google/tunix
A Lightweight LLM Post-Training Library
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
No releases in the last 90 days; the most recent was 143 days ago, with 89 contributors on GitHub.
Gained 21% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides a JAX-native library for efficient post-training of large language models including fine-tuning, reinforcement learning, and knowledge distillation.
- Enables scalable and modular LLM post-training optimized for TPU accelerators with native support for advanced training strategies and model sharding.
- Use for supervised fine-tuning of LLMs with full weights or parameter-efficient LoRA/Q-LoRA methods in JAX-based environments.
- Use for reinforcement learning applications on LLMs using algorithms like PPO, GRPO, and token-level GSPO for policy optimization.
- Use for knowledge distillation to transfer knowledge between teacher and student models via logit matching, attention transfer, and feature projection.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Tunix(Tune-in-JAX) is a JAX based library designed to streamline the post-training of Large Language Models. It provides efficient and scalable supports for:
Tunix leverages the power of JAX for accelerated computation and seamless integration with JAX-based modeling framework Flax NNX.
Tunix is in early development. We're actively working to expand its capabilities, usability and improve its performance. Stay tuned for upcoming updates and new features!
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
381+55
Open issues
517+251
Compared with peers in LLM
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| thedotmack/claude-mem | 113.6K | +8.8K | 35 | today |
| NVIDIA/auto-ontology | 7.5K | +5.6K | 37 | — |
| HKUDS/DeepTutor | 55.5K | +5.5K | 65 | 5 days ago |
| affaan-m/ECC | 297.9K | +5.2K | 63 | 35 days ago |
| DietrichGebert/ponytail | 185.3K | +5.1K | 60 | 7 days ago |
| google/tunix | 2.5K | — | 57 | 143 days ago |
| Category median | 113.6K | +5.5K | 60 | — |
Also by google
Other repositories from this maintainer that GStars tracks
- 54.2K stars
material-design-icons
Material Design icons by Google (Material Symbols)
- Java51.9K stars
guava
Google core libraries for Java
- JavaScript45.8K stars
zx
A tool for writing better scripts
- C++39.7K stars
googletest
GoogleTest - Google Testing and Mocking Framework
- Python39.0K stars
langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Discover Repositories
Search across tracked repositories by name or description