commit c824ec4ff0ab180a2f01f8587893472426386ff3 Author: ufjdarwin95127 Date: Sat Apr 5 20:24:38 2025 +0800 Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model' 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..6776ce6 --- /dev/null +++ b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md @@ -0,0 +1,2 @@ +
DeepSeek open-sourced DeepSeek-R1, an LLM [fine-tuned](http://88.198.122.2553001) with reinforcement knowing (RL) to enhance thinking [ability](http://47.75.109.82). DeepSeek-R1 attains outcomes on par with o1 model on [numerous](https://thathwamasijobs.com) criteria, consisting of MATH-500 and SWE-bench.
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of [professionals](http://git.bplt.ru) (MoE) design just recently open-sourced by DeepSeek. This [base design](http://git.bplt.ru) is fine-tuned using Group [Relative Policy](http://1.12.246.183000) [Optimization](https://social.updum.com) (GRPO), a [reasoning-oriented variant](https://pompeo.com) of RL. The research study team also performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and released a number of versions of each \ No newline at end of file