commit 07c28f18c14694c03d7010662396d7aafc36a868 Author: ihvtrisha79363 Date: Sat Feb 15 03:47:25 2025 +0000 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..b519f95 --- /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 with support learning (RL) to [improve reasoning](http://www.mouneyrac.com) ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](http://personal-view.com) o1 design on numerous criteria, [engel-und-waisen.de](http://www.engel-und-waisen.de/index.php/Benutzer:FranklinBreillat) consisting of MATH-500 and [setiathome.berkeley.edu](https://setiathome.berkeley.edu/view_profile.php?userid=11860868) SWE-bench.
+
DeepSeek-R1 is based upon DeepSeek-V3, a mix of specialists (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy [Optimization](https://hcp.com.gt) (GRPO), a reasoning-oriented variation of RL. The research study team likewise [performed](http://175.24.174.1733000) understanding distillation from DeepSeek-R1 to open-source Qwen and [Llama models](http://8.136.199.333000) and launched several versions of each \ No newline at end of file