Minish (original) (raw)

Hello, we're Minish!

About us

We're a two-person (pringled and stephantul) open-source lab, with a focus on Natural Language Processing.

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

Using our models and packages, 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

Our projects:

• model2vec: tiny static embedding models with state-of-the-art performance.
• potion: the best small models in the world. 100-500x faster than a sentence-transformer, and almost as good.
• vicinity: consistent interfaces to many approximate nearest neighbor algorithms.
• semhash: lightning-fast, super accuracte, semantic deduplication and filtering for your text datasets.
• model2vec-rs: a Rust port of model2vec.

You can also find us on:

• 🤗 huggingface
• 👽 LinkedIn
• 💬 Discord

Pinned Loading

1. Fast State-of-the-Art Static Embeddings
   Python 2k 120
2. Fast Multimodal Semantic Deduplication & Filtering
   Python 909 56
3. Lightweight Nearest Neighbors with Flexible Backends
   Python 336 10
4. Pre-train Static Word Embeddings
   Python 98 8
5. Official Rust Implementation of Model2Vec
   Rust 167 17

Repositories

Showing 10 of 10 repositories

• model2vec-rs Public
  Official Rust Implementation of Model2Vec
  MinishLab/model2vec-rs’s past year of commit activity
  Rust
  167
  MIT
  17 0 1
  Updated Apr 10, 2026
• vicinity Public
  Lightweight Nearest Neighbors with Flexible Backends
  MinishLab/vicinity’s past year of commit activity
  Python
  336
  MIT
  10 1 1
  Updated Apr 10, 2026
• model2vec Public
  Fast State-of-the-Art Static Embeddings
  MinishLab/model2vec’s past year of commit activity
• MinishLab/docs’s past year of commit activity
  MDX 0
  2 0 0
  Updated Mar 30, 2026
• tokenlearn Public
  Pre-train Static Word Embeddings
  MinishLab/tokenlearn’s past year of commit activity
  Python
  98
  MIT
  8 1 0
  Updated Mar 27, 2026
• MinishLab/.github’s past year of commit activity
  0 0
  0 0
  Updated Mar 16, 2026
• semhash Public
  Fast Multimodal Semantic Deduplication & Filtering
  MinishLab/semhash’s past year of commit activity
  Python
  909
  MIT
  56 0 0
  Updated Jan 20, 2026
• evaluation Public
  Code to evaluate performance for embeddings
  MinishLab/evaluation’s past year of commit activity
  Python
  11
  MIT 0
  0 0
  Updated Sep 20, 2025
• MinishLab/minishlab.github.io’s past year of commit activity
  SCSS 0 MIT
  1 0 0
  Updated Jun 1, 2025
• MinishLab/watertemplate’s past year of commit activity
  Makefile
  4
  MIT
  3 0 1
  Updated Dec 9, 2024