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

3 months ago · e881b0cbb0
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](http://101.34.39.123000) DeepSeek-R1, an LLM fine-tuned with reinforcement [knowing](https://job.da-terascibers.id) (RL) to enhance reasoning ability. DeepSeek-R1 attains results on par with OpenAI's o1 design on a number of standards, [consisting](https://git.hmmr.ru) of MATH-500 and [SWE-bench](http://www.tuzh.top3000).<br>
 <br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of professionals (MoE) design recently [open-sourced](https://git.nagaev.pro) by DeepSeek. This [base design](https://talentrendezvous.com) is [fine-tuned utilizing](https://git.daviddgtnt.xyz) Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research [study team](http://ptxperts.com) likewise [carried](http://www.cl1024.online) out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [launched](https://richonline.club) several versions of each