From 055d84f1a92d51f290dbdc09376fd7208653ae9f Mon Sep 17 00:00:00 2001 From: israelz660394 Date: Sun, 9 Feb 2025 04:55:41 +0100 Subject: [PATCH] Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model' --- ...R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md 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..c71f358 --- /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 support learning (RL) to improve reasoning ability. DeepSeek-R1 [attains](https://suprabullion.com) results on par with OpenAI's o1 design on several benchmarks, [including](http://hualiyun.cc3568) MATH-500 and [SWE-bench](https://gogs.zhongzhongtech.com).
+
DeepSeek-R1 is based upon DeepSeek-V3, a mix of [experts](https://www.9iii9.com) (MoE) model just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a reasoning-oriented variation of RL. The research study group also [performed understanding](http://expand-digitalcommerce.com) distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [released](https://nse.ai) several [versions](http://121.37.138.2) of each \ No newline at end of file