commit 9443c4f5ad669e7fd73d34738b3735f6a2b1cdbd Author: wilmaschott878 Date: Fri Apr 4 02:38:43 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..88cd7aa --- /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://germanjob.eu) DeepSeek-R1, an [LLM fine-tuned](https://www.eticalavoro.it) with reinforcement learning (RL) to improve thinking capability. DeepSeek-R1 attains outcomes on par with [OpenAI's](https://grailinsurance.co.ke) o1 design on several criteria, consisting of MATH-500 and SWE-bench.
+
DeepSeek-R1 is based upon DeepSeek-V3, a [mixture](https://mypungi.com) of specialists (MoE) model just recently open-sourced by DeepSeek. This [base design](http://154.64.253.773000) is fine-tuned using Group Relative Policy Optimization (GRPO), a [reasoning-oriented variation](https://code.nwcomputermuseum.org.uk) of RL. The research study team also performed understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and [launched numerous](https://zkml-hub.arml.io) variations of each \ No newline at end of file