Small character level GPT built from scratch in PyTorch and trained on Tiny Shakespeare text. It has 10.8M params, measured val loss 1.48 vs 2.48 for a bigram model
TinyBard: a 2.8M-parameter, character-level language model built from scratch in PyTorch with modern Llama-style components (RMSNorm, RoPE, grouped-query attention, SwiGLU), trained on Tiny Shakespeare.
A modern, from-scratch implementation of a GPT model featuring state-of-the-art techniques like RoPE, GQA, and Sparse Mixture of Experts (MoE).
Learning reproduction: a Colab TinyGPT exercise trained on Tiny Shakespeare, not presented as an original nanoGPT implementation.
A controlled comparison of character-level language models on Tiny Shakespeare: bigram vs LSTM vs transformer, with an in-browser demo.
Decoder-only Transformer language model built from scratch with PyTorch — 4 layers, 8 heads, character-level tokenizer, trained on Tiny Shakespeare (~6M params, loss 8.69→0.83 over 5 epochs on P100). Foundational educational project; see STATUS.md.
To associate your repository with the tiny-shakespeare topic, visit your repo's landing page and select "manage topics."