Small Multimodal Vision Model "Imp-v1-3b" trained using Phi-2 and Siglip.
mexicanamerican / small-multimodal-vision-model Goto Github PK
View Code? Open in Web Editor NEWThis project forked from aianytime/small-multimodal-vision-model
Small Multimodal Vision Model "Imp-v1-3b" trained using Phi-2 and Siglip.
License: MIT License