zacherygwin626/howtolo
1
0
Code Issues Projects Wiki

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

Zachery Gwin
2025-02-20 09:17:14 +00:00
commit e24344af76
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 with reinforcement knowing (RL) to enhance thinking capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on a number of criteria, consisting of MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a [mixture](http://vts-maritime.com) of professionals (MoE) model just recently [open-sourced](http://111.231.76.912095) by DeepSeek. This [base design](https://www.imdipet-project.eu) is fine-tuned utilizing Group [Relative Policy](https://git.uucloud.top) [Optimization](http://photorum.eclat-mauve.fr) (GRPO), a reasoning-oriented variation of RL. The research team likewise carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [launched numerous](http://povoq.moe1145) versions of each