Pure C implementation of the complete Transformer architecture from Attention Is All You Need, assembling embeddings, positional encoding, encoder stack, decoder layers, multi-head attention, and token prediction from modular components built entirely from scratch.
c nlp word-embeddings transformer sequence-to-sequence layer-normalization encoder-decoder attention-is-all-you-need multi-head-attention positional-encoding llm cross-attention masked-attention transformers-in-c
-
Updated
Jul 17, 2026 - C