modelscope / modelscope/ms-swift
Supporting ColPali Engine for Late Integration Embedding/Reranking models
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Describe the feature
Late Interaction training pradigm has become widely popular and well accepted in the community. We should enable/integrate - https://github.com/illuin-tech/colpali among the pioneers for embedding and reranking models with late interaction.
This would include adding support for VisBert and other Colpali models and their finetuning/experiments
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the linked ColPali project and the ms-swift entry points for embedding and reranking models. Then investigate how VisBert and other ColPali models are represented, including the requested finetuning and experiments. Done means supported ColPali models can be integrated, fine-tuned, and evaluated, but the issue does not name specific files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100