cornellvalenti/keeloke
1
0
Code Issues Projects Wiki

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

Cornell Valenti 2025-02-16 00:08:41 -06:00
commit 91067b3030
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md Normal file

@ -0,0 +1,2 @@
<br>DeepSeek open-sourced DeepSeek-R1, an [LLM fine-tuned](http://129.151.171.1223000) with [reinforcement](http://xn--ok0b850bc3bx9c.com) learning (RL) to enhance reasoning ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://git.joystreamstats.live) o1 design on several criteria, [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:RusselEdler299) consisting of MATH-500 and [SWE-bench](https://www.srapo.com).<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of experts (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy [Optimization](https://source.futriix.ru) (GRPO), a [reasoning-oriented variant](https://idemnaposao.rs) of RL. The research study group also [performed knowledge](https://www.dynamicjobs.eu) distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [launched](https://www.opentx.cz) several variations of each