microsoft
/

Phi-4-multimodal-instruct

Automatic Speech Recognition

text-generation

speech-summarization

speech-translation

visual-question-answering

phi-4-multimodal

Model card Files Files and versions Community

Phi-4-multimodal-instruct / modeling_phi4mm.py

Commit History

Fix image embedding logic to be mps-compatible

f580f2d
verified

DefOs9 commited on Mar 14

fixes the asserion error when num_beams > 1 (#42)

18812f4
verified

freewym commited on Mar 12

Added model files

d93d2f6

garg-amit commited on Feb 24