metadata
library_name: transformers
tags:
- Danish
- Mixed Tokenization
- LLaMA
_______ ___ .___ ___. ______ .______ .______ __ __
| \ / \ | \/ | / __ \ | _ \ | _ \ | | | |
| .--. | / ^ \ | \ / | | | | | | |_) | | |_) | | |__| |
| | | | / /_\ \ | |\/| | | | | | | / | ___/ | __ |
| '--' | / _____ \ | | | | | `--' | | |\ \----.| | | | | |
|_______/ /__/ \__\ |__| |__| \______/ | _| `._____|| _| |__| |__|
DA-MIXED-LLAMA3.2
An experimental model built on the LLaMA-3.2 architecture, combining morphological and BPE tokenization strategies. This model investigates the effects of mixed tokenization on Danish language understanding and generation.