Hugging Face's logo

Duoia
/
duovlm-40m-v1

Visual Question Answering
English
custom
vision-language-model
image-to-text
small-model
clip
from-scratch
Model card Files
xet
 Community
duovlm-40m-v1 / code /decoding.py

Commit History

DuoVLM-40M v1: from-scratch 40M vision-language model (frozen CLIP + MiniPile-pretrained LM)
4afe981
verified

Duoia commited on