#140 · Primary category： MLOps & Evaluation
GongBU
Paper accepted by CIKM 2024. Codes of GongBU, a LLM fine-tuning platform for domain-specific adaptation.
Project last updated：01/22/26
GitHub Stars
1.2K
Forks
90
Contributors
3
License
MIT
Why we included this project
GongBU gives teams a way to fine-tune an open model on their own domain data without anyone writing training code. The whole flow runs in a web browser: import datasets, pull a base model, tune it with Transformers and Peft underneath, check the results, and ship the adapted model, all on your own hardware rather than a hosted API. Because the UI hides the plumbing, people outside the ML team can drive the process, which suits small groups with no spare engineering time. The documented install path is docker-compose on Linux with nvidia-docker, and the design comes from a CIKM 2024 paper, a reasonable sign that the fine-tuning pipeline was built with care. One thing to know before exposing it beyond a trusted network: client and server talk in plain text, so plan to enable SSL.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
airflow
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
langfuse
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
netron
Visualizer for neural network, deep learning and machine learning models