1.hiyouga / LlamaFactoryUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)fine-tuningllamallmpefttransformersrlhf+14 morePythonAPACHE-2.076K total9.3K forks+2,348 starsfrom 73,476 · score 7.76
2.modelscope / ms-swiftUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).llmlorasftmultimodalpeftliger+13 morePythonAPACHE-2.016K total1.8K forks+1,004 starsfrom 15,004 · score 6.91
3.huggingface / peft🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.adapterdiffusionllmparameter-efficient-learningpythonpytorch+4 morePythonAPACHE-2.022K total2.6K forks+430 starsfrom 21,435 · score 6.07