colqwen2.5 3b multilingual v1.0 EU AI Act Compliance Profile

ColQwen2.5-3b-multilingual-v1.0: Multilingual Visual Retriever based on Qwen2.5-VL-3B-Instruct with ColBERT strategy

This is the base version trained on 8xH100 80GB with per_device_batch_size=128 for 8 epoch.

ColQwen 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 Qwen2.5-VL-3B 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 repository

Version specificity

This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali. Maximal resolution is set so that 768 image patches are created at most. Experiments show clear improvements with larger amounts of image patches, at the cost of memory requirements.

This version is trained with colpali-engine==0.3.9.

Data

• German & English: Taken from the tsystems/vqa_de_en_batch1 dataset.
• Multilingual dataset: Taken from llamaindex/vdr-multilingual-train.
• Synthetic data: Taken from openbmb/VisRAG-Ret-Train-Synthetic-data dataset.
• In-domain VQA dataset: Taken from openbmb/VisRAG-Ret-Train-In-domain-data dataset.
• Colpali dataset: Taken from vidore/colpali_train_set.

Model Training

Parameters

We train models use low-rank adapters (LoRA) with alpha=128 and r=128 on the transformer layers from the language model, as well as the final randomly initialized projection layer, and use a `pag

Your obligations as a colqwen2.5 3b multilingual v1.0 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library

Base Model