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

Donny Harpster 2025-02-06 17:13:25 -06:00
parent 3f223ab7b4
commit 60002e36f3

@ -0,0 +1,2 @@
<br>[DeepSeek open-sourced](https://www.laciotatentreprendre.fr) DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to enhance reasoning ability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on numerous standards, including MATH-500 and SWE-bench.<br>
<br>DeepSeek-R1 is based on DeepSeek-V3, a [mixture](https://www.dynamicjobs.eu) of [professionals](https://mtglobalsolutionsinc.com) (MoE) design recently open-sourced by DeepSeek. This is [fine-tuned utilizing](https://gitea.dokm.xyz) Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research study group also carried out [understanding distillation](https://thematragroup.in) from DeepSeek-R1 to open-source Qwen and Llama models and released several variations of each