---
base_model: vidore/colqwen2-base
language:
- en
library_name: colpali
license: apache-2.0
tags:
- colpali
- vidore-exclude
- sentence-transformers
- multi-vector
pipeline_tag: visual-document-retrieval
---
# ColQwen2: Visual Retriever based on Qwen2-VL-2B-Instruct with ColBERT strategy

ColQwen2 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-2B](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images. 
It was introduced in the paper [ColPali: Efficient Document Retrieval with Vision Language Models](https://arxiv.org/abs/2407.01449) and first released in [this repository](https://github.com/ManuelFay/colpali)

<p align="center"><img width=800 src="https://github.com/illuin-tech/colpali/blob/main/assets/colpali_architecture.webp?raw=true"/></p>

## Version specificity

> [!NOTE]
> This version is similar to [`vidore/colqwen2-v1.0`](https://huggingface.co/vidore/colqwen2-v1.0), except that the LoRA adapter was merged into the base model. Thus, loading ColQwen2 from this checkpoint saves you the trouble of merging the pre-trained adapter yourself.
> 
> This can be useful if you want to train a new adapter from scratch.

## Model Training

### Dataset
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*](https://huggingface.co/collections/vidore/vidore-benchmark-667173f98e70a1c0fa4db00d) and in 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](https://arxiv.org/abs/2106.09685)) 
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.

## Usage

### Sentence Transformers

ColQwen2 can be loaded as a multi-vector (ColBERT-style late interaction) retriever with [Sentence Transformers](https://www.sbert.net/) via the `MultiVectorEncoder`, exposing the familiar `encode_query` / `encode_document` / `similarity` API.

```bash
pip install "sentence-transformers[image]>=6.0.0"
```

```python
from sentence_transformers import MultiVectorEncoder

model = MultiVectorEncoder("vidore/colqwen2-v1.0-merged")

queries = [
    "What is the variable represented on the y-axis of the graph?",
    "Total outlay is maximum in which year?",
]
images = [
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc1.jpg",
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc2.jpg",
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc3.jpg",
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc4.jpg",
]

query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(images)
print(f"Query 0 shape:    {tuple(query_embeddings[0].shape)}")
print(f"Document 0 shape: {tuple(document_embeddings[0].shape)}")
# Query 0 shape:    (25, 128)
# Document 0 shape: (755, 128)

scores = model.similarity(query_embeddings, document_embeddings)
print(scores)
# tensor([[13.6689, 11.1143, 11.5332, 10.2905],
#         [ 7.1914, 16.0020,  6.7881,  6.3818]])
```

### ColPali Engine

> [!WARNING]
> Note: `colpali-engine` 0.3.13 and later no longer send the `"Query: "` query prefix that this checkpoint
> was trained with (illuin-tech/colpali#280 dropped it from `ColQwen2Processor`, and illuin-tech/colpali#339
> then changed the base class default it fell back on to `""`). The Sentence Transformers configuration in
> this repository reproduces the original training-time format, so its embeddings differ slightly from
> current `colpali-engine` output.

Make sure `colpali-engine` is installed from source or with a version superior to 0.3.1.
`transformers` version must be > 4.45.0.

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

```python
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-merged",
    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-merged")

# 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)
```


## Limitations

 - **Focus**: The model primarily focuses on PDF-type documents and high-ressources 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:

```bibtex
@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}, 
}
```