Hugging Face's logo

Xenova
/
vit-gpt2-image-captioning

Image-to-Text
Transformers.js
ONNX
vision-encoder-decoder
image-text-to-text
image-captioning
Model card Files Community
1

quantized ONNX export and inference

#1
by Centaur31 - opened
Discussion
Centaur31

Hi!
I have 2 questions about the model.

  1. how did you export the 4 quantized models in the ONNX folder?
    and 2) how do you inference the quantized ONNX model?
    Thanks!

Sign up or log in to comment