Bunny-v1_0-3B_dev

Model Card

Compared to BAAI/Bunny-v1_0-3B, this model is added a layer lm_head.bias of all-zeros for consistency with Phi-2.

Below is the original introduction of BAAI/Bunny-v1_0-3B.

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

📖 Technical report | 🏠 Code | 🐰 Demo

This is the merged weights of bunny-phi-2-siglip-lora.

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-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. Remarkably, our Bunny-v1.0-3B model built upon SigLIP and Phi-2 outperforms the state-of-the-art MLLMs, not only in comparison with models of similar size but also against larger MLLM frameworks (7B), and even achieves performance on par with 13B models.

The model is pretrained on LAION-2M and finetuned on Bunny-695K. More details about this model can be found in GitHub.

Quickstart

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

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
torch.set_default_device('cpu')  # or 'cuda'

# create model
model = AutoModelForCausalLM.from_pretrained(
    'BAAI/Bunny-v1_0-3B',
    torch_dtype=torch.float16,
    device_map='auto',
    trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
    'BAAI/Bunny-v1_0-3B',
    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], dtype=torch.long).unsqueeze(0)

# 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)

# generate
output_ids = model.generate(
    input_ids,
    images=image_tensor,
    max_new_tokens=100,
    use_cache=True)[0]

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

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

pip install torch transformers accelerate pillow

License

This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses. The content of this project itself is licensed under the Apache license 2.0.