---
title: README
emoji: 📊
colorFrom: red
colorTo: yellow
sdk: static
pinned: false
---

## Hello, we're minish!

We're a two-person ([@pringled](https://github.com/Pringled) and [@stephantul](https://github.com/stephantul)) open-source company, with a focus on Natural Language Processing.

We believe that if you make models fast enough, you unlock new possibilities.

Using our software, you can:
* Ingest the entire English Wikipedia in 5 minutes
* Classify tens of thousands of documents per second on 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

Our projects:

* [model2vec](https://github.com/MinishLab/model2vec): make tiny models that are still really really good.
* [potion](https://huggingface.co/minishlab/potion-base-8M): the best small model in the world. 100-500x faster than a sentence-transformer, and almost as good.
* [vicinity](https://github.com/MinishLab/vicinity): consistent interfaces to many approximate nearest neighbor algorithms.
* [semhash](https://github.com/MinishLab/semhash): lightning-fast, super accuracte, approximate deduplication for your text datasets.

You can also find us on: 
🔬 [GitHub](https://github.com/MinishLab)
👽 [LinkedIn](https://www.linkedin.com/company/minish-lab/)