mehtaaarav5/mobilevit-retrieval-exp83

Mobilevit experiments: Retrieval

Overview

This is an experimental Mobilevit codebase for Retrieval. It keeps the xlarge setup intentionally manageable so architecture changes can be inspected before a full training run.

Default Experiment Recipe

Defaults: rmsprop optimizer, exponential schedule. Treat these as starting points; a real run should sweep learning rate and batch size before drawing conclusions.

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

Training Details

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

Changelog

• 2026-10-13 — initial upload
• 2026-10-21 — config and docs sync

Repository Status

• The Python file contains the model and runnable example or training entry point.
• 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.
• No benchmark score is claimed in this repository.

Files

• inference.py — primary artifact
• README.md — this documentation
• config.json — architecture configuration
• training_args.json — default experiment settings
• model.safetensors — initialization checkpoint

License

Released under bsd-3-clause. Review the source-data terms separately when this repository is used with external datasets.