jrz97619761/test-model-thing
A small proof-of-concept language model (not an LLM) incorporating latent-space prediction, internal state using recurrent trace units, and byte-by-byte output, built with MLX.
GitHub repository with 301 stars and 56 forks.
Language: Python
Topics: ai, apple-silicon, artificial-intelligence, bytes, continual-learning, jepa, language-model, language-models, latent-space, machine-learning