unslothai/unsloth — Sponsor Star

52,499 stars | 4,360 forks | Python

Sponsor

      Star









  
    unslothai /

  unsloth  


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

What it does

Unsloth is a powerful tool for fine-tuning and reinforcement learning of large language models (LLMs) like OpenAI's gpt-oss, enabling faster training with reduced memory usage. This innovation is significant for developers and researchers looking to optimize their machine learning workflows.

Why it matters: Unlock the potential of AI with Unsloth - train LLMs faster and smarter with less memory!

View on GitHub

---

Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.