Hugging Face· PlatformResearch paper

Open-R1: a fully open reproduction of DeepSeek-R1

Hugging Face launches the Open-R1 project to systematically reconstruct DeepSeek-R1's data and training pipeline, aiming to provide transparency on how reinforcement learning can enhance reasoning and share reproducible insights with the open-source community.

From the source

These questions prompted us to launch the Open-R1 project, an initiative to systematically reconstruct DeepSeek-R1’s data and training pipeline, validate its claims, and push the boundaries of open reasoning models.

huggingface.co

Announced

28 Jan 2025 00:00 UTC

Detected

03 Aug 2026 21:12 UTC (+552d after)