Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model'

DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

@@ -0,0 +1,2 @@
+<br>DeepSeek open-sourced DeepSeek-R1,  [genbecle.com](https://www.genbecle.com/index.php?title=Utilisateur:LouiseDoyle2) an LLM fine-tuned with reinforcement learning (RL) to improve reasoning capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on several criteria, [including](http://103.77.166.1983000) MATH-500 and [SWE-bench](https://photohub.b-social.co.uk).<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of professionals (MoE) design recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO), a [reasoning-oriented variation](https://www.empireofember.com) of RL. The research study group likewise [performed knowledge](http://xn--ok0b74gbuofpaf7p.com) [distillation](https://aws-poc.xpresso.ai) from DeepSeek-R1 to open-source Qwen and Llama models and released a number of versions of each