Token Classification
Transformers
PyTorch
Ukrainian
roberta
ukrainian
pos
ubertext
dependency-parsing
Instructions to use KoichiYasuoka/roberta-base-ukrainian-upos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KoichiYasuoka/roberta-base-ukrainian-upos with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="KoichiYasuoka/roberta-base-ukrainian-upos")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-ukrainian-upos") model = AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-base-ukrainian-upos", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 674 Bytes
bc6ccab | 1 2 3 4 5 6 7 8 9 10 | #! /usr/bin/python3
src="KoichiYasuoka/roberta-base-ukrainian"
tgt="KoichiYasuoka/roberta-base-ukrainian-upos"
import os,sys
os.system("test -d UD_Ukrainian-IU || git clone --depth=1 https://github.com/UniversalDependencies/UD_Ukrainian-IU")
os.system("test -d UD_Ukrainian-ParlaMint || git clone --depth=1 https://github.com/UniversalDependencies/UD_Ukrainian-ParlaMint")
os.system("for F in train dev test ; do cat UD_Ukrainian-*/*-$F.conllu > $F.conllu ; done ; cat *.conllu > train.upos")
os.system(f"{sys.executable} -m esupar.train {src} {tgt} -16 /tmp train.upos")
os.system(f"{sys.executable} -m esupar.train {tgt} {tgt} 16 /// train.conllu dev.conllu test.conllu")
|