michaelfeil / michaelfeil/infinity

Implement Colbert for Optimum

Open
#512 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.9k
Forks
206
PR merge metrics
No merged PRs in 30d

Description

### 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)

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by comparing how ColBERT token embeddings are handled in the existing torch engine with the corresponding optimum engine path. Confirm the expected output for ONNX versions of ColBERT-style models, then verify that the optimum engine returns token embeddings consistently with the torch engine.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.