GitHub – deepseek-ai/DeepSeek-R1
Paper Link👁️ We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL)…
deepseekaiDeepSeekR1
Paper Link👁️ We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL)…