Skip to content

marketplace Search Results · in:license distribute

17 results
 (79 ms)

17 results

MAI-DS-R1 is a DeepSeek-R1 reasoning model that has been post-trained by the Microsoft AI team to fill in information gaps in the previous version of the model and improve its harm protections while maintaining R1 reasoning capabilities.
  • By Microsoft
  • 128k input
  • 4k output

Refresh of Phi-3-mini model.
  • By Microsoft
  • 131k input
  • 4k output

A new mixture of experts model
  • By Microsoft
  • 131k input
  • 4k output

Refresh of Phi-3-vision model.
  • By Microsoft
  • 131k input
  • 4k output

Phi-4 14B, a highly capable model for low latency scenarios.
  • By Microsoft
  • 16k input
  • 16k output

3.8B parameters Small Language Model outperforming larger models in reasoning, math, coding, and function-calling
  • By Microsoft
  • 128k input
  • 4k output

Same Phi-3-medium model, but with a larger context size for RAG or few shot prompting.
  • By Microsoft
  • 131k input
  • 4k output

A 14B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data.
  • By Microsoft
  • 4k input
  • 4k output

A 7B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data.
  • By Microsoft
  • 131k input
  • 4k output

State-of-the-art open-weight reasoning model.
  • By Microsoft
  • 33k input
  • 4k output