AI Potluck
Contribute
Back to Gap Map Organization

ILLUIN Technology

company · France

Scores

1 product on the map — 1 open-ish.

ColPali

Openness

3 high confidence
3.0
weights
open(45 ungated checkpoints on the vidore org, covering ColPali, ColQwen2/2.5, ColSmol and ColQwen-Omni)
data
open(vidore/colpali_train_set, the 118,195-pair training set, published ungated on the Hub)
code
open(colpali-engine[train] ships scripts/train/train_colbert.py and the per-model training configs used for the released checkpoints)
license
Gemma-License(non-OSI, resolved most-restrictive across the distributed SKUs - the PaliGemma-backed colpali-v1.2/v1.3-hf and -merged weights carry the Gemma terms)+MIT(OSI, the ColPali adapters and, with Apache-2.0 Qwen2-VL backbones, the ColQwen SKUs)

ColPali publishes its training set and training pipeline in full, which is as open as data and code get in this category. But some checkpoints, the PaliGemma-backed ColPali releases, merge in Gemma-licensed weights, and a family's license reading follows its most restrictive distributed checkpoint; the ColQwen line alone, released under MIT and Apache-2.0, would score higher.

Adoption

3 high confidence
3.0

Adoption is measured as Hugging Face downloads summed across the ColPali family's retriever checkpoints on the vidore account, in every format published: ColPali, ColQwen2 and ColQwen2.5, ColSmol and ColQwen-Omni. The base initializations the adapters load are excluded so that one load is not counted twice, as are the paper's single-vector bi-encoder baselines and its ColIdefics ablation.

Capability

4 high confidence
4.0

ColPali's family, especially ColQwen2.5, sits near the top of the ViDoRe leaderboard it defined, a few points behind the current leader. It carries the same MaxSim late-interaction mechanism as ColBERT, extended from text retrieval into the document-image setting.