From cefe6fe8d1ae62c82788343cdfc6f37c700b777f Mon Sep 17 00:00:00 2001 From: tyreegilles211 Date: Thu, 3 Apr 2025 03:14:53 +0000 Subject: [PATCH] Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model' --- ...R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md diff --git 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 new file mode 100644 index 0000000..37ff4ec --- /dev/null +++ b/DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md @@ -0,0 +1,2 @@ +
[DeepSeek open-sourced](https://jobdd.de) DeepSeek-R1, an [LLM fine-tuned](http://www.jobteck.co.in) with [reinforcement knowing](http://175.27.189.803000) (RL) to enhance thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on numerous standards, consisting of MATH-500 and [SWE-bench](http://shiningon.top).
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) design just recently open-sourced by [DeepSeek](https://eurosynapses.giannistriantafyllou.gr). This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented variant](https://savico.com.br) of RL. The research group also carried out understanding distillation from DeepSeek-R1 to [open-source](https://www.paknaukris.pro) Qwen and [trademarketclassifieds.com](https://trademarketclassifieds.com/user/profile/2929296) Llama models and launched numerous versions of each \ No newline at end of file