Loading…
Loading…
A small ViT implementation for Classification, packaged with an explicit configuration and an initialization checkpoint. The xlarge variant is a reproducible starting point, not a trained model release.
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.| Item | Value |
|---|---|
| Architecture | ViT |
| Scale | xlarge |
| Attention | dilated |
| Fusion | cross attention |
| Activation | gelu |
| Normalization | layernorm |
The included configuration uses lion 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.
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.
A useful first evaluation would use a task-specific labeled split, report the task metric across at least three seeds, and include a matched-capacity baseline. Keep training logs and environment versions with any published result.
The initialization checkpoint has not been trained or audited for robustness, fairness, or domain transfer. The implementation should be treated as an experimental starting point. Results from a future trained checkpoint must be documented separately from the defaults shipped here.
run.py — primary artifactREADME.md — this documentationconfig.json — architecture configurationtraining_args.json — default experiment settingsmodel.safetensors — initialization checkpointReleased under mit. Review the source-data terms separately when this repository is used with external datasets.