---
language:
- en
license: mit
library_name: Tevatron
tags:
- vidore
datasets:
- Tevatron/docmatix-ir
- HuggingFaceM4/Docmatix
- Tevatron/msmarco-passage-aug
- vidore/colpali_train_set
- Tevatron/wiki-ss-nq
---


# DSE-QWen2-2b-MRL-V0

To support better effectiveness--efficiency trade-off, this checkpoint are trained to have:

1. Flexible representation dimension
2. Flexible image size

Details will be updated soon.