Vijay Janapa Reddi a348acf977 fix(package): Add PyTorch-style __call__ methods to exported modules ...

Resolved transformer training issues by adding __call__ methods to:
- Embedding, PositionalEncoding, EmbeddingLayer (text.embeddings)
- LayerNorm, MLP, TransformerBlock, GPT (models.transformer)
- MultiHeadAttention (core.attention)

This enables PyTorch-style syntax: model(x) instead of model.forward(x)
All transformer diagnostic tests now pass (5/5 ✓)

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-10-28 13:53:43 -04:00

..

__init__.py

Add exported package files and cleanup

2025-09-30 12:38:56 -04:00

embeddings.py

fix(package): Add PyTorch-style __call__ methods to exported modules

2025-10-28 13:53:43 -04:00

tokenization.py

fix: Add missing typing imports to Module 10 tokenization

2025-10-28 09:44:24 -04:00