From 1b4dc555c945deb1bb6d2111fc3c6d5ec682b91f Mon Sep 17 00:00:00 2001 From: verenacorlis66 Date: Mon, 17 Feb 2025 20:50:54 +0000 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..f0eea44 --- /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 learning (RL) to enhance [reasoning capability](http://59.110.68.1623000). DeepSeek-R1 attains outcomes on par with OpenAI's o1 model on [numerous](http://119.45.195.10615001) standards, including MATH-500 and SWE-bench.
+
DeepSeek-R1 is based on DeepSeek-V3, a [mixture](https://savico.com.br) of [professionals](https://git.elferos.keenetic.pro) (MoE) design just recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented variant of RL. The research group likewise performed knowledge [distillation](http://159.75.133.6720080) from DeepSeek-R1 to [open-source Qwen](http://152.136.232.1133000) and Llama models and released a number of versions of each \ No newline at end of file