---
license: apache-2.0
pipeline_tag: text-generation
datasets:
- liuhaotian/LLaVA-Pretrain
- liuhaotian/LLaVA-Instruct-150K
---
# 😈 Imp

\[[Paper](https://arxiv.org/abs/2405.12107)\]  [[Demo](https://xmbot.net/imp/)\]  [[Github](https://github.com/MILVLG/imp)\]


## Introduction

The Imp project aims to provide a family of highly capable yet lightweight LMMs. Our `Imp-v1.5-4B-Phi3` is a strong lightweight LMMs with only **4B** parameters, which is build upon [Phi-3 ](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)(3.8B) and a powerful visual encoder [SigLIP ](https://huggingface.co/google/siglip-so400m-patch14-384)(0.4B), and trained on 1M mixed dataset.  


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). 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-v1.5-4B-Phi3", 
    torch_dtype=torch.float16, 
    device_map="auto",
    trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("MILVLG/Imp-v1.5-4B-Phi3", trust_remote_code=True)

#Set inputs
text = "<|user|>\n<image>\nWhat are the colors of the bus in the image?\n<|end|>\n<|assistant|>\n"
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 lightweight LMMs of similar model sizes.

| Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE |  MME(P) | MMB  |MMB_CN|MM-Vet|
|:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:|
| Bunny-v1.0-4B| 4B | **81.5** |**63.5** | 75.1|- | 86.7| 1495.2 |**73.5**  |-|-|
| **Imp-v1.5-4B-Phi3**| 4B | **81.5** | **63.5** | **78.0**|60.2 | **86.9**| **1507.7** |73.3  |61.1|44.6|



## 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.


## 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 Zheng, Lihao and Gai, Zhenbiao and Wang, Mingyang and Ding, Jiajun},
  journal={arXiv preprint arXiv:2405.12107},
  year={2024}
}
```