Pinned Loading

1. unslothai/unsloth unslothai/unsloth Public

   Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.

   Python 44k 3.6k

2. trl trl Public

   Forked from huggingface/trl

   Train transformer language models with reinforcement learning.

   Python

3. EarthLiveSharp EarthLiveSharp Public

   EarthLiveSharp 的python脚本,可以在ubuntu和mac上运行

   Python 37 10