Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model'

2 months ago · 138e6db447
1 changed files with 2 additions and 0 deletions
--- 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
@ -0,0 +1,2 @@
+<br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to [improve](http://ncdsource.kanghehealth.com) reasoning capability. DeepSeek-R1 [attains outcomes](https://ramique.kr) on par with OpenAI's o1 design on numerous criteria,  [wiki.vst.hs-furtwangen.de](https://wiki.vst.hs-furtwangen.de/wiki/User:MichaelCrocker0) including MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of professionals (MoE) model just recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented variant](https://matchpet.es) of RL. The research study team likewise carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and [released](http://59.57.4.663000) numerous versions of each