commit 912fe1f2d90b7af47a39415546f8bbcc5d55ac0d Author: jeanettecummin Date: Sat May 31 15:54:37 2025 +0800 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..3b5c512 --- /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://101.33.225.953000) DeepSeek-R1, [yewiki.org](https://www.yewiki.org/User:EltonDalziel) an LLM fine-tuned with reinforcement knowing (RL) to improve reasoning capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://www.jobspk.pro) o1 model on several criteria, [consisting](https://video.disneyemployees.net) of MATH-500 and SWE-bench.
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of experts (MoE) design just recently [open-sourced](https://yaseen.tv) by [DeepSeek](http://103.140.54.203000). This base design is fine-tuned using Group [Optimization](https://pivotalta.com) (GRPO), a reasoning-oriented variant of RL. The research study group also carried out understanding distillation from DeepSeek-R1 to [open-source Qwen](https://www.cvgods.com) and Llama models and launched numerous variations of each \ No newline at end of file