Intel

Image-to-text models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU.

Models derived from Mistral

BERT models of varying flavors

Quantized versions of ALBERT models for language tasks

DPT 3.1 (MiDaS) models, leveraging state-of-the-art vision backbones such as BEiT and Swinv2

DPT 3.0 (MiDaS) models, leveraging ViT and ViT-hybrid backbones

Smaller BERT models for question answering and text classification

DeBERTa is a language model that originates from Meta's RoBERTa model with disentangled attention and enhanced mask decoder.

Fine-tuned version of Microsoft's MiniLM models, trained on the GLUE MRPC dataset.

Large scale information retrieval corpus that was created based on real user search queries using Bing search engine