Implements a hierarchical transformer for language modeling that operates directly on raw text without a tokenizer.

Byte Latent Transformer (BLT) LLM built from scratch in PyTorch — tokenizer-free, byte-level, trained end-to-end on TinyStories to 0.71 BPB. Clone & run.

Four-seed matched ASR feasibility study using an HSL byte-signal substrate and spectral lens. Open code, weights, controls, and limitations; not SOTA.

Tokenizer-free HSL text-to-speech feasibility prototype with open code and weights. Working synthesis evidence; formal perceptual evaluation remains open.

PyTorch transformer input from raw bytes with zero learned input parameters: no tokenizer, embedding table, or learned input projection.

Engram without a tokenizer

A tokenizer-free NLP library with T-FREE, CANINE, and byte-level approaches

Language-model proof of operation for HSL's zero-learned-parameter input path. Open code, weights, and documented limitations; not a SOTA claim.

Open HSL/HoLo research: a deterministic byte-native signal substrate tested across language, speech, and diffusion with matched controls and honest limits.

Deterministic, non-learned byte-to-HSL signal encoder for PyTorch: 27-D interpretable features, lossless byte codec, tests, controls, and GPU paths.