pszemraj/nougat-base-onnx

nougat-base onnx

https://huggingface.co/facebook/nougat-base but exported to onnx. This is not quantized.

from transformers import NougatProcessor
from optimum.onnxruntime import ORTModelForVision2Seq

model_name = 'pszemraj/nougat-base-onnx'
processor = NougatProcessor.from_pretrained(model_name)
model = ORTModelForVision2Seq.from_pretrained(
    model_name,
    provider="CPUExecutionProvider", # 'CUDAExecutionProvider' for gpu 
    use_merged=False,
    use_io_binding=True
)

on colab CPU-only (at time of writing) you may get CuPy errors, to solve this uninstall it:

pip uninstall cupy-cuda11x -y

how do da inference?

See here