commit d5c42606db9aee589e09688908b66ebb74774d40 Author: katlyncharles4 Date: Fri Feb 7 11:43:57 2025 +0000 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..25299d4 --- /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](https://51.75.215.219) with [support knowing](https://funitube.com) (RL) to improve thinking ability. DeepSeek-R1 attains results on par with [OpenAI's](https://superappsocial.com) o1 design on numerous criteria, [wiki.vst.hs-furtwangen.de](https://wiki.vst.hs-furtwangen.de/wiki/User:MichaelCrocker0) including MATH-500 and [SWE-bench](https://www.designxri.com).
+
DeepSeek-R1 is based on DeepSeek-V3, a mixture of [experts](https://copyrightcontest.com) (MoE) design recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group [Relative Policy](https://jollyday.club) Optimization (GRPO), a reasoning-oriented version of RL. The research study group also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama models and released a number of versions of each \ No newline at end of file