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, an [LLM fine-tuned](https://teba.timbaktuu.com) with [support knowing](https://git.arcbjorn.com) (RL) to improve reasoning capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://vezonne.com) o1 design on several criteria, including MATH-500 and [SWE-bench](https://git.goolink.org).<br>
+<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of specialists (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO),  [larsaluarna.se](http://www.larsaluarna.se/index.php/User:OdellMcLaughlin) a [reasoning-oriented](https://theneverendingstory.net) version of RL. The research team also carried out [knowledge distillation](https://teba.timbaktuu.com) from DeepSeek-R1 to open-source Qwen and Llama designs and launched a number of versions of each