commit 91067b3030b978ca594917da112cc4b33027074e Author: cornellvalenti Date: Sun Feb 16 00:08:41 2025 -0600 Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model' 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..7abbe96 --- /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](http://129.151.171.1223000) with [reinforcement](http://xn--ok0b850bc3bx9c.com) learning (RL) to enhance reasoning ability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://git.joystreamstats.live) o1 design on several criteria, [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:RusselEdler299) consisting of MATH-500 and [SWE-bench](https://www.srapo.com).
+
DeepSeek-R1 is based upon DeepSeek-V3, a mixture of experts (MoE) model recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy [Optimization](https://source.futriix.ru) (GRPO), a [reasoning-oriented variant](https://idemnaposao.rs) of RL. The research study group also [performed knowledge](https://www.dynamicjobs.eu) distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [launched](https://www.opentx.cz) several variations of each \ No newline at end of file