The DeepSeek-R1 repository contains the implementation and models for DeepSeek's first-generation reasoning models, specifically DeepSeek-R1-Zero and DeepSeek-R1, along with six distilled variants. These models represent a significant advancement in large language model reasoning capabilities, trained using large-scale reinforcement learning applied directly to base models without requiring supervised fine-tuning as a preliminary step. DeepSeek-R1-Zero demonstrates that reasoning capabilities can emerge purely through RL optimization, marking what the repository describes as the first open research validating this approach. The full DeepSeek-R1 model incorporates cold-start data before RL training and achieves performance comparable to OpenAI-o1 across mathematics, code, and reasoning tasks.

The repository's technical approach involves a multi-stage pipeline combining two RL stages designed to discover improved reasoning patterns and align with human preferences, followed by two SFT stages that seed the model's reasoning and non-reasoning capabilities. DeepSeek-R1-Zero and DeepSeek-R1 are both built on the DeepSeek-V3-Base architecture, featuring 671 billion total parameters with 37 billion activated parameters and a 128K token context length. The models naturally develop reasoning behaviors including self-verification, reflection, and generation of extended chain-of-thought reasoning, though DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing that the full DeepSeek-R1 addresses.

A key contribution is the distillation of reasoning patterns into smaller models, with six open-sourced distilled checkpoints ranging from 1.5B to 70B parameters based on Qwen2.5 and Llama3 series architectures. DeepSeek-R1-Distill-Qwen-32B notably outperforms OpenAI-o1-mini across various benchmarks, achieving state-of-the-art results for dense models. The repository demonstrates that smaller models can effectively learn reasoning patterns from larger models, enabling practical deployment of advanced reasoning capabilities.

Evaluation results show DeepSeek-R1 achieving strong performance across multiple benchmark categories. On English benchmarks, it scores 90.8 on MMLU, 84.0 on MMLU-Pro, and 92.2 on DROP. For code tasks, it achieves 65.9 pass@1 on LiveCodeBench and 96.3 percentile on Codeforces. On mathematics benchmarks, DeepSeek-R1 reaches 79.8 on AIME 2024 and 97.3 on MATH-500. Chinese language performance includes 92.8 on CLUEWSC and 91.8 on C-Eval.

The repository is actively maintained with significant community engagement. GitGenius tracking shows 588 total issues and pull requests with a median response latency of 8.7 hours, though mean latency reaches 270 hours indicating some longer-running discussions. The most active contributor tracked is mowentian with 134 events, followed by LinUser-000 and MinecraftEarthVillage with 28 events each. The repository uses stale issue management extensively, with 378 stale labels and 362 closed-as-stale items tracked. The codebase shares contributors with major projects including Microsoft's VSCode and TypeScript repositories, as well as the Rust language project, indicating cross-pollination with significant open-source ecosystems. The repository is released under the MIT license and provides access to models through Hugging Face, with a detailed technical paper available for reference.