infinity
infinity copied to clipboard
Implement Colbert for Optimum
Feature request
Add logic for colbert in the optimum engine so it returns token embeddings
Motivation
Since this is already supported for the torch engine, it will be useful to be able to use onnx versions of Colbert style models correctly as well
Your contribution
I can potentially submit a PR
(This issue is converted from https://github.com/michaelfeil/infinity/issues/512)