GitHub 项目简介: Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5…
README: SWIFT (Scalable lightWeight Infrastructure for Fine-Tuning)
README: 🍲 **ms-swift** is a large model and multimodal large model fine-tuning and deployment framework provided by the ModelScope community. It now supports training (pre-training, fine-…
Release: Patch release v4.4.2
README: ms-swift supports a rich set of GRPO family algorithms: