Skip to main content
Hello, we’re Minish! We’re an open-source lab, with a focus on building small, efficient, and effective models for natural language processing. The lab is currently maintained by pringled, and was originally founded by pringled and stephantul. Our goal is to make state-of-the-art NLP accessible to everyone, regardless of their resources or expertise. We believe that if you make models fast enough, you unlock new possibilities. Using our software, you can:
  • Embed the entire English Wikipedia in 5 minutes
  • Classify tens of thousands of documents per second on a CPU
  • Approximately deduplicate extremely large datasets in minutes
  • Build the fastest RAG application in the world
  • Easily evaluate which ANN algorithm works best for your data