#68 · Primary category： Foundation Models
mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Project last updated：05/30/25
GitHub Stars
2.4K
Forks
154
Contributors
8
License
Apache-2.0
Why we included this project
mPLUG-DocOwl is a family of open multimodal language models from Alibaba that handles document understanding without a separate OCR step. It answers questions about scanned pages, contracts, invoices, tables, and charts straight from the page image, which is the main reason teams building document Q&A or data-extraction features keep coming back to it. The repo bundles checkpoints from several model generations, including a compact chart-focused variant and a multi-page model, along with the inference, evaluation, and training code to run or extend them. Released training datasets and recipes make it realistic to fine-tune on your own document corpus rather than just running the models out of the box, and researchers will find reproduced benchmark numbers plus the published papers behind each major release. If your work turns messy, visual-heavy documents into structured answers, this is a strong starting point.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities