DeepSeek-R1
DeepSeek-R1 Paper Link 👁️ 1. Introduction We introduce our first-generation
About this project
DeepSeek-R1 Paper Link 👁️ 1. Introduction 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) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates…
Project health
GitHub
Reviews
Built by
Maintain deepseek-ai/DeepSeek-R1? Claiming verifies admin access through your GitHub account and gives you control of this listing.
