Harmon-1.5B-ReAlign (Paper Coming Soon)

A self-supervised training framework that aligns understanding and generation in modest compute, with huge zero-shot gain on generation and editing capability.

This repository hosts the model weights for Harmon-1.5B-ReAlign. For installation, usage instructions, and further documentation, please visit Harmon's original GitHub repository.

🧠 Method

Coming soon! Stay tuned~

📊 Benchmarks

Model	GenEval ↑	DPGBench ↑	WISE ↑
Harmon-1.5B	0.73	80.93	0.41
Harmon-1.5B-ReAlign	0.86	87.21	0.50

License

Harmon-1.5B-ReAlign is licensed under the Apache 2.0 license.

✍️ Citation

Coming soon!