Token Classification
Transformers
PyTorch
TensorFlow
TensorBoard
Safetensors
Russian
bert
PyTorch
Transformers
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("bond005/rubert-multiconer")
model = AutoModelForTokenClassification.from_pretrained("bond005/rubert-multiconer")Quick Links
RuBERT-MultiCoNER
This is a BERT-based named entity recognizer for extracting named entities in Russian texts. Entities of the following six classes can be recognized:
- Persons, i.e. names of people (PER)
- Locations or physical facilities (LOC)
- Corporations and businesses (CORP)
- All other groups (GRP)
- Consumer products (PROD)
- Titles of creative works like movie, song, and book titles (CW).
- Downloads last month
- 55
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="bond005/rubert-multiconer")