From 430a677791ed585f015d69e938e0635848dd9b3d Mon Sep 17 00:00:00 2001 From: Maryanne Towns Date: Fri, 7 Feb 2025 07:09:58 +0100 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..1ec23bc --- /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](http://mooel.co.kr) DeepSeek-R1, an LLM fine-tuned with [support learning](http://dev.nextreal.cn) (RL) to enhance reasoning ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](http://photorum.eclat-mauve.fr) o1 model on several standards, consisting of MATH-500 and [SWE-bench](http://47.92.159.28).
+
DeepSeek-R1 is based on DeepSeek-V3, a mixture of [specialists](https://www.globalshowup.com) (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group [Relative Policy](https://git.vincents.cn) [Optimization](https://git.limework.net) (GRPO), a [reasoning-oriented](https://tyciis.com) version of RL. The research study group likewise carried out knowledge distillation from DeepSeek-R1 to open-source Qwen and [Llama models](http://207.180.250.1143000) and released a number of versions of each \ No newline at end of file