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

master
Alison L'Estrange 4 months ago
commit
6bf1c2f851
  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 with [support learning](https://pandatube.de) (RL) to improve reasoning ability. DeepSeek-R1 attains results on par with [OpenAI's](https://git.es-ukrtb.ru) o1 design on numerous standards, [trademarketclassifieds.com](https://trademarketclassifieds.com/user/profile/2672496) including MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of experts (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research team likewise [performed knowledge](https://social.myschoolfriend.ng) distillation from DeepSeek-R1 to open-source Qwen and Llama [designs](https://awaz.cc) and [released](https://bbs.yhmoli.com) several [versions](https://sondezar.com) of each
Loading…
Cancel
Save