ColSmolVLM is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
It is a SmolVLM extension that generates
ColBERT- style multi-vector representations of text and images.
It was introduced in the paper
ColPali: Efficient Document Retrieval with Vision Language Models and first released in
this repositoryThis version is trained with the commit b983e40 of the Colpali repository. (main branch from the repo)
Data is the same as the ColPali data described in the paper.
Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%).
Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both
ViDoRe and in the train set to prevent evaluation contamination.
A validation set is created with 2% of the samples to tune hyperparameters.
Unless specified otherwise, we train models in
bfloat16 format, use low-rank adapters (
LoRA)
with
alpha=32 and
r=32 on the transformer layers from the language model,
as well as the final randomly initialized projection layer, and use a
paged_adamw_8bit optimizer.
We train on a 4 GPU setup with data parallelism, a learning rate of 5e-4 with linear decay with 2.5% warmup steps, and a batch size of 8.
This should not be used as it is the base model, used only for initiliasation of the linear head weights of the model.
If you use any datasets or models from this organization in your research, please cite the original dataset as follows:
1@misc{faysse2024colpaliefficientdocumentretrieval,
2 title={ColPali: Efficient Document Retrieval with Vision Language Models},
3 author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
4 year={2024},
5 eprint={2407.01449},
6 archivePrefix={arXiv},
7 primaryClass={cs.IR},
8 url={https://arxiv.org/abs/2407.01449},
9}
