imaniket
/

vit-gpt2-test-image-captioning

Image-Text-to-Text

vision-encoder-decoder

Model card Files Files and versions

vit-gpt2-test-image-captioning

File size: 179 Bytes

5f7c459

{
  "_from_model_config": true,
  "bos_token_id": 50256,
  "decoder_start_token_id": 50256,
  "eos_token_id": 50256,
  "pad_token_id": 50256,
  "transformers_version": "4.31.0"
}