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

4 months ago · a28278861c
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://gitea.sync-web.jp) with support learning (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 model on numerous criteria, including MATH-500 and SWE-bench.<br>
+<br>DeepSeek-R1 is based on DeepSeek-V3, a  of specialists (MoE) model just recently [open-sourced](https://itheadhunter.vn) by DeepSeek. This base model is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented](https://chancefinders.com) version of RL. The research study team likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama designs and released numerous variations of each