Ribeiro87/swin-t-generation-light

Swin T experiments: Generation

Overview

A small Swin T implementation for Generation, packaged with an explicit configuration and an initialization checkpoint. The huge variant is a reproducible starting point, not a trained model release.

The whole setup fits in a single module on purpose.

Default experiment recipe

The included configuration uses novograd with a exponential 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.

Quick check

Run python run.py --help for the built-in smoke test. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.

Repository status

• Single-file implementation; the __main__ block runs a smoke test.
• config.json and training_args.json hold the generated settings.
• model.safetensors is freshly initialized — plumbing, not results.
• No benchmark numbers are reported on purpose.

Limitations

• weights are random-init, so outputs carry no signal
• robustness, fairness and domain transfer are untested
• the API may change without notice while the design settles

Evaluation guidance

A useful first evaluation would use a task-specific held-out set, 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.

Files

• 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 mit. Review the source-data terms separately when this repository is used with external datasets.