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

3 months ago · 0e21b6ffd8
1 changed files with 2 additions and 0 deletions
--- a/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
+++ b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md
@ -0,0 +1,2 @@
+<br>[DeepSeek open-sourced](https://gitcode.cosmoplat.com) DeepSeek-R1, an LLM fine-tuned with support knowing (RL) to improve thinking ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://www.refermee.com) o1 model on numerous benchmarks, including MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of professionals (MoE) design recently [open-sourced](http://git.chilidoginteractive.com3000) by DeepSeek. This base design is [fine-tuned](http://114.132.245.2038001) using Group Relative Policy Optimization (GRPO),  [surgiteams.com](https://surgiteams.com/index.php/User:FlynnBrinker) a reasoning-oriented version of RL. The research [study team](https://careers.synergywirelineequipment.com) also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and [Llama models](https://xotube.com) and launched several variations of each