Skip to content
#

causal-masking

Star

Here are 4 public repositories matching this topic...

syedhamzamohiuddin / -attention-is-all-you-need-tf2

Star 0

From paper to code: a rigorous Transformer implementation in TensorFlow 2 — real WMT14 data, Moses tokenizer, and causal masking done right.

natural-language-processing tensorflow machine-translation transformer attention-mechanism from-scratch tokenization encoder-decoder attention-is-all-you-need multi-head-attention transformer-architecture paper-implementation causal-masking natural-language-processing-nlp research-replication three-way-weight-tying shared-embeddings
  • Updated Jul 28, 2025

Aavya05 / transformer_from_scratch

Star 0

Fully vectorized Transformer decoder implemented from scratch in NumPy with causal masking, autoregressive training, and empirical O(n²) complexity analysis.

machine-learning deep-learning optimization numpy linear-algebra transformer scientific-computing neural-networks research-project vectorization numerical-methods attention-mechanism backpropagation cross-entropy computational-complexity multi-head-attention algorithmic-analysis autoregressive-models transformer-decoder causal-masking
  • Updated Feb 14, 2026
  • Python

Improve this page

Add a description, image, and links to the causal-masking topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the causal-masking topic, visit your repo's landing page and select "manage topics."

Learn more