POINTS-Qwen-2-5-7B-Chat

POINTS-Qwen-2-5-7B-Chat

Introduction

We are excited to announce the first version of POINTS, which integrates recent advancement in vision-language model and new techniques proposed by researchers from WeChat AI.

<p align="center"> 🏠 <a href="https://github.com/WePOINTS/WePOINTS">Github</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/abs/2409.04828">Paper</a> &nbsp&nbsp </a> </p>

What's new in POINTS?

Key Innovations

1. Strong Baseline: We integrate the most recent advancement in vision-language model, i.e., CapFusion, Dual Vision Encoder, and Dynamic High Resolution, into POINTS.

2. Pre-training Dataset Filtering: We propose to filter the pre-training dataset using perplexity as a metric. Utilizing this filtering strategy, we can significantly reduce the size of the pre-training dataset and improve the performance of the model.

3. Model Soup: We propose to apply model soup to models, fine-tuned with different visual instruction tuning datasets, which can further significantly improve the performance of the model.

<p align="center"> <img src="https://github.com/user-attachments/assets/6af35008-f501-400a-a870-b66a9bf2baab" width="60%"/> <p>

How to use POINTS?

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import CLIPImageProcessor
from PIL import Image
import torch
import requests
from io import BytesIO


image_url = 'https://github.com/user-attachments/assets/83258e94-5d61-48ef-a87f-80dd9d895524'
response = requests.get(image_url)
image_data = BytesIO(response.content)
pil_image = Image.open(image_data)
prompt = 'please describe the image in detail'
model_path = 'WePOINTS/POINTS-Qwen-2-5-7B-Chat'
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path, trust_remote_code=True, device_map='cuda').to(torch.bfloat16)
image_processor = CLIPImageProcessor.from_pretrained(model_path)
generation_config = {
    'max_new_tokens': 1024,
    'temperature': 0.0,
    'top_p': 0.0,
    'num_beams': 1,
}
res = model.chat(
    pil_image,
    prompt,
    tokenizer,
    image_processor,
    True,
    generation_config
)
print(res)

Evaluation

Citation

If you find our work helpful, feel free to cite us:

@article{liu2024points,
  title={POINTS: Improving Your Vision-language Model with Affordable Strategies},
  author={Liu, Yuan and Zhao, Zhongyin and Zhuang, Ziyuan and Tian, Le and Zhou, Xiao and Zhou, Jie},
  journal={arXiv preprint arXiv:2409.04828},
  year={2024}
}

@article{liu2024rethinking,
  title={Rethinking Overlooked Aspects in Vision-Language Models},
  author={Liu, Yuan and Tian, Le and Zhou, Xiao and Zhou, Jie},
  journal={arXiv preprint arXiv:2405.11850},
  year={2024}
}