Colqwen2 V1.0 Hf

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

ColQwen2 is a model that leverages a novel model architecture and training strategy based on Vision Language Models (VLMs). It can efficiently index documents using their visual features. It extends Qwen2-VL-2B and generates ColBERT-style multi-vector representations of text and images. This model was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository.

The HuggingFace transformers 🤗 implementation was contributed by Tony Wu (@tonywu71) and Yoni Gozlan (@yonigozlan).

🚀 Quick Start

Important Notes

⚠️ Important Note EXPERIMENTAL: Wait for https://github.com/huggingface/transformers/pull/35778 to be merged before using!

💡 Usage Tip This version of ColQwen2 should be loaded with the transformers 🤗 release, not with colpali-engine. It was converted using the convert_colqwen2_weights_to_hf.py script from the vidore/colqwen2-v1.0-merged checkpoint.

✨ Features

• Based on a novel model architecture and training strategy of Vision Language Models (VLMs).
• Can efficiently index documents from their visual features.
• Generates ColBERT-style multi-vector representations of text and images.

📚 Documentation

Model Description

Read the transformers 🤗 model card: https://huggingface.co/docs/transformers/en/model_doc/colqwen2.

Model Training

Dataset

Our training dataset consists of 127,460 query - page pairs. It is composed 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 by design, which allows us to study zero - shot generalization to non - English languages. We explicitly ensure that 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.

💻 Usage Examples

Basic Usage

import torch
from PIL import Image

from transformers import ColQwen2ForRetrieval, ColQwen2Processor
from transformers.utils.import_utils import is_flash_attn_2_available


model_name = "vidore/colqwen2-v1.0-hf"

model = ColQwen2ForRetrieval.from_pretrained(
    model_name,
    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(model_name)

# Your inputs (replace dummy images with screenshots of your documents)
images = [
    Image.new("RGB", (128, 128), color="white"),
    Image.new("RGB", (64, 32), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

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

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

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings, image_embeddings)

🔧 Technical Details

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 retrieving 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 apache - 2.0 license. ColQwen2 inherits from this apache - 2.0 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}, 
}