open-r1

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, InternVL3, Ovis2.5, Llava, GLM4v, Phi4, ...) (AAAI 2025).

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

R1V, trained with AI feedback, answers open-ended visual questions.

xVerify: Efficient Answer Verifier for Large Language Model Evaluations