Open JingyaHuang opened 3 months ago
As requested in aws neuron caching, we need to support layout lm models export and inference first.
Tasks: feature-extraction / fill-mask / question-answering / text-classification / token-classification
Requested by users in aws-neuron/optimum-neuron-cache.
aws-neuron/optimum-neuron-cache
I can pick it up when I have the bandwidth, but I would encourage members to contribute following this guide, it should be very straightforward.
Feature request
As requested in aws neuron caching, we need to support layout lm models export and inference first.
Tasks: feature-extraction / fill-mask / question-answering / text-classification / token-classification
Motivation
Requested by users in
aws-neuron/optimum-neuron-cache.Your contribution
I can pick it up when I have the bandwidth, but I would encourage members to contribute following this guide, it should be very straightforward.