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

4 weeks ago · 18590db5c9
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 reinforcement knowing (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://www.jobassembly.com) o1 model on a number of criteria, consisting of MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a mixture of specialists (MoE) design just recently [open-sourced](https://careers.tu-varna.bg) by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO),  [engel-und-waisen.de](http://www.engel-und-waisen.de/index.php/Benutzer:JordanSawers7) a reasoning-oriented version of RL. The research [study team](https://esvoe.video) likewise carried out knowledge distillation from DeepSeek-R1 to [open-source](http://152.136.126.2523000) Qwen and Llama designs and  [forum.pinoo.com.tr](http://forum.pinoo.com.tr/profile.php?id=1344686) released several [versions](https://hylpress.net) of each