---
title: Bunny-v1_0-4B
canonical_url: "https://www.modelscope.cn/models/BAAI/Bunny-v1_0-4B"
md_url: "https://www.modelscope.cn/models/BAAI/Bunny-v1_0-4B.md"
repository: BAAI/Bunny-v1_0-4B
last_updated: 2024-09-13
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - bunny-phi3
architectures:
  - BunnyPhi3ForCausalLM
parameters: 4.3B
tensor_type:
  - F16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 2159
stars: 0
---

# Bunny-v1_0-4B

> Bunny-v1_0-4B - BAAI 在 ModelScope 开源的模型。📖 Technical report | 🏠 Code | 🐰 Demo | 🤗 GGUF

BAAI/Bunny-v1_0-4B 是 ModelScope 魔搭社区上的 4.3B 参数text-generation模型，采用 apache-2.0 许可。

- **Repository**: BAAI/Bunny-v1_0-4B
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 4.3B
- **Downloads**: 2159
- **Stars**: 0
- **Last updated**: 2024-09-13

Source: https://www.modelscope.cn/models/BAAI/Bunny-v1_0-4B

---

# 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) | 🤗 [GGUF](https://huggingface.co/BAAI/Bunny-v1_0-4B-gguf)

This is Bunny-v1.0-4B.

We also provide v1.1 version accepting high-resolution images up to 1152x1152. 🤗 [v1.1](https://huggingface.co/BAAI/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-v1.0-4B, 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). More details about this model can be found in [GitHub](https://github.com/BAAI-DCAI/Bunny).

![comparison](comparison.png)


# 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_0-4B',
    torch_dtype=torch.float16, # float32 for cpu
    device_map='auto',
    trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
    'BAAI/Bunny-v1_0-4B',
    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())
```