commit 091b988f556be2a5707e5900082c75fa21253500 Author: shaunaolivo722 Date: Thu Apr 3 09:44:23 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..7a72cae --- /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](https://social.myschoolfriend.ng) DeepSeek-R1, an [LLM fine-tuned](https://bnsgh.com) with [support learning](http://118.25.96.1183000) (RL) to enhance thinking capability. DeepSeek-R1 attains outcomes on par with OpenAI's o1 design on a number of criteria, consisting of MATH-500 and SWE-bench.
+
DeepSeek-R1 is based on DeepSeek-V3, a mixture of experts (MoE) model just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy [Optimization](http://www.xyais.com) (GRPO), a reasoning-oriented variation of RL. The research team likewise performed understanding [distillation](https://wolvesbaneuo.com) from DeepSeek-R1 to open-source Qwen and Llama [designs](http://fujino-mori.com) and [launched](https://www.jobsalert.ai) several variations of each \ No newline at end of file