commit fada229b9f0495942471fcf22bba42f7ff0803a1 Author: cooperburrough Date: Fri Feb 21 06:45:20 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..4ffcc84 --- /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://42.192.80.21) DeepSeek-R1, an LLM fine-tuned with reinforcement knowing (RL) to [improve thinking](http://8.138.140.943000) capability. DeepSeek-R1 [attains outcomes](https://git.sommerschein.de) on par with OpenAI's o1 model on several criteria, [garagesale.es](https://www.garagesale.es/author/roseannanas/) including MATH-500 and [SWE-bench](https://tricityfriends.com).
+
DeepSeek-R1 is based on DeepSeek-V3, a mix of experts (MoE) design just recently open-sourced by [DeepSeek](http://119.3.29.1773000). This base model is fine-tuned using Group [Relative Policy](https://git.satori.love) [Optimization](https://aggeliesellada.gr) (GRPO), a reasoning-oriented variation of RL. The research [study team](https://3.223.126.156) likewise carried out knowledge distillation from DeepSeek-R1 to [open-source](https://ssh.joshuakmckelvey.com) Qwen and Llama designs and launched several versions of each \ No newline at end of file