--- license: apache-2.0 datasets: - Lin-Chen/ShareGPT4V - liuhaotian/LLaVA-Pretrain - liuhaotian/LLaVA-Instruct-150K language: - en - zh tags: - llava - vision-language - llm - lmm ---

TinyLLaVA: A Framework of Small-scale Large Multimodal Models

[![github](https://img.shields.io/badge/GitHub-TinyLLaVA-blue)](https://github.com/DLCV-BUAA/TinyLLaVABench) [![arXiv](https://img.shields.io/badge/Arxiv-2402.14289-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2402.14289) [![License](https://img.shields.io/badge/License-Apache%202.0-yellow)](https://github.com/PKU-YuanGroup/MoE-LLaVA/blob/main/LICENSE) ## 🎉 News * **[2024.02.25]** Update evaluation scripts and docs! * **[2024.02.25]** Data descriptions out. Release TinyLLaVA-1.5B and TinyLLaVA-2.0B! * **[2024.02.24]** Example code on inference and model loading added! * **[2024.02.23]** Evaluation code and scripts released! * **[2024.02.21]** Creating the [TinyLLaVABench](https://github.com/DLCV-BUAA/TinyLLavaBench) repository on GitHub! * **[2024.02.21]** Our paper: [TinyLLaVA: A Framework of Small-scale Large Multimodal Models](https://arxiv.org/abs/2402.14289) is out! * **[2024.01.11]** Our fist model [TinyLLaVA-1.4B](https://huggingface.co/bczhou/tiny-llava-v1-hf) is out! ## ⌛ TODO - [ ] Add support for Ollama and llama.cpp. - [ ] Developers' guide / How to build demo locally. - [x] Model Zoo descriptions. - [x] Examples and inference. - [x] Release code for training. - [x] Add descriptions for evaluation. - [x] Add descriptions for data preparation. - [x] Release TinyLLaVA-1.5B and TinyLLaVA-2.0B. - [x] Release TinyLLaVA-3.1B. - [x] Release the evaluation code and weights today(2024.2.23). ### 🔥 High performance, but with fewer parameters - Our best model, TinyLLaVA-3.1B, achieves better overall performance against existing 7B models such as LLaVA-1.5 and Qwen-VL. ## 🐳 Model Zoo ### Legacy Model - [tiny-llava-hf](https://huggingface.co/bczhou/tiny-llava-v1-hf) ### Pretrained Models - [TinyLLaVA-3.1B](https://huggingface.co/bczhou/TinyLLaVA-3.1B) - [TinyLLaVA-2.0B](https://huggingface.co/bczhou/TinyLLaVA-2.0B) - [TinyLLaVA-1.5B](https://huggingface.co/bczhou/TinyLLaVA-1.5B) ### Model Details | Name | LLM | Checkpoint | LLaVA-Bench-Wild | MME | MMBench | MM-Vet | SQA-image | VQA-v2 | GQA | TextVQA | |---------------|-------------------|------------------------------------------------|------------------|----------|---------|--------|-----------|--------|-------|---------| | TinyLLaVA-3.1B | Phi-2 | [TinyLLaVA-3.1B](https://huggingface.co/bczhou/TinyLLaVA-3.1B) | 75.8 | 1464.9 | 66.9 | 32.0 | 69.1 | 79.9 | 62.0 | 59.1 | | TinyLLaVA-2.0B | StableLM-2-1.6B | [TinyLLaVA-2.0B](https://huggingface.co/bczhou/TinyLLaVA-2.0B) | 66.4 | 1433.8 | 63.3 | 32.6 | 64.7 | 78.9 | 61.9 | 56.4 | | TinyLLaVA-1.5B | TinyLlama | [TinyLLaVA-1.5B](https://huggingface.co/bczhou/TinyLLaVA-1.5B) | 60.8 | 1276.5 | 55.2 | 25.8 | 60.3 | 76.9 | 60.3 | 51.7 | ## 🔧 Requirements and Installation We recommend the requirements as follows. 1. Clone this repository and navigate to LLaVA folder ```bash git clone https://github.com/DLCV-BUAA/TinyLLaVABench.git cd TinyLLaVABench ``` 2. Install Package ```Shell conda create -n tinyllava python=3.10 -y conda activate tinyllava pip install --upgrade pip # enable PEP 660 support pip install -e . ``` 3. Install additional packages for training cases ```Shell pip install -e ".[train]" pip install flash-attn --no-build-isolation ``` ### Upgrade to latest code base ```Shell git pull pip install -e . # if you see some import errors when you upgrade, please try running the command below (without #) # pip install flash-attn --no-build-isolation --no-cache-dir ``` ## 🔧 Quick Start
Load model ```Python from tinyllava.model.builder import load_pretrained_model from tinyllava.mm_utils import get_model_name_from_path from tinyllava.eval.run_tiny_llava import eval_model model_path = "bczhou/TinyLLaVA-3.1B" tokenizer, model, image_processor, context_len = load_pretrained_model( model_path=model_path, model_base=None, model_name=get_model_name_from_path(model_path) ) ```
## 🔧 Run Inference Here's an example of running inference with [TinyLLaVA-3.1B](https://huggingface.co/bczhou/TinyLLaVA-3.1B)
Run Inference ```Python from tinyllava.model.builder import load_pretrained_model from tinyllava.mm_utils import get_model_name_from_path from tinyllava.eval.run_tiny_llava import eval_model model_path = "bczhou/TinyLLaVA-3.1B" prompt = "What are the things I should be cautious about when I visit here?" image_file = "https://llava-vl.github.io/static/images/view.jpg" args = type('Args', (), { "model_path": model_path, "model_base": None, "model_name": get_model_name_from_path(model_path), "query": prompt, "conv_mode": "phi", "image_file": image_file, "sep": ",", "temperature": 0, "top_p": None, "num_beams": 1, "max_new_tokens": 512 })() eval_model(args) ```
### Important We use different `conv_mode` for different models. Replace the `conv_mode` in `args` according to this table: | model | conv_mode | |-------------------|---------------| | TinyLLaVA-3.1B | phi | | TinyLLaVA-2.0B | phi | | TinyLLaVA-1.5B | v1 | ## Evaluation To ensure the reproducibility, we evaluate the models with greedy decoding. See [Evaluation.md](https://github.com/DLCV-BUAA/TinyLLaVABench/blob/main/docs/Evaluation.md) ## ✏ Citation If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:. ```BibTeX @misc{zhou2024tinyllava, title={TinyLLaVA: A Framework of Small-scale Large Multimodal Models}, author={Baichuan Zhou and Ying Hu and Xi Weng and Junlong Jia and Jie Luo and Xien Liu and Ji Wu and Lei Huang}, year={2024}, eprint={2402.14289}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```