A compact Dino for Retrieval

Overview

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

The whole setup fits in a single module on purpose.

Contact

Found a mistake? Open an issue — patches and pointers both welcome.

Evaluation guidance

A first evaluation could use Flickr30k. Report the metric across at least three seeds and include a matched-capacity baseline; keep logs and library versions with any published number.

Quick check

Run python finetune.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 included configuration uses adafactor 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.

Acknowledgments

Thanks to the maintainers of the open-source libraries this project leans on.

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.

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

File	Purpose
`finetune.py`	primary artifact
`README.md`	this documentation
`config.json`	architecture configuration
`training_args.json`	default experiment settings
`model.safetensors`	initialization checkpoint
`NOTES.md`	informal to-do notes
`examples/sample_usage.py`	usage sketch

License

Released under cc-by-4.0. Review the source-data terms separately when this repository is used with external datasets.

Downloads last month: -

Safetensors

Model size

24.8k params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support