Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).
moe llama lora embedding liger peft multimodal reranker sft megatron llm internvl deepseek-r1 grpo open-r1 qwen3 llama4 qwen3-vl qwen3-next qwen3-omni
-
Updated
Feb 26, 2026 - Python