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

master
Tahlia Pirkle 2 months ago
commit
ed048776d8
  1. 2
      DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md

2
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](https://social.ishare.la) with support [learning](https://gitea.sitelease.ca3000) (RL) to improve thinking ability. DeepSeek-R1 attains results on par with [OpenAI's](http://orcz.com) o1 design on a number of benchmarks, consisting of MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of [specialists](http://139.9.50.1633000) (MoE) model recently open-sourced by [DeepSeek](https://gitlab.appgdev.co.kr). This [base design](http://101.132.100.8) is fine-tuned using Group Relative Policy Optimization (GRPO), [wavedream.wiki](https://wavedream.wiki/index.php/User:RobertoPark2) a reasoning-oriented variant of RL. The research team likewise carried out understanding distillation from DeepSeek-R1 to [open-source Qwen](https://gemma.mysocialuniverse.com) and Llama models and released several versions of each
Loading…
Cancel
Save