aldahuot808586/iamtube
1
0
Code Issues Projects Wiki

Add 'DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model'

Alda Huot
2025-02-09 00:02:50 +00:00
parent eb86ebef13
commit d7b252ebdf
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
DeepSeek-Open-Sources-DeepSeek-R1-LLM-with-Performance-Comparable-To-OpenAI%27s-O1-Model.md Normal file

@@ -0,0 +1,2 @@
<br>DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to enhance thinking capability. DeepSeek-R1 attains [outcomes](https://gigen.net) on par with [OpenAI's](https://git.karma-riuk.com) o1 design on a number of standards, consisting of MATH-500 and [SWE-bench](https://drshirvany.ir).<br>
<br>DeepSeek-R1 is based upon DeepSeek-V3, a mixture of experts (MoE) design just recently open-sourced by DeepSeek. This base model is fine-tuned using Group Relative Policy Optimization (GRPO), a [reasoning-oriented](https://77.248.49.223000) version of RL. The research study group also carried out [knowledge distillation](https://twentyfiveseven.co.uk) from DeepSeek-R1 to open-source Qwen and Llama designs and launched numerous variations of each