Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Hugging Face has announced an upcoming fully open reconstruction of the Deepseek-R1 model, referred to as Open-R1. The project aims to replicate the Deepseek-R1 pipeline and dataset, with a focus on community involvement. Recent updates indicate that evaluation results from Open-R1 closely match Deepseek's benchmarks, although challenges remain in managing responses exceeding 6,000 tokens. The initiative is crucial as building the original Deepseek-R1 from scratch is resource-intensive and costly. Community contributions are being encouraged to facilitate this effort.
Open-R1 Update (2025/02/03) The update of the Open-R1 project, hosted by @huggingface, to reproduce DeepSeek-R1 at the community level, has been shared. ✦︎ Since building DeepSeek-R1 itself from scratch requires a lot of resources and incurs astronomical amounts of $$, the… https://t.co/njHAbMpcsH
Beautiful piece by @huggingface on Open-R1's effort to replicate the DeepSeek-R1 pipeline and dataset. Some of the Key Takeaways - Some of the Evaluation results closely match DeepSeek’s benchmarks, but handling its massive 6,000+ token responses remains a challenge. →… https://t.co/ovUyIPp7xp https://t.co/BuNNro3hnv
Beautiful piece @huggingface of Open-R1 to replicate the DeepSeek-R1 pipeline and dataset Some of the Key Takeaways - Some of the Evaluation results closely match DeepSeek’s benchmarks, but handling its massive 6,000+ token responses remains a challenge. → The training… https://t.co/rRBxfzgwsk https://t.co/BuNNro3hnv
