News for hackers. Stuff that matters.

A comment on DeepSeek-R1. Parent comment

Re:DeepSeek-R1 by roborovskis on Monday January 20, 2025 @10:46AM (#42769815)
Where are you seeing this? On https://github.com/deepseek-ai/DeepSeek-R1/tree/main?tab=rea... I only see the paper and related figures.
[ Parent | on HN ]
Re:DeepSeek-R1 by ozgune on Monday January 20, 2025 @11:17AM (#42770090)
I see it in the "2. Model Summary" section. In the next section, I see links to Hugging Face to download the DeepSeek-R1 Distill Models.

https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-fil...

https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-fil...

[ Parent | on HN ]
Re:DeepSeek-R1 by scribu on Monday January 20, 2025 @11:27AM (#42770205)
The repo contains only the PDF, not actual runnable code for the RL training pipeline.

Publishing a high-level description of the training algorithm is good, but it doesn't count as "open-sourcing", as commonly understood.

[ Parent | on HN ]