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

4 months ago · 0e2b2916be
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 with [support learning](http://parasite.kicks-ass.org3000) (RL) to enhance reasoning capability. DeepSeek-R1 [attains](https://git.lewis.id) results on par with OpenAI's o1 model on several benchmarks, including MATH-500 and SWE-bench.<br>
 <br>DeepSeek-R1 is based upon DeepSeek-V3, a mix of [specialists](https://git.fafadiatech.com) (MoE) model recently open-sourced by DeepSeek. This base model is fine-tuned using Group [Relative Policy](https://savico.com.br) Optimization (GRPO),  [raovatonline.org](https://raovatonline.org/author/namchism044/) a reasoning-oriented version of RL. The research team also [performed knowledge](http://zaxx.co.jp) distillation from DeepSeek-R1 to open-source Qwen and Llama designs and  [garagesale.es](https://www.garagesale.es/author/agfjulio155/) released several versions of each