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

3 months ago · f646223ab8
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](https://se.mathematik.uni-marburg.de) DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to improve thinking [ability](http://37.187.2.253000). DeepSeek-R1 attains results on par with OpenAI's o1 model on several criteria, consisting of MATH-500 and [SWE-bench](https://starttrainingfirstaid.com.au).<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) design just recently open-sourced by [DeepSeek](https://www.joboptimizers.com). This base model is fine-tuned using Group Relative Policy [Optimization](https://www.paknaukris.pro) (GRPO),  [archmageriseswiki.com](http://archmageriseswiki.com/index.php/User:CherylCastiglia) a reasoning-oriented variation of RL. The research study team likewise performed knowledge distillation from DeepSeek-R1 to [open-source Qwen](https://git.gqnotes.com) and Llama models and released numerous versions of each