Open source fine-tuning projects

Every project in the registry tagged fine-tuning, ranked by real GitHub adoption.

projects 6 combined stars ★ 96K refresh nightly
01 llama_index ★ 52K

LlamaIndex is the document processing platform for AI

last push4 hours ago languagePython licenseMIT
02 CosyVoice ★ 24K

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

last push4 months ago languagePython licenseApache-2.0
03 OpenLLM ★ 13K

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

last push3 days ago languagePython licenseApache-2.0
04 lorax ★ 3.8K

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

last push4 months ago languagePython licenseApache-2.0
05 dstack ★ 2.3K

GPU orchestration across clouds, Kubernetes, and on-prem

last push10 hours ago languagePython licenseMPL-2.0
06 Beam ★ 1.8K

Serverless GPU compute with sub-second cold starts

last push27 hours ago languageGo licenseAGPL-3.0

Related tags

← all tags

Frequently asked questions

How many open source fine-tuning projects are there?

This registry tracks 6 projects tagged fine-tuning, with 96,262 GitHub stars between them. The most-adopted is llama_index at 52,202 stars.

Are these fine-tuning projects free to use?

Yes — 6 of the 6 carry an explicit open-source licence across 4 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.

Which fine-tuning project should I choose?

The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.

Are these fine-tuning projects still maintained?

4 of the 6 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.