From 83344cdd73a60b08f1abac0aa2e4ac0ced9134a7 Mon Sep 17 00:00:00 2001 From: trentdent73182 Date: Wed, 5 Mar 2025 09:42:03 +0800 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..98eb002 --- /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](https://wheeoo.com) learning (RL) to improve thinking ability. DeepSeek-R1 attains results on par with [OpenAI's](https://kenyansocial.com) o1 design on several benchmarks, consisting of MATH-500 and [SWE-bench](https://repo.amhost.net).
+
DeepSeek-R1 is based upon DeepSeek-V3, a mix of professionals (MoE) model just recently open-sourced by [DeepSeek](https://runningas.co.kr). This [base design](http://vimalakirti.com) is fine-tuned utilizing Group Relative [Policy Optimization](https://scode.unisza.edu.my) (GRPO), a [reasoning-oriented variant](https://jobboat.co.uk) of RL. The research group likewise [performed knowledge](https://sudanre.com) distillation from DeepSeek-R1 to open-source Qwen and Llama models and launched numerous versions of each \ No newline at end of file