Model2Vec Size Improvements
In this blogpost, we showcase the various size reduction techniques we implemented in Model2Vec, and how they can be combined to create tiny models (~6mb) with minimal performance loss.
Minish Lab
8 posts by Minish Lab
Model2Vec as a fasttext alternative
In this blogpost, we compare Model2Vec and fastText. We show that Model2Vec is faster, smaller, and more performant.
Tokenlearn 0.2.0
We’ve released a new version of Tokenlearn! It contains usability improvements, fixes some bugs, and has a new learning algorithm under the hood that improves performance. Read on to see what it does and how you can use it.
New improvements to model2vec distillation
We’ve made a lot of improvements to Model2Vec since it came out, many of which target the baseline performance of our distillation process. In this post, we walk through each change and explain why it matters for making your models smaller and faster.
ModernBERT support and why it doesn't work
Our newest shiny release is here! 0.3.8! This is a small release in line for a big one we’ll be releasing next week. See here for the release notes, and read on for details about ModernBERT compatibility (spoiler: it’s trickier than you’d think).
semhash: deduplication and dataset multitool
We’re super excited to announce the release of semhash, our semantic deduplication and dataset multitool (other features coming soon).
POTION: bag of tricks leads to better models
This blogpost describes the Tokenlearn method, which is a method to pre‐train Model2Vec models.
Model2Vec Introduction blogpost
This blog was first posted on the Hugging Face blog. We’re also posting it here for archival purposes.