unslothai/unsloth

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

81
/ 100
Verified

This tool helps AI engineers and researchers efficiently customize large language models (LLMs) and other AI models for specific tasks. You can input various data formats like PDFs, CSVs, and DOCX files to fine-tune models such as GPT-OSS, Llama, or Gemma. The output is a specialized AI model that performs better on your unique data, with significantly faster training and reduced memory use.

53,879 stars. Used by 8 other packages. Actively maintained with 453 commits in the last 30 days. Available on PyPI.

Use this if you need to rapidly train and deploy powerful text, audio, embedding, or vision AI models with limited GPU resources, or if you want a unified interface to manage your model development.

Not ideal if you primarily work with pre-trained models without any need for customization or advanced training techniques.

AI model training natural language processing machine learning engineering deep learning optimization AI research
Maintenance 22 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

53,879

Forks

4,503

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

453

Dependencies

23

Reverse dependents

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/unslothai/unsloth"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.