Hugging Face's logo

gurumurthy3
/
gpt2-stackformer-vision_V2

Image-to-Text
PyTorch
English
stackformer
gpt2
vision-language
image-captioning
cross-attention
perceiver-resampler
Model card Files
xet
 Community
gpt2-stackformer-vision_V2 / model_checkpoint.pth

Commit History

Upload V2: stackformer GPT-2 + sparse cross-attention vision model (128 visual tokens)
4666d47
verified

gurumurthy3 commited on