From c5f74acebc91c5f8548f5ffce23d5d73c7f25f9b Mon Sep 17 00:00:00 2001 From: Alvin Baecker Date: Sat, 15 Feb 2025 17:08:34 +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..5ceaeee --- /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 capability. DeepSeek-R1 attains results on par with [OpenAI's](https://gitea.eggtech.net) o1 design on a number of criteria, including MATH-500 and [SWE-bench](http://git.vimer.top3000).
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of specialists (MoE) model recently open-sourced by DeepSeek. This base design is [fine-tuned](https://nujob.ch) utilizing Group Relative Policy Optimization (GRPO), a [reasoning-oriented](https://jobs.sudburychamber.ca) version of RL. The research group likewise performed knowledge distillation from DeepSeek-R1 to open-source Qwen and Llama models and launched numerous versions of each \ No newline at end of file