Metadata-Version: 2.4
Name: torchblocks-vp
Version: 2.0.1
Summary: Typed pluggable Transformer blocks with registries for attention, norm, feedforward, adapters, and position layers.
Author: F000NK, Voluntas Progressus
License-Expression: MIT
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.14
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.14
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.0.0

# torchblocks-vp

`torchblocks-vp` provides reusable neural building blocks on top of PyTorch.

It includes:

- registry-based module factories
- attention, normalization, feedforward, and adapter layers
- rotary position embeddings and convolutional blocks
- typed interfaces for downstream model packages

Install:

```bash
pip install torchblocks-vp
```
