colqwen2-7b-v1.0 / README.md
yydxlv's picture
Update README.md
4fd76e7 verified
metadata
license: mit
datasets:
  - vidore/colpali_train_set
base_model:
  - Qwen/Qwen2-VL-7B-Instruct
pipeline_tag: feature-extraction
library_name: transformers
tags:
  - vidore

Model Details

Model Description

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-VL-7B 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.

This version is trained with batch_size 256 for 3 epochs.

  • Developed by: IEIT systems