Our own 'transformers' — a from-scratch neural-network framework built on Fisher-Rao geometry (simplex attention, unbounded Fourier features, recursive Φ-integration) instead of Euclidean dot-products.
License Sources
| Source | License | Class |
|---|---|---|
Licensie (detected) | Pending | - |
PyPI (reported) | Proprietary | Unknown |
License detection is still in progress for this version.
Loading dependencies…