Update README.md

README.md

@@ -1,202 +1,143 @@
 ---
+license: mit
+library_name: colpali
 base_model: vidore/colpaligemma-3b-pt-448-base
-library_name: peft
+language:
+- en
+tags:
+- vidore
 ---
+# 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. -->
+This version has right padding to fix unwanted tokens in the query encoding.
+It also stems from the fixed `vidore/colpaligemma-3b-pt-448-base` to guarantee deterministic projection layer initialization.
+It was trained for 5 epochs, with in-batch negatives and hard mined negatives and a warmup of 1000 steps to help reduce non-english language collapse.
 
 
+## Model Description
 
-## Model Details
+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). 
 
-### Model Description
+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. 
 
-<!-- Provide a longer summary of what this model is. -->
+## 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 (Gemma-2B) and potentially occurs during PaliGemma-3B's multimodal 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]
+### Parameters
 
-### Model Sources [optional]
+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.
 
-<!-- Provide the basic links for the model. -->
+## Usage
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+```python
+import torch
+import typer
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+from transformers import AutoProcessor
+from PIL import Image
 
-## Uses
+from colpali_engine.models.paligemma_colbert_architecture import ColPali
+from colpali_engine.trainer.retrieval_evaluator import CustomEvaluator
+from colpali_engine.utils.colpali_processing_utils import process_images, process_queries
+from colpali_engine.utils.image_from_page_utils import load_from_dataset
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-### Direct Use
+def main() -> None:
+    """Example script to run inference with ColPali"""
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+    # Load model
+    model_name = "vidore/colpali-v1.1"
+    model = ColPali.from_pretrained("vidore/colpaligemma-3b-pt-448-base", torch_dtype=torch.bfloat16, device_map="cuda").eval()
+    model.load_adapter(model_name)
+    processor = AutoProcessor.from_pretrained(model_name)
 
-[More Information Needed]
+    # select images -> load_from_pdf(<pdf_path>),  load_from_image_urls(["<url_1>"]), load_from_dataset(<path>)
+    images = load_from_dataset("vidore/docvqa_test_subsampled")
+    queries = ["From which university does James V. Fiorca come ?", "Who is the japanese prime minister?"]
 
-### Downstream Use [optional]
+    # run inference - docs
+    dataloader = DataLoader(
+        images,
+        batch_size=4,
+        shuffle=False,
+        collate_fn=lambda x: process_images(processor, x),
+    )
+    ds = []
+    for batch_doc in tqdm(dataloader):
+        with torch.no_grad():
+            batch_doc = {k: v.to(model.device) for k, v in batch_doc.items()}
+            embeddings_doc = model(**batch_doc)
+        ds.extend(list(torch.unbind(embeddings_doc.to("cpu"))))
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+    # run inference - queries
+    dataloader = DataLoader(
+        queries,
+        batch_size=4,
+        shuffle=False,
+        collate_fn=lambda x: process_queries(processor, x, Image.new("RGB", (448, 448), (255, 255, 255))),
+    )
 
-[More Information Needed]
+    qs = []
+    for batch_query in dataloader:
+        with torch.no_grad():
+            batch_query = {k: v.to(model.device) for k, v in batch_query.items()}
+            embeddings_query = model(**batch_query)
+        qs.extend(list(torch.unbind(embeddings_query.to("cpu"))))
 
-### Out-of-Scope Use
+    # run evaluation
+    retriever_evaluator = CustomEvaluator(is_multi_vector=True)
+    scores = retriever_evaluator.evaluate(qs, ds)
+    print(scores.argmax(axis=1))
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-[More Information Needed]
+if __name__ == "__main__":
+    typer.run(main)
 
-## Bias, Risks, and Limitations
+```
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## Limitations
 
-[More Information Needed]
+ - **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.
 
-### Recommendations
+## License
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+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.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### 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]
-### Framework versions
-
-- PEFT 0.11.1
+## 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}, 
+}
+```