Colqwen2 V1.0

🚀 ColQwen2: Visual Retriever based on Qwen2-VL-2B-Instruct with ColBERT strategy

ColQwen2 is a model leveraging a novel architecture and training strategy based on Vision Language Models (VLMs). It can efficiently index documents from their visual features, offering a powerful solution for visual document retrieval.

Key Features

• It's an extension of Qwen2-VL-2B, generating ColBERT-style multi-vector representations of text and images.
• Introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository.

🚀 Quick Start

Prerequisites

Make sure colpali-engine is installed from source or with a version superior to 0.3.4. transformers version must be > 4.46.1.

pip install git+https://github.com/illuin-tech/colpali

Basic Usage

import torch
from PIL import Image
from transformers.utils.import_utils import is_flash_attn_2_available

from colpali_engine.models import ColQwen2, ColQwen2Processor

model = ColQwen2.from_pretrained(
    "vidore/colqwen2-v1.0",
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
    attn_implementation="flash_attention_2" if is_flash_attn_2_available() else None,
).eval()
processor = ColQwen2Processor.from_pretrained("vidore/colqwen2-v1.0")

# Your inputs
images = [
    Image.new("RGB", (128, 128), color="white"),
    Image.new("RGB", (64, 32), color="black"),
]
queries = [
    "Is attention really all you need?",
    "What is the amount of bananas farmed in Salvador?",
]

# Process the inputs
batch_images = processor.process_images(images).to(model.device)
batch_queries = processor.process_queries(queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

scores = processor.score_multi_vector(query_embeddings, image_embeddings)

✨ Features

• Dynamic Image Resolution: This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali. The 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.
• Trained with Specific Engine: This version is trained with colpali-engine==0.3.1.
• Same Training Data: Data is the same as the ColPali data described in the paper.

📚 Documentation

Model Training

Dataset

Our training dataset of 127,460 query - page pairs consists of train sets from openly available academic datasets (63%) and a synthetic dataset. The synthetic dataset is made up of pages from web - crawled PDF documents and augmented with VLM - generated (Claude - 3 Sonnet) pseudo - questions (37%). The training set is fully English, allowing us to study zero - shot generalization to non - English languages. We ensure no multi - page PDF document is used in both ViDoRe and the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.

Note: Multilingual data is present in the pretraining corpus of the language model and most probably in the multimodal training.

Parameters

All models are trained for 1 epoch on the train set. 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 an 8 GPU setup with data parallelism, a learning rate of 5e - 5 with linear decay with 2.5% warmup steps, and a batch size of 32.

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==0.3.1. Data is the same as the ColPali data described in the paper.

Limitations

• Focus: The model primarily focuses on PDF - type documents and high - resources languages, potentially limiting its generalization to other document types or less represented languages.
• Support: The model relies on multi - vector retreiving derived from the ColBERT late interaction mechanism, which may require engineering efforts to adapt to widely used vector retrieval frameworks that lack native multi - vector support.

📄 License

ColQwen2's vision language backbone model (Qwen2 - VL) is under apache2.0 license. The adapters attached to the model are under MIT license.

📞 Contact

• Manuel Faysse: manuel.faysse@illuin.tech
• Hugues Sibille: hugues.sibille@illuin.tech
• Tony Wu: tony.wu@illuin.tech

📚 Citation

If you use any datasets or models from this organization in your research, please cite the original dataset as follows:

@misc{faysse2024colpaliefficientdocumentretrieval,
  title={ColPali: Efficient Document Retrieval with Vision Language Models}, 
  author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2407.01449}, 
}

📋 Model Information