|
--- |
|
license: apache-2.0 |
|
pipeline_tag: text-generation |
|
datasets: |
|
- liuhaotian/LLaVA-Pretrain |
|
- liuhaotian/LLaVA-Instruct-150K |
|
--- |
|
# 😈 Imp |
|
|
|
> A very small man can cast a very large shadow. |
|
> |
|
> ——*George R.R. Martin, A Clash of Kings* |
|
|
|
|
|
\[[Paper](https://arxiv.org/abs/2405.12107)\] [[Demo](https://xmbot.net/imp/)\] [[Github](https://github.com/MILVLG/imp)\] |
|
|
|
## Introduction |
|
|
|
The Imp project aims to provide a family of a strong multimodal `small` language models (MSLMs). Our `Imp-v1.5-3B-Phi2` is a strong MSLM with only **3B** parameters, which is build upon a small yet powerful SLM [Phi-2 ](https://huggingface.co/microsoft/phi-2)(2.7B) and a powerful visual encoder [SigLIP ](https://huggingface.co/google/siglip-so400m-patch14-384)(0.4B), and trained on 1M mixed dataset. |
|
|
|
As shown in the Table below, `Imp-v1.5-3B-Phi2` significantly outperforms the counterparts of similar model sizes, and even achieves slightly better performance than the strong LLaVA-7B model on various multimodal benchmarks. |
|
|
|
We release our model weights and provide an example below to run our model . Detailed technical report and corresponding training/evaluation code will be released soon on our [GitHub repo](https://github.com/MILVLG/imp). We will persistently improve our model and release the next versions to further improve model performance :) |
|
|
|
|
|
## How to use |
|
|
|
|
|
**Install dependencies** |
|
```bash |
|
pip install transformers # latest version is ok, but we recommend v4.36.0 |
|
pip install -q pillow accelerate einops |
|
``` |
|
|
|
You can use the following code for model inference. The format of text instruction is similar to [LLaVA](https://github.com/haotian-liu/LLaVA). A Colab page to run this example is provided [here](https://colab.research.google.com/drive/1EBYky6xIPjnlPppo2gZaiNK6gEsjXgom?usp=drive_link#scrollTo=2-VpU6QzWCVZ). Note that the example can only be run on GPUs currently. |
|
|
|
```Python |
|
import torch |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
from PIL import Image |
|
|
|
torch.set_default_device("cuda") |
|
|
|
#Create model |
|
model = AutoModelForCausalLM.from_pretrained( |
|
"MILVLG/Imp-v1.5-3B-Phi2", |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
trust_remote_code=True) |
|
tokenizer = AutoTokenizer.from_pretrained("MILVLG/Imp-v1.5-3B-Phi2", trust_remote_code=True) |
|
|
|
#Set inputs |
|
text = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\nWhat are the colors of the bus in the image? ASSISTANT:" |
|
image = Image.open("images/bus.jpg") |
|
|
|
input_ids = tokenizer(text, return_tensors='pt').input_ids |
|
image_tensor = model.image_preprocess(image) |
|
|
|
#Generate the answer |
|
output_ids = model.generate( |
|
input_ids, |
|
max_new_tokens=100, |
|
images=image_tensor, |
|
use_cache=True)[0] |
|
print(tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()) |
|
``` |
|
|
|
## Model evaluation |
|
We conduct evaluation on 9 commonly-used benchmarks, including 5 academic VQA benchmarks and 4 popular MLLM benchmarks, to compare our Imp model with LLaVA (7B) and existing MSLMs of similar model sizes. |
|
|
|
| Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE | MME(P) | MMB |MMBCN |MM-Vet| |
|
|:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:| |
|
| [LLaVA-v1.5-lora](https://huggingface.co/liuhaotian/llava-v1.5-7b) | 7B |79.10 | 63.00| 68.40 |58.20| 86.40 | 1476.9 | 66.10 |- |30.2| |
|
| [TinyGPT-V-3B](https://huggingface.co/Tyrannosaurus/TinyGPT-V) | 3B | - | 38.9 | - | - | -| - | - |- |-| |
|
| [LaVA-Phi-3B](https://github.com/zhuyiche/llava-phi) | 3B | 71.40 | - | 68.40 | 48.60 | 85.00 | 1335.1 | 59.80 |-|28.9| |
|
| [MobileVLM-3B](https://huggingface.co/mtgv/MobileVLM-3B) | 3B | - | 59.00 | 61.00 | 47.50 | 84.90 | 1288.9 | 59.60 |- |-| |
|
| [MiniCPM-V-3B](https://huggingface.co/mtgv/MobileVLM-3B) | 3B | - |- | - | - | - | 1452.0 | 67.9 | 65.3 |-| |
|
| [Bunny-3B](https://huggingface.co/visheratin/MC-LLaVA-3b) | 3B | 79.8 | 62.5 | 70.9 | - | 86.8| 1488.8 | 68.6 |- |-| |
|
| **Imp-v1.5-3B-Phi2** | 3B | **81.18** | **63.54** | **72.78**| **59.84** | **88.87**| **1446.4** | **72.94**| 46.65 |**43.3**| |
|
|
|
## License |
|
This project is licensed under the Apache License 2.0 - see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) file for details. |
|
|
|
## About us |
|
This project is maintained by the [MILVLG](https://github.com/MILVLG)@Hangzhou Dianzi University (HDU) led by Prof. Zhou Yu and Jun Yu, and is mainly developed by Zhenwei Shao and Xuecheng Ouyang. We hope our model may serve as a strong baseline to inspire future research on MSLM, as well as its derivative applications on mobile devices and robots. |
|
|
|
## Citation |
|
|
|
If you use our model or refer our work in your studies, please cite: |
|
|
|
```bibtex |
|
@article{imp2024, |
|
title={Imp: Highly Capable Large Multimodal Models for Mobile Devices}, |
|
author={Shao, Zhenwei and Yu, Zhou and Yu, Jun and Ouyang, Xuecheng and Lihao, Zheng and Zhenbiao, Gai and Mingyang, Wang and Jiajun, Ding}, |
|
journal={arXiv preprint arXiv:2405.12107}, |
|
year={2024} |
|
} |
|
``` |
