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

1 week ago · afe72d414a
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 ability. DeepSeek-R1 [attains outcomes](http://dkjournal.co.kr) on par with [OpenAI's](http://39.106.223.11) o1 design on a number of standards, consisting of MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of experts (MoE) design recently [open-sourced](https://git.iws.uni-stuttgart.de) by DeepSeek. This base design is [fine-tuned](https://wiki.airlinemogul.com) using Group Relative Policy [Optimization](http://www.vokipedia.de) (GRPO), a reasoning-oriented variation of RL. The research study group also performed understanding [distillation](https://portalwe.net) from DeepSeek-R1 to [open-source Qwen](https://www.rozgar.site) and Llama designs and launched several variations of each