| ---
|
| license: mpl-2.0
|
| tags:
|
| - pytorch
|
| - hybrid
|
| - multitask
|
| - wip
|
| - prototype
|
| ---
|
|
|
| # Hybrid experiments: Multitask
|
|
|
| ## Overview
|
|
|
| This repository is a compact, custom PyTorch implementation of **Hybrid** for **Multitask**. The **small** configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release.
|
|
|
| Feedback on the structure is welcome; the code is intentionally short.
|
|
|
| ## 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.
|
|
|
| ## Quick Check
|
|
|
| Run `python model.py --help` for the built-in smoke test. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.
|
|
|
| ## Default Experiment Recipe
|
|
|
| The generated recipe uses lamb with a step schedule.
|
|
|
| These values exist so the script runs end-to-end. A meaningful experiment needs its own tuning budget and at least three seeds.
|
|
|
| ## 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
|
|
|
| ## Files
|
|
|
| + `model.py` — primary artifact
|
| + `README.md` — this documentation
|
| + `config.json` — architecture configuration
|
| + `training_args.json` — default experiment settings
|
| + `model.safetensors` — initialization checkpoint
|
|
|
| ## License
|
|
|
| Released under **mpl-2.0**. Review the source-data terms separately when this repository is used with external datasets.
|
|
|
