A complete implementation of a Decoder-Only Transformer (GPT-style) built using PyTorch, without relying on high-level abstractions. This implementation includes all core components: token embeddings, positional embeddings, multi-head self-attention, feedforward networks, causal masking, and output logits generation.
Decoder-only GPT-style Transformer for autoregressive language modeling with BPE tokenization, supporting greedy, temperature, top-k, and nucleus sampling
Small educational C++20 character-level language model with a tiny automatic-differentiation engine, training/generation CLIs, and checkpointing.
Add a description, image, and links to the decoder-only-transformer topic page so that developers can more easily learn about it.
To associate your repository with the decoder-only-transformer topic, visit your repo's landing page and select "manage topics."