---
inference: false
license: apache-2.0
---

# Model Card

<p align="center">
  <img src="./icon.png" alt="Logo" width="350">
</p>

📖 [Technical report](https://arxiv.org/abs/2402.11530) | 🏠 [Code](https://github.com/BAAI-DCAI/Bunny) | 🐰 [Demo](http://bunny.baai.ac.cn)

This is Bunny-v1.1-4B.

Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Phi-3-mini, Llama-3-8B, Phi-1.5, StableLM-2 and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.

We provide Bunny-v1.1-4B, which is built upon [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) and [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) with [S \\(^{2}\\)-Wrapper](https://github.com/bfshi/scaling_on_scales), supporting 1152x1152 resolution. More details about this model can be found in [GitHub](https://github.com/BAAI-DCAI/Bunny).

|                    | MME \\(^{\text{P}}\\) | MME \\(^{\text{C}}\\) | MMB \\(^{\text{T/D}}\\) | MMB-CN \\(^{\text{T/D}}\\) |SEED(-IMG) | MMMU \\(^{\text{V/T}}\\) | VQA \\(^{\text{v2}}\\) | GQA  | SQA \\(^{\text{I}}\\) | POPE |
| ------------------ | :--------------: | :--------------: |:--------------: | :----------------: | :--: | :-----------------: | :---------------: | :--: | :--------------: | :--: |
| Bunny-v1.1-4B |      1503.9      |      362.9      |     74.1/74.1   |66.3/64.8  | 64.6(71.7) |      40.2/38.8      |       81.7       | 63.4 |       76.3       | 87.0 |




# Quickstart

Here we show a code snippet to show you how to use the model with transformers.

Before running the snippet, you need to install the following dependencies:

```shell
pip install torch transformers accelerate pillow
```
If the CUDA memory is enough, it would be faster to execute this snippet by setting `CUDA_VISIBLE_DEVICES=0`.

Users especially those in Chinese mainland may want to refer to a HuggingFace [mirror site](https://hf-mirror.com).

```python
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import warnings

# disable some warnings
transformers.logging.set_verbosity_error()
transformers.logging.disable_progress_bar()
warnings.filterwarnings('ignore')

# set device
device = 'cuda'  # or cpu
torch.set_default_device(device)

# create model
model = AutoModelForCausalLM.from_pretrained(
    'BAAI/Bunny-v1_1-4B',
    torch_dtype=torch.float16, # float32 for cpu
    device_map='auto',
    trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
    'BAAI/Bunny-v1_1-4B',
    trust_remote_code=True)

# text prompt
prompt = 'Why is the image funny?'
text = f"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>\n{prompt} ASSISTANT:"
text_chunks = [tokenizer(chunk).input_ids for chunk in text.split('<image>')]
input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1][1:], dtype=torch.long).unsqueeze(0).to(device)

# image, sample images can be found in images folder
image = Image.open('example_2.png')
image_tensor = model.process_images([image], model.config).to(dtype=model.dtype, device=device)

# generate
output_ids = model.generate(
    input_ids,
    images=image_tensor,
    max_new_tokens=100,
    use_cache=True,
    repetition_penalty=1.0 # increase this to avoid chattering
)[0]

print(tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip())
```