evaluate and deploy fine-tuned language models
- adapt a base LLM to a specific domain with PEFT/LoRA
- manage datasets and models for LLM training in one place

## When to choose
- you want browser-based, no-code LLM fine-tuning on your own hardware
- you have a Linux machine with NVIDIA GPUs and can use docker-compose
- your users are non-technical and need a guided UI for training and evaluation

## When to avoid
- you need managed cloud training infrastructure
- you only need inference/serving without fine-tuning
- you cannot use Docker or lack NVIDIA GPU resources
- you need a lightweight scriptable training pipeline rather than a full platform

## Facets
- artifact type: application
- maturity: active
- function: llm-training, machine-learning, web-framework, self-hosted
- domain: large-language-models, machine-learning, artificial-intelligence, self-hosted
- platform: self-hosted
- tags: no-code, fine-tuning, llm, peft, transformers, web-ui, svelte, docker-compose, linux, docker, web-server, gpu

## Member repositories
- Bolin97/GongBU (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.949536+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:21.747318+00:00, confidence not recorded.
  - readme: https://github.com/Bolin97/GongBU (fetched 2026-08-28T04:04:02.949536+00:00, sha 56f4a49e3185)
- Data as of 2026-08-30T08:39:29.467469+00:00.