Pinned Loading

1. CLAP CLAP Public archive

   Contrastive Language-Audio Pretraining

   Python 87 4

2. humongous-rs humongous-rs Public

   A Rust pipeline for extracting HUMONGOUS, a dataset of web-based text extracted from Common Crawl and ready for multilingual language modeling.

   Rust 4

3. simple-parallel-transformer simple-parallel-transformer Public

   As it says on the tin, this repo has a simple implementation of a transformer model, with some borrowed efficiency improvements. The purpose is mainly pedagogical.

   Python 8

4. simple-diffusion-model simple-diffusion-model Public

   Pedagogical codebase for a simplified score-based generative model design, with training loop

   Python 39 10