pszemraj
/

nougat-small-onnx-quant_avx2

Image-Text-to-Text

vision-encoder-decoder

Inference Endpoints

Model card Files Files and versions

nougat-small-onnx-quant_avx2

This was quantized from pszemraj/nougat-small-onnx using the --avx2 flag so should work properly on most machines.

per_channel is set to True for better accuracy
Usage is the same as: https://huggingface.co/pszemraj/nougat-small-onnx

Downloads last month: 9

Inference API

Image-Text-to-Text

Inference API (serverless) does not yet support transformers models for this pipeline type.

Collection including pszemraj/nougat-small-onnx-quant_avx2

Nougat ONNX

Faster Nougat in ONNX format (optimum onnxruntime) • 6 items • Updated Feb 24 • 1