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..91fcb4d
--- /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, an LLM fine-tuned with support learning (RL) to [improve](https://ozoms.com) reasoning ability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on a number of criteria, including MATH-500 and [SWE-bench](https://1.214.207.4410333).<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) model recently [open-sourced](https://hot-chip.com) by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variant of RL. The research team also carried out understanding distillation from DeepSeek-R1 to [open-source Qwen](https://git.on58.com) and Llama models and released several [versions](https://wiki.lafabriquedelalogistique.fr) of each
\ No newline at end of file