24-Game-Reasoning
24-Game-Reasoning copied to clipboard
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。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1
Results
0
24-Game-Reasoning issues
Sort by
recently updated
recently updated
newest added