base on mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding <div align="center"> <img src="assets/mPLUG_new1.png" width="80%"> </div> <div align="center"> <h2>The Powerful Multi-modal LLM Family for OCR-free Document Understanding<h2> <strong>Alibaba Group</strong> </div> <p align="center"> <a href="https://trendshift.io/repositories/9061" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9061" alt="DocOwl | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </p> ## 📢 News * 🔥🔥🔥 [2024.12.24] We have released the training code of DocOwl2 by [**ms-swift**](https://github.com/modelscope/ms-swift)! Now you can finetune a stronger model with your own data based on DocOwl2! * 🔥🔥🔥 [2024.9.28] We have released the training data, inference code and evaluation code of [DocOwl2](./DocOwl2/) on both **HuggingFace** 🤗 and **ModelScope** <img src="./assets/modelscope.png" width='20'>. * 🔥🔥🔥 [2024.9.20] Our paper [DocOwl 1.5](http://arxiv.org/abs/2403.12895) and [TinyChart](https://arxiv.org/abs/2404.16635) is accepted by EMNLP 2024. * 🔥🔥 [2024.9.06] We release the arxiv paper of [mPLUG-DocOwl 2](https://arxiv.org/abs/2409.03420), a SOTA 8B Multimodal LLM on OCR-free Multipage Document Understanding, each document image is encoded with just 324 tokens! * [2024.7.16] Our paper [PaperOwl](https://arxiv.org/abs/2311.18248) is accepted by ACM MM 2024. * [2024.5.08] We have released the training code of [DocOwl1.5](./DocOwl1.5/) supported by DeepSpeed. You can now finetune a stronger model based on DocOwl1.5! * [2024.4.26] We release the arxiv paper of [TinyChart](https://arxiv.org/abs/2404.16635), a SOTA 3B Multimodal LLM for Chart Understanding with Program-of-Throught ability (ChartQA: 83.6 > Gemin-Ultra 80.8 > GPT4V 78.5). The demo of TinyChart is available on [HuggingFace](https://huggingface.co/spaces/mPLUG/TinyChart-3B) 🤗. Both codes, models and data are released in [TinyChart](./TinyChart/). * [2024.4.3] We build demos of DocOwl1.5 on both [ModelScope](https://modelscope.cn/studios/iic/mPLUG-DocOwl/) <img src="./assets/modelscope.png" width='20'> and [HuggingFace](https://huggingface.co/spaces/mPLUG/DocOwl) 🤗, supported by the DocOwl1.5-Omni. The source codes of launching a local demo are also released in [DocOwl1.5](./DocOwl1.5/). * [2024.3.28] We release the training data (DocStruct4M, DocDownstream-1.0, DocReason25K), codes and models (DocOwl1.5-stage1, DocOwl1.5, DocOwl1.5-Chat, DocOwl1.5-Omni) of [mPLUG-DocOwl 1.5](./DocOwl1.5/) on both **HuggingFace** 🤗 and **ModelScope** <img src="./assets/modelscope.png" width='20'>. * [2024.3.20] We release the arxiv paper of [mPLUG-DocOwl 1.5](http://arxiv.org/abs/2403.12895), a SOTA 8B Multimodal LLM on OCR-free Document Understanding (DocVQA 82.2, InfoVQA 50.7, ChartQA 70.2, TextVQA 68.6). * [2024.01.13] Our Scientific Diagram Analysis dataset [M-Paper](https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/PaperOwl) has been available on both **HuggingFace** 🤗 and **ModelScope** <img src="./assets/modelscope.png" width='20'>, containing 447k high-resolution diagram images and corresponding paragraph analysis. * [2023.10.13] Training data, models of [mPLUG-DocOwl](./DocOwl/)/[UReader](./UReader/) has been open-sourced. * [2023.10.10] Our paper [UReader](https://arxiv.org/abs/2310.05126) is accepted by EMNLP 2023. <!-- * 🔥 [10.10] The source code and instruction data will be released in [UReader](https://github.com/LukeForeverYoung/UReader). --> * [2023.07.10] The demo of mPLUG-DocOwl on [ModelScope](https://modelscope.cn/studios/damo/mPLUG-DocOwl/summary) is avaliable. * [2023.07.07] We release the technical report and evaluation set of mPLUG-DocOwl. ## 🤖 Models - [**mPLUG-DocOwl2**](./DocOwl2/) (Arxiv 2024) - mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding - [**mPLUG-DocOwl1.5**](./DocOwl1.5/) (EMNLP 2024) - mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding - [**TinyChart**](./TinyChart/) (EMNLP 2024) - TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning - [**mPLUG-PaperOwl**](./PaperOwl/) (ACM MM 2024) - mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model - [**UReader**](./UReader/) (EMNLP 2023) - UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model - [**mPLUG-DocOwl**](./DocOwl/) (Arxiv 2023) - mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding ## 📺 Online Demo Note: The demo of HuggingFace is not as stable as ModelScope because the GPU in ZeroGPU Spaces of HuggingFace is dynamically assigned. ### 📖 DocOwl 1.5 - 🤗 [HuggingFace Space](https://huggingface.co/spaces/mPLUG/DocOwl) - <img src="assets/modelscope.png" width='20'> [ModelScope Space](https://modelscope.cn/studios/iic/mPLUG-DocOwl/) ### 📈 TinyChart-3B - 🤗 [HuggingFace Space](https://huggingface.co/spaces/mPLUG/TinyChart-3B) ## 🌰 Cases  ## Related Projects * [mPLUG](https://github.com/alibaba/AliceMind/tree/main/mPLUG). * [mPLUG-2](https://github.com/alibaba/AliceMind). * [mPLUG-Owl](https://github.com/X-PLUG/mPLUG-Owl) ", Assign "at most 3 tags" to the expected json: {"id":"9061","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"