From 9d665afab92cbc46ade3b09a8b3cecfb4c0952d5 Mon Sep 17 00:00:00 2001 From: Alfonso Thiele Date: Sat, 15 Feb 2025 02:25:36 +0300 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..a3bc099 --- /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 DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to improve thinking ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://rosaparks-ci.com) o1 design on several standards, including MATH-500 and [SWE-bench](http://47.105.162.154).
+
DeepSeek-R1 is based on DeepSeek-V3, a mixture of [experts](https://www.p3r.app) (MoE) design recently open-sourced by DeepSeek. This base model is [fine-tuned](http://git.wangtiansoft.com) using Group Relative Policy Optimization (GRPO), a reasoning-oriented variant of RL. The research group also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched a number of versions of each \ No newline at end of file