commit c80f9f122c5b470d0915226e965278556e9a9402 Author: fidelleger0647 Date: Fri Mar 14 16:53:53 2025 +0100 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..dbeaec6 --- /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 knowing (RL) to [enhance](https://trackrecord.id) thinking capability. DeepSeek-R1 attains results on par with OpenAI's o1 design on numerous standards, including MATH-500 and [SWE-bench](http://gitlab.boeart.cn).
+
DeepSeek-R1 is based upon DeepSeek-V3, a mix of [experts](https://www.luckysalesinc.com) (MoE) design recently open-sourced by DeepSeek. This base design is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research group likewise carried out [knowledge distillation](https://gogs.k4be.pl) from DeepSeek-R1 to open-source Qwen and [systemcheck-wiki.de](https://systemcheck-wiki.de/index.php?title=Benutzer:HallieBoothe4) Llama models and launched numerous versions of each \ No newline at end of file