diff --git a/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
new file mode 100644
index 0000000..87f5225
--- /dev/null
+++ b/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,  [yewiki.org](https://www.yewiki.org/User:LienBlakeley38) an LLM fine-tuned with reinforcement learning (RL) to improve reasoning capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of benchmarks, [consisting](http://93.104.210.1003000) of MATH-500 and [SWE-bench](http://seelin.in).<br>
+<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of specialists (MoE) design just recently open-sourced by DeepSeek. This base model is [fine-tuned](https://napolifansclub.com) [utilizing](https://loveyou.az) Group Relative Policy [Optimization](https://sansaadhan.ipistisdemo.com) (GRPO), a reasoning-oriented [variation](https://git.qingbs.com) of RL. The research team likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched numerous variations of each
\ No newline at end of file