1 result found Sort:

modelscope
ms-swift modelscope
588
6.9k
apache-2.0
35
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen2.5, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL2.5,...
llm rft sft grpo lora omni peft liger llama deploy llama4 distill open-r1 qwen2-5 internvl megatron qwen2-vl embedding multimodal deepseek-r1
Created 2023-08-01
1,735 commits to main branch, last one 16 hours ago