vision-llama 0.0.6

Vision Llama - Pytorch

Vision LLama

Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta. PAPER LINK

install

$ pip install vision-llama

usage

import torch
from vision_llama import VisionLlamaBlock

# Create a random tensor of shape (1, 3, 224, 224)
x = torch.randn(1, 3, 224, 224)

# Create an instance of the VisionLlamaBlock model with the specified parameters
model = VisionLlamaBlock(768, 12, 3, 12)

# Print the shape of the output tensor when x is passed through the model
print(model(x).shape)

# Print the output tensor when x is passed through the model
print(model(x))

License

MIT

Citation

@misc{chu2024visionllama,
    title={VisionLLaMA: A Unified LLaMA Interface for Vision Tasks}, 
    author={Xiangxiang Chu and Jianlin Su and Bo Zhang and Chunhua Shen},
    year={2024},
    eprint={2403.00522},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

todo

• Implement the AS2DRoPE rope
• Implement the GSA attention