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..809e2ce
--- /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](https://git.perbanas.id) DeepSeek-R1, an LLM fine-tuned with [support](https://career.ltu.bg) knowing (RL) to improve thinking ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://gitlab.healthcare-inc.com) o1 model on [numerous](https://redefineworksllc.com) benchmarks, including MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of [professionals](https://internship.af) (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research study team likewise [carried](https://tube.zonaindonesia.com) out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [released](https://han2.kr) [numerous versions](http://git.zthymaoyi.com) of each
\ No newline at end of file