MeganMoore/vit-finetuned

📘 ViT experiments: Contrastive

Overview

This is an experimental ViT codebase for Contrastive. It keeps the large setup intentionally manageable so architecture changes can be inspected before a full training run.

Repository Status

• The Python file contains the model and runnable example or training entry point.
• config.json records the generated architecture settings.
• training_args.json records the default experiment recipe.
• model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint.
• No benchmark score is claimed in this repository.

Architecture

Item	Value
Architecture	ViT
Scale	large
Attention	linear
Fusion	tucker
Activation	swish
Normalization	layernorm

Limitations

The checkpoint is untrained and unaudited. Treat the repository as an experimental starting point; anything learned from a future trained version must be documented separately.

Contact

Questions or corrections: open a discussion in this repository.

Quick Check

python run.py --help

Inspect the script's __main__ block for its generated smoke-test example. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.

Citation

@misc{vitexperimentscontra},
  title = {ViT experiments: Contrastive},
  year = {{2026}},
  publisher = {{Hugging Face}},
}

Default Experiment Recipe

The included configuration uses sgd with a constant warmup schedule. These are starting values in the script, not evidence of a completed run. For a meaningful evaluation, train all baselines with the same data exposure, tuning budget, and random seeds.

Files

File	Purpose
run.py	primary artifact
README.md	this documentation
config.json	architecture configuration
training_args.json	default experiment settings
model.safetensors	initialization checkpoint
USE_POLICY.md	use and redistribution notes

License

Released under cc-by-4.0. Review the source-data terms separately when this repository is used with external datasets.