latincy
/

latin-bert

feature-extraction

Model card Files Files and versions

latin-bert / src /latincy_latinbert

11.7 kB

Ctrl+K

Ctrl+K

3 contributors

History: 2 commits

diyclassics's picture

Fix tokenizer ID offset: reserve IDs 0-4 for BERT special tokens

ce59834 about 2 months ago

__init__.py

177 Bytes
Initial: HF-compatible Latin BERT tokenizer (Bamman & Burns 2020) about 2 months ago
tokenization_latin_bert.py

11.2 kB
Fix tokenizer ID offset: reserve IDs 0-4 for BERT special tokens about 2 months ago
tokenizer_config.json

315 Bytes
Fix tokenizer ID offset: reserve IDs 0-4 for BERT special tokens about 2 months ago