base on TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones # TinyGPT-V <font size='5'>**TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones**</font> [Zhengqing Yuan](https://dlyuangod.github.io/zhengqingyuan/)✟, Zhaoxu Li❁, [Weiran Huang](https://www.weiranhuang.com/)❋, [Yanfang Ye](http://yes-lab.org/)✟, [Lichao Sun](https://lichao-sun.github.io/)❁ ✟University of Notre Dame, ❁Lehigh University, ❋Shanghai Jiao Tong University Zhaoxu is a visiting student in the LAIR lab at Lehigh University. </a> <a href='https://arxiv.org/abs/2312.16862'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> <a href='https://huggingface.co/Tyrannosaurus/TinyGPT-V'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-blue'></a> <a href='https://huggingface.co/spaces/llizhx/TinyGPT-V'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'> English | [简体中文](/README_zh-CN.md) </font> ## News [Apr.08 2024] Update our paper v2. We revised some type errors, provided more details and updated TinyGPT-V lastest results. [Mar.20 2024] Update the Phi-2 weight download link. [Jan.22 2024] Welcome to Hugging Face online demo to try out our models (for Stage-4 v1)! [Jan.19 2024] Major Updates! We are officially releasing v1 of TinyGPT-V! After our evaluation, the performance of TinyGPT-V has reached 98% of InstructBLIP's performance and exceeds the performance of other models of the same period! [Jan.03 2024] Welcome to Hugging Face online demo to try out our models (for Stage-3)! [Dec.28 2023] Breaking! We release the code of our TinyGPT-V. ## TinyGPT-V Model Structure ### Whole Model Structure  ### Language Model Structure  ## TinyGPT-V Traning Process  ## TinyGPT-V Results ### Radar Chart  ### Performance and Efficiency  ## Getting Started ### Installation **1. Prepare the code and the environment** Git clone our repository, creating a python environment and activate it via the following command ```bash git clone https://github.com/DLYuanGod/TinyGPT-V.git cd TinyGPT-V conda env create -f environment.yml conda activate tinygptv ``` **2. Prepare the pretrained LLM weights** **TinyGPT-V** is based on Phi-2. Download the corresponding LLM weights from the following huggingface space via clone the repository using git-lfs. Phi-2 2.7B: [Download](https://huggingface.co/spaces/llizhx/TinyGPT-V/tree/main/phi-2) Then, set the variable *phi_model* in the model config file to the LLM weight path. * Set the LLM path [here](minigpt4/configs/models/minigpt_v2.yaml#L14) at Line 14, [here](minigpt4/configs/models/minigpt4_vicuna0.yaml#L18) at Line 18 and [here](minigpt4/conversation/conversation.py#L16) at Line 16. **3. Prepare the pretrained model checkpoints** Download the pretrained model checkpoints | After stage-1 | After stage-2 | After stage-3| After stage-4 | | ------ | ------ | ------ | -------| | [Download](https://huggingface.co/Tyrannosaurus/TinyGPT-V/blob/main/TinyGPT-V_for_Stage1.pth) |[Download](https://huggingface.co/Tyrannosaurus/TinyGPT-V/blob/main/TinyGPT-V_for_Stage2.pth) | [Download](https://huggingface.co/Tyrannosaurus/TinyGPT-V/blob/main/TinyGPT-V_for_Stage3.pth) |[Download](https://huggingface.co/Tyrannosaurus/TinyGPT-V/blob/main/TinyGPT-V_for_Stage4.pth) | For **TinyGPT-V**, set the path to the pretrained checkpoint in the evaluation config file in [tinygptv_stage1_2_3_eval.yaml](eval_configs/tinygptv_stage1_2_3_eval.yaml#L8) at Line 8 for Stage 1, 2 and 3 version or [tinygptv_stage4_eval.yaml](eval_configs/tinygptv_stage4_eval.yaml#L8) for Stage 4 version. **4. Update the Phi-2 Modeling for transformers lib.** Linux system: ``` cp modeling_phi.py /root/miniconda3/envs/tinygptv/lib/python3.9/site-packages/transformers/models/phi/ ``` Windows system Find your conda yourself: conda_sit/envs/tinygptv/lib/python3.9/site-packages/transformers/models/phi/ Replace modeling_phi.py in that directory with the one in TinyGPT-V/modeling_phi.py. ### Launching Demo Locally For Stage 4, run ``` python demo_v2.py --cfg-path eval_configs/tinygptv_stage4_eval.yaml --gpu-id 0 ``` Note: Stage 4 will have some Grounding abilities. But the performance is not very good, we are working on this! For Stage 1, 2 and 3, run ``` python demo.py --cfg-path eval_configs/tinygptv_stage1_2_3_eval.yaml --gpu-id 0 ``` To perfer more powerful model, LLMs loads as 16 bit by default. This configuration requires about 8G GPU memory. To more save GPU memory, you can run the model in 8 bit below 8G device by setting `low_resource` to `True` in the relevant config file: * Stage 4 [tinygptv_stage4_eval.yaml](eval_configs/tinygptv_stage4_eval.yaml#6) * Stage 1, 2 and 3 [tinygptv_stage1_2_3_eval.yaml](eval_configs/tinygptv_stage1_2_3_eval.yaml#6) ### Training First you need to adjust all the updated weights in the LLM to be calculated with full precision:[Here](minigpt4\models\base_model.py). Remove the comments from the following lines: ``` layer.self_attn.q_layernorm.weight.data = layer.self_attn.q_layernorm.weight.data.float() layer.self_attn.k_layernorm.weight.data = layer.self_attn.k_layernorm.weight.data.float() layer.post_layernorm.weight.data = layer.post_layernorm.weight.data.float() layer.input_layernorm.weight.data = layer.input_layernorm.weight.data.float() # Perform a similar operation for the bias item if layer.self_attn.q_layernorm.bias is not None: layer.self_attn.q_layernorm.bias.data = layer.self_attn.q_layernorm.bias.data.float() if layer.self_attn.k_layernorm.bias is not None: layer.self_attn.k_layernorm.bias.data = layer.self_attn.k_layernorm.bias.data.float() if layer.input_layernorm.bias is not None: layer.input_layernorm.bias.data = layer.input_layernorm.bias.data.float() llama_model.model.model.final_layernorm.weight.requires_grad = True llama_model.model.model.final_layernorm.weight.data = llama_model.model.model.final_layernorm.weight.data.float() if llama_model.model.model.final_layernorm.bias is not None: llama_model.model.model.final_layernorm.bias.data = llama_model.model.model.final_layernorm.bias.float() ``` **Stage 1 and 2:** * Datasets: [first stage dataset preparation instruction](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/dataset/README_1_STAGE.md) * Then run: ``` torchrun --nproc-per-node NUM_GPU train.py --cfg-path train_configs/tinygptv_stage1.yaml ``` You need to execute the above code 17 times to complete the first stage of training. * Then run: ``` torchrun --nproc-per-node NUM_GPU train.py --cfg-path train_configs/tinygptv_stage2.yaml ``` **Stage 3:** * Datasets: [stage 3 dataset preparation instruction](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/dataset/README_2_STAGE.md) * Then run: ``` torchrun --nproc-per-node NUM_GPU train.py --cfg-path train_configs/tinygptv_stage3.yaml ``` **Stage 4:** * Datasets: [stage 4 dataset preparation instruction](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/dataset/README_MINIGPTv2_FINETUNE.md). * Then run: ``` torchrun --nproc-per-node NUM_GPU train.py --cfg-path train_configs/tinygptv_stage4.yaml ``` ### Evaluation For eval. details of TinyGPT-V, check [here](eval_scripts/EVAL_README.md) ## Star History [](https://star-history.com/#DLYuanGod/TinyGPT-V&Date) ## Acknowledgement + [MiniGPT](https://github.com/Vision-CAIR/MiniGPT-4) A very versatile model of MLLMs. If you're using TinyGPT-V in your research or applications, please cite using this BibTeX: ```bibtex @misc{yuan2024tinygptv, title={TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones}, author={Zhengqing Yuan and Zhaoxu Li and Weiran Huang and Yanfang Ye and Lichao Sun}, year={2024}, eprint={2312.16862}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` ## License This repository is under [BSD 3-Clause License](LICENSE.md). Many codes are based on [Lavis](https://github.com/salesforce/LAVIS) with BSD 3-Clause License [here](LICENSE_Lavis.md). ", Assign "at most 3 tags" to the expected json: {"id":"6501","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"