gurumurthy3
/

gpt2-stackformer-vision_V2

vision-language

image-captioning

cross-attention

perceiver-resampler

Model card Files Files and versions

gpt2-stackformer-vision_V2 / tokenizer /tokenizer.json

gurumurthy3's picture

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

4666d47 verified about 12 hours ago

History Contribute Delete

2.11 MB

File too large to display, you can check the raw version instead.