lqdev🦫

https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1

Just like most existing LLMs, DeepSeek-R1 generates one token at a time, except it excels at solving math and reasoning problems because it is able to spend more time processing a problem through the process of generating thinking tokens that explain its chain of thought.

DeepSeek R1 Training Recipe

Source: newsletter.languagemodels.co

Send me a message or webmention
Back to feed