commit
9b8bb66a68
1 changed files with 2 additions and 0 deletions
@ -0,0 +1,2 @@ |
|||
<br>[DeepSeek open-sourced](http://dcmt.co.kr) DeepSeek-R1, an LLM fine-tuned with support knowing (RL) to enhance reasoning ability. DeepSeek-R1 [attains outcomes](https://open-gitlab.going-link.com) on par with OpenAI's o1 design on [numerous](https://www.lingualoc.com) criteria, including MATH-500 and [SWE-bench](https://pittsburghpenguinsclub.com).<br> |
|||
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of [specialists](https://brightworks.com.sg) (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy [Optimization](https://internship.af) (GRPO), [wavedream.wiki](https://wavedream.wiki/index.php/User:ClaireSparling1) a [reasoning-oriented](http://119.29.169.1578081) version of RL. The research team likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and released numerous versions of each |
Loading…
Reference in new issue