Xenova
/

vit-gpt2-image-captioning

Transformers.js

vision-encoder-decoder

image-captioning

Model card Files Files and versions

vit-gpt2-image-captioning / onnx

3.32 GB

2 contributors

History: 2 commits

Xenova's picture

Xenova HF Staff

Upload folder using huggingface_hub

7e763a4 over 2 years ago

decoder_model.onnx

768 MB
xet

Upload folder using huggingface_hub over 2 years ago
decoder_model_merged.onnx

768 MB
xet

Upload folder using huggingface_hub over 2 years ago
decoder_model_merged_quantized.onnx

196 MB
xet

Upload folder using huggingface_hub over 2 years ago
decoder_model_quantized.onnx

195 MB
xet

Upload folder using huggingface_hub over 2 years ago
decoder_with_past_model.onnx

768 MB
xet

Upload folder using huggingface_hub over 2 years ago
decoder_with_past_model_quantized.onnx

195 MB
xet

Upload folder using huggingface_hub over 2 years ago
encoder_model.onnx

343 MB
xet

Upload folder using huggingface_hub over 2 years ago
encoder_model_quantized.onnx

87.5 MB
xet

Upload folder using huggingface_hub over 2 years ago