<br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to [enhance thinking](http://svn.ouj.com) capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 model on a number of standards, [engel-und-waisen.de](http://www.engel-und-waisen.de/index.php/Benutzer:MadonnaBrunner) including MATH-500 and [SWE-bench](http://www.lucaiori.it).<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of [specialists](https://git.spitkov.hu) (MoE) model just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy [Optimization](https://jobspage.ca) (GRPO), a version of RL. The research group likewise performed understanding distillation from DeepSeek-R1 to open-source Qwen and Llama models and launched a number of versions of each
