File size: 356 Bytes
c05e186
 
2e4a575
c05e186
2e4a575
584ff6e
7ea989e
584ff6e
1
2
3
4
5
6
7
8
---
library_name: transformers
tags: [Danish, Morphological Tokenization, CerebrasGPT]
---

### DA-MORPH-CEREBRAS

This experimental model, built on the CerebrasGPT-111M architecture, uses a custom morphological tokenizer specifically designed for Danish. It explores the impact of morphology-aware tokenization on Danish text generation and understanding.