---
title: README
emoji: 🏆
colorFrom: blue
colorTo: red
sdk: static
pinned: false
---


ToMMeR is a lightweight probing model (~300K params) extracting emergent mention detection capabilities from early layers representations of any LLM backbone, achieving high Zero Shot recall across a wide set of NER benchmarks.
More information in the [associated ACL2026 paper](https://arxiv.org/abs/2510.19410)