---
title: README
emoji: 🌖
colorFrom: yellow
colorTo: gray
sdk: static
pinned: false
---

Model weights and datasets for "Small Model, Native Design: Exploring Linguistic Purity and Reduced Language Bleeding in a 100M Khmer Language Model" (AACL-IJCNLP 2026 Student Research Workshop). Code files can be found at the Github repo [sovannpanhaseng/aaclijcnlp2026](https://github.com/sovannpanhaseng/aaclijcnlp2026)