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..9d447f9
--- /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](http://gnu5.hisystem.com.ar) DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://say.la) o1 model on a number of benchmarks, including MATH-500 and [SWE-bench](https://coopervigrj.com.br).<br>
+<br>DeepSeek-R1 is based upon DeepSeek-V3, a [mixture](https://www.flughafen-jobs.com) of [specialists](https://drapia.org) (MoE) design just recently open-sourced by DeepSeek. This base model is [fine-tuned](http://123.206.9.273000) using Group Relative Policy Optimization (GRPO), a [reasoning-oriented](http://43.142.132.20818930) version of RL. The research team also carried out [knowledge distillation](https://www.joboptimizers.com) from DeepSeek-R1 to open-source Qwen and Llama models and launched numerous variations of each
\ No newline at end of file