Update README.md

README.md

@@ -1,199 +1,131 @@
 ---
-library_name: transformers
-tags: []
+license: mit
+library_name: colpali
+base_model: vidore/colpaligemma-3b-pt-448-base
+language:
+- en
+tags:
+- vidore
+datasets:
+- vidore/colpali_train_set
 ---
+# ColPali: Visual Retriever based on PaliGemma-3B with ColBERT strategy
 
-# Model Card for Model ID
+ColPali 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 [PaliGemma-3B](https://huggingface.co/google/paligemma-3b-mix-448) 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)
 
-<!-- Provide a quick summary of what the model is/does. -->
+<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/colpali-v1.2`](https://huggingface.co/vidore/colpali-v1.2), except that the LoRA adapter was merged into the base model. Thus, loading ColPali 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 adpter from scratch.
 
-## Model Details
+## Model Description
 
-### Model Description
+This model is built iteratively starting from an off-the-shelf [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) model. 
+We finetuned it to create [BiSigLIP](https://huggingface.co/vidore/bisiglip) and fed the patch-embeddings output by SigLIP to an LLM, [PaliGemma-3B](https://huggingface.co/google/paligemma-3b-mix-448) to create [BiPali](https://huggingface.co/vidore/bipali). 
 
-<!-- Provide a longer summary of what this model is. -->
+One benefit of inputting image patch embeddings through a language model is that they are natively mapped to a latent space similar to textual input (query). 
+This enables leveraging the [ColBERT](https://arxiv.org/abs/2004.12832) strategy to compute interactions between text tokens and image patches, which enables a step-change improvement in performance compared to BiPali. 
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## Model Training
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+### 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.
 
-### Model Sources [optional]
+*Note: Multilingual data is present in the pretraining corpus of the language model (Gemma-2B) and potentially occurs during PaliGemma-3B's multimodal training.*
 
-<!-- Provide the basic links for the model. -->
+### Parameters
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+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.
 
-## Uses
+## Usage
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+Install [`colpali-engine`](https://github.com/illuin-tech/colpali):
 
-### Direct Use
+```bash
+pip install colpali-engine>=0.3.0,<0.4.0
+```
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+Then run the following code:
 
-[More Information Needed]
+```python
+from typing import cast
 
-### Downstream Use [optional]
+import torch
+from PIL import Image
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+from colpali_engine.models import ColPali, ColPaliProcessor
 
-[More Information Needed]
+model = cast(
+    ColPali,
+    ColPali.from_pretrained(
+        "vidore/colpali-v1.2",
+        torch_dtype=torch.bfloat16,
+        device_map="cuda:0",  # or "mps" if on Apple Silicon
+    ),
+)
 
-### Out-of-Scope Use
+processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained("google/paligemma-3b-mix-448"))
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+# Your inputs
+images = [
+    Image.new("RGB", (32, 32), color="white"),
+    Image.new("RGB", (16, 16), color="black"),
+]
+queries = [
+    "Is attention really all you need?",
+    "Are Benjamin, Antoine, Merve, and Jo best friends?",
+]
 
-[More Information Needed]
+# Process the inputs
+batch_images = processor.process_images(images).to(model.device)
+batch_queries = processor.process_queries(queries).to(model.device)
 
-## Bias, Risks, and Limitations
+# Forward pass
+with torch.no_grad():
+    image_embeddings = model(**batch_images)
+    querry_embeddings = model(**batch_queries)
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+scores = processor.score_multi_vector(querry_embeddings, image_embeddings)
+```
 
-[More Information Needed]
+## Limitations
 
-### Recommendations
+ - **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.
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+## License
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+ColPali's vision language backbone model (PaliGemma) is under `gemma` license as specified in its [model card](https://huggingface.co/google/paligemma-3b-mix-448). The adapters attached to the model are under MIT license.
 
-## How to Get Started with the Model
+## Contact
 
-Use the code below to get started with the model.
+- Manuel Faysse: manuel.[email protected]
+- Hugues Sibille: [email protected]
+- Tony Wu: [email protected]
 
-[More Information Needed]
+## Citation
 
-## Training Details
+If you use any datasets or models from this organization in your research, please cite the original dataset as follows:
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+```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}, 
+}
+```