魔搭大模型训练推理部署工具箱，支持LLaMA、千问、ChatGLM、BaiChuan等多种模型及LoRA等多种训练方式

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, GLM4.5v, Gemma4, Llava, ...