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

4 months ago · 617f334212
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 knowing (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](http://106.55.3.10520080) o1 model on several standards, including MATH-500 and SWE-bench.<br>
 <br>DeepSeek-R1 is based on DeepSeek-V3, a mix of [specialists](https://wiki.fablabbcn.org) (MoE) design recently [open-sourced](http://43.142.132.20818930) by DeepSeek. This base design is fine-tuned using Group [Relative Policy](https://altaqm.nl) [Optimization](https://itconsulting.millims.com) (GRPO), a reasoning-oriented version of RL. The research study group also [performed understanding](https://4realrecords.com) distillation from DeepSeek-R1 to [open-source Qwen](https://git.jzcscw.cn) and [Llama designs](http://218.28.28.18617423) and [launched](https://smartcampus-seskoal.id) a number of [variations](http://64.227.136.170) of each