加载中…
加载中…
This repository is a compact, custom PyTorch implementation of Mae for Classification. The base configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained 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 | Mae |
| Scale | base |
| Attention | linear |
| Fusion | cross attention |
| Activation | mish |
| Normalization | batchnorm |
The included configuration uses rmsprop with a onecycle 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 train.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.
train.py — primary artifactREADME.md — this documentationconfig.json — architecture configurationtraining_args.json — default experiment settingsmodel.safetensors — initialization checkpointReleased under apache-2.0. Review the source-data terms separately when this repository is used with external datasets.