From the source
Open-R1 project provides a one-week update on reproducing DeepSeek-R1's training pipeline and synthetic data, including evaluation results on MATH-500, integration of GRPO into TRL, and efforts to scale synthetic data generation.
Open-R1: Update #1
From the source
It’s been two weeks since the release of DeepSeek R1 and just a week since we started the open-r1 project to replicate the missing pieces, namely the training pipeline and the synthetic data.
huggingface.co
