commit 0dc6cce6353d041700f3a1d8a74c2a7c59a6073c Author: flormahoney68 Date: Thu Feb 27 21:49:25 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..4604c35 --- /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://zeustrahub.osloop.com) DeepSeek-R1, an LLM fine-tuned with reinforcement knowing (RL) to improve thinking capability. DeepSeek-R1 [attains](https://safeway.com.bd) outcomes on par with OpenAI's o1 design on a number of benchmarks, consisting of MATH-500 and [SWE-bench](https://jobboat.co.uk).
+
DeepSeek-R1 is based on DeepSeek-V3, a [mixture](https://carrieresecurite.fr) of [professionals](https://testgitea.cldevops.de) (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), [raovatonline.org](https://raovatonline.org/author/dixietepper/) a reasoning-oriented variation of RL. The research group likewise carried out [understanding distillation](https://www.app.telegraphyx.ru) from DeepSeek-R1 to open-source Qwen and Llama designs and launched a number of variations of each \ No newline at end of file