ldnjones/swin-t-multitask

Multitask (Swin T)

Overview

This repository is a compact, custom PyTorch implementation of Swin T for Multitask. The giant configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release.

Default Experiment Recipe

The included configuration uses adam with a linear 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.

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.

Training Details

• Weights initialized with a xavier uniform scheme.
• Runs on a single consumer GPU.
• Full smoke test takes minutes, not hours.
• No distributed setup required.

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

Contact

Questions or corrections: open a discussion in this repository.

Files

File	Purpose
pipeline.py	primary artifact
README.md	this documentation
config.json	architecture configuration
training_args.json	default experiment settings
model.safetensors	initialization checkpoint

License

Released under apache-2.0. Review the source-data terms separately when this repository is used with external datasets.