This is a RoBERTa model pre-trained on Classical Chinese texts, derived from GuwenBERT-large. Character-embeddings are enhanced into traditional/simplified characters. You can fine-tune
roberta-classical-chinese-large-char for downstream tasks, such as sentence-segmentation, POS-tagging, dependency-parsing, and so on.
from transformers import AutoTokenizer,AutoModelForMaskedLM tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char") model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char")
SuPar-Kanbun: Tokenizer POS-tagger and Dependency-parser for Classical Chinese
Select AutoNLP in the “Train” menu to fine-tune this model automatically.
- Downloads last month