# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("marcosgg/bert-base-gl-SLI-NER")
model = AutoModelForTokenClassification.from_pretrained("marcosgg/bert-base-gl-SLI-NER", device_map="auto")Quick Links
Named Entity Recognition (NER) model for Galician
This is a NER model for Galician (ILG/RAG spelling) which uses the standard 'enamex' classes: LOC (geographical locations); PER (people); ORG (organizations); MISC (other entities).
The model is based on BERT-base-gl-cased, which has been fine-tuned using custom splits of the SLI_NERC dataset. On the test split of this dataset (not used for training), the model obtained the following results (Precision/Recall/F-score): 87.69 / 89.7 / 88.68.
- Downloads last month
- 22
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="marcosgg/bert-base-gl-SLI-NER")