Use PEFT or Full-parameter to finetune 500+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).
deploy llama lora embedding omni liger peft multimodal sft megatron distill rft llm internvl qwen2-vl qwen2-5 llama3-3 deepseek-r1 grpo open-r1
-
Updated
Mar 28, 2025 - Python