Favicon de microsoft

Microsoft AI: MAI DS R1

MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model’s responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1’s reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1.

MAI-DS-R1 demonstrates improved performance on harm mitigation benchmarks and maintains competitive results across general reasoning tasks. It surpasses R1-1776 in satisfaction metrics for blocked queries and reduces leakage in harmful content categories. The model is based on a transformer MoE architecture and is suitable for general-purpose use cases, excluding high-stakes domains such as legal, medical, or autonomous systems.

Modalidades
Contexto
164K
Publicado
21 abr 2025
Fecha límite de conocimiento
jul 2024

Actividad

Volumen de tokens y tráfico de solicitudes a este modelo a lo largo del tiempo.

Actualmente no está disponible mediante el enrutamiento dentro de la región de la UE. Documentación de enrutamiento dentro de la región

Preguntas frecuentes