← Latest products

Linear RNN/Reservoir hybrid generative model

one C file (no deps.). I just noticed it takes literally ~5 minutes to train millions parameters on slow CPU...but before you call Yudkowsky that "it's over", an important note: the main bottleneck is the corpus size, params are just 'cleverness' but given limited info it's powerless.

Visit raw.githubusercontent.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Self-growing neural networks via a custom Rust-to-LLVM compiler

    github.com

    A systems programming language where automatic differentiation is a compiler pass and model parameters are explicit, growable memory.

    Hacker News8 pts

  2. i

    github.com

    An experimental tensor DSL/compiler with explicit scheduling

    Hacker News5 pts

  3. I built a tiny LLM to demystify how language models work

    github.com

    A ~9M parameter LLM that talks like a small fish.

    Hacker News915 pts

  4. Minimum Description Length RNNs in PyTorch

    github.com

    Minimum Description Length Recurrent Neural Networks (MDLRNNs) in PyTorch

    Hacker News7 pts

  5. Speeding up LLM inference 2x times (possibly)

    asciinema.org

    Here's a project I've been working on for the last few months.

    Hacker News419 pts