r1-zero

Here are 3 public repositories matching this topic...

Explore the Multimodal “Aha Moment” on 2B Model

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

thompson-sampling alignment reasoning distributed-training ppo dueling-bandits dpo distributed-rl llm online-rl rlhf llm-aligment online-alignment llm-exploration grpo r1-zero

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。

alignment reasoning r1 post-training cot sft o1 24game llm rlhf deepseek r1-zero verl long-cot

Add a description, image, and links to the r1-zero topic page so that developers can more easily learn about it.

To associate your repository with the r1-zero topic, visit your repo's landing page and select "manage topics."