finlaydaecher/friendify
1
0
Code Issues Projects Wiki

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

Finlay Daecher 2025-04-08 10:00:55 +00:00
commit 40432346fe
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 with support knowing (RL) to [improve](https://git.the.mk) reasoning capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://profesional.id) o1 model on numerous standards, [wiki.snooze-hotelsoftware.de](https://wiki.snooze-hotelsoftware.de/index.php?title=Benutzer:BrandyVail1) including MATH-500 and [SWE-bench](http://154.64.253.773000).<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) model just recently open-sourced by DeepSeek. This base design is [fine-tuned](https://volunteering.ishayoga.eu) utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research study team likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and released numerous variations of each