aarongifford2/collegestudentjobboard
1
0
Code Issues Projects Wiki

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

Aaron Gifford
2025-05-31 23:01:44 +00:00
parent ba0c0eec04
commit 04e1d1d5d3
1 changed files with 2 additions and 0 deletions
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](https://baripedia.org) with support learning (RL) to [improve thinking](https://movie.nanuly.kr) ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://iamzoyah.com) o1 model on several standards, consisting of MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of experts (MoE) model just recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy [Optimization](https://clik.social) (GRPO), a [reasoning-oriented](https://gitea.cisetech.com) variation of RL. The research study group also carried out understanding distillation from DeepSeek-R1 to [open-source Qwen](http://115.238.142.15820182) and [Llama designs](https://airsofttrader.co.nz) and launched several [versions](http://dcmt.co.kr) of each