Pinned Loading

1. modelscope/ms-swift modelscope/ms-swift Public

   Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…

   Python 13.4k 1.3k

2. Triton_Kernels- Triton_Kernels- Public

   Kernels Triton

   Jupyter Notebook 1

3. RL-MAX RL-MAX Public

   Decoupled rl enviornment training with zero2 and hot reload of weights with vllm

   Python 4