Minish

Building Model2Vec, Semble, SemHash, and the Potion embedding models. GitHub: HuggingFace:

[Minish @minishlab]

- JSON output: CLI and MCP results are now structured JSON, making Semble easier to use from agents and scripts.
- Better file control: use `.sembleignore` to exclude files or force-include custom extensions.

Release notes: https://t.co/H4rO6DTC4O

[Minish @minishlab]

We’ve just released Semble v0.3.0!

Biggest changes:

- Automatic disk caching: First search builds the index; later searches are (much) faster.
- Search more than code: new `--content` flag for searching docs, config, code, or all of them together.

🧵

[Minish @minishlab]

@CommonSenseTOC Hey, thanks! This is something we are actively working on and we will likely release docs search for Semble soon.

[Minish @minishlab]

Today we're releasing Semble, a fast and accurate code search library built for agents 🤖!

We're also releasing potion-code-16M, a small code-specialized static embedding model that powers Semble.

🧵

[Minish @minishlab]

Semble: https://t.co/wlswINJe6r

Benchmarks: https://t.co/YrKz8uO3nN

How it works: https://t.co/lHajTrLHkL

Model: https://t.co/d4DpJDzIJ1

[Minish @minishlab]

Main features:
- Fast: indexes a full codebase in ~250 ms and answers queries in ~1.5 ms, all on CPU
- Accurate: on par with transformers
- MCP server: drop-in tool for Claude Code, Cursor, Codex, OpenCode, and any other MCP-compatible agent
- Zero setup: no API keys, no GPU

🧵

[Minish @minishlab]

We also have a new blogpost on model size reduction where we showcase how to reduce model size by a factor of 15, creating a 6MB model (!) without impacting performance.

Links:
Release notes: https://t.co/wVsFOqQLT4

Blogpost: https://t.co/lPJFuCWvEo

[Minish @minishlab]

Model2Vec 0.7.0 is out now, as well as a blogpost on model size reduction techniques!

This release features a large number of ways to improve the distillation process.
- Vocabulary quantization
- Configurable pooling
- A number of small improvements and bugfixes

🧵

[Minish @minishlab]

@casper_hansen_ Thanks for the feedback (and for using SemHash)! That's a good idea, we can add something to our readme. There's also a HF space where you can use it directly on the hub: https://t.co/FFvqw29Qpz

[Casper Hansen @casper_hansen_]

semhash is so so so convenient and fast

[Minish @minishlab]

We have a new website (and name): https://t.co/4Zdi049lCy

We’ve been working on an improved website for a while, and it’s finally here. It has documentation for all our packages as well as our blog. More things coming soon! 🚀

[slm tokens @tulkenss]

Some guy forked our "model2vec-rs" crate, and put it under the "model2vec" name on crates io and then didn't tell us about it. See here: https://t.co/4IZHlJB5wV

Like what's the goal here except name squatting.

[Minish @minishlab]

- Smaller tokenizers: all tokenizers are now 40% smaller, at no cost to anyone.

A blog post with experimental results is coming in the next couple of days.

[Minish @minishlab]

We just released model2vec 0.6.0!

This is a big release, containing many big improvements 🔥

GitHub release: https://t.co/qj3aQCGfcg

PyPi release: https://t.co/dtMlfACXzR

🧵

[Minish @minishlab]

- Model improvements: nearly all distilled models will perform better, especially in STS and clustering tasks. A while ago we published a blog post on modernbert not working, but we now found out why, and fixed it!

🧵

[Minish @minishlab]

@tomaarsen Thanks for sharing our deduplication space! For those who are interested in applying this in their own workflows, this is powered by SemHash: https://t.co/wqmBc33kzy

[tomaarsen @tomaarsen]

The deduplication Space by @minishlab just got a fresh update, allowing you to remove near duplicates in (training) datasets.

Details in 🧵

[Minish @minishlab]

@ben_burtenshaw Thanks for sharing our deduplication space and adding some shiny new features! For those who are interested in applying this in their own workflows, this is powered by SemHash: https://t.co/wqmBc33kzy