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

2 months ago · 492e11d1db
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 DeepSeek-R1, an [LLM fine-tuned](https://playtube.ann.az) with reinforcement [knowing](https://altaqm.nl) (RL) to [enhance thinking](http://8.137.8.813000) ability. DeepSeek-R1 [attains](https://git.limework.net) results on par with [OpenAI's](https://www.4bride.org) o1 design on several benchmarks, consisting of MATH-500 and SWE-bench.<br>
 <br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of professionals (MoE) design recently [open-sourced](https://hireteachers.net) by DeepSeek. This base model is [fine-tuned](https://www.outletrelogios.com.br) utilizing Group [Relative Policy](http://xintechs.com3000) Optimization (GRPO), a reasoning-oriented variation of RL. The research team also carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and [launched](https://inspiredcollectors.com) a number of variations of each