This is the Linux app named ToMe (Token Merging) whose latest release can be downloaded as ToMesourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named ToMe (Token Merging) with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS
Ad
ToMe (Token Merging)
DESCRIPTION
ToMe (Token Merging) is a PyTorch-based optimization framework designed to significantly accelerate Vision Transformer (ViT) architectures without retraining. Developed by researchers at Facebook (Meta AI), ToMe introduces an efficient technique that merges similar tokens within transformer layers, reducing redundant computation while preserving model accuracy. This approach differs from token pruning, which removes background tokens entirely; instead, ToMe merges tokens based on feature similarity, allowing it to compress both foreground and background information efficiently. ToMe integrates seamlessly into existing transformer models such as DeiT, MAE, SWAG, and timm ViTs, offering 2–3x speedups during inference and substantial efficiency gains during training. The method can be applied dynamically at inference time or incorporated into training for improved performance.
Features
- Supported for both ImageNet evaluation and research extensions
- Open source PyTorch patching tools for quick integration
- Offers pretrained checkpoints for DeiT, ViT-B/L/H, and MAE models
- Can be applied without retraining or integrated during training for better results
- Compatible with timm, SWAG, and MAE ViT implementations
- Provides 2–3× inference speedup with minimal accuracy loss
- Token Merging algorithm for accelerating Vision Transformers
Programming Language
Python
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/tome-token-merging.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
