Downloads · 30 days
38
18% of all-time downloads
harshag11/zero-shot-wikidata-classifier
zero-shot-wikidata-classifier is a zero-shot classification model from harshag11. Use it when you need labels you did not train the model on. The card lists the license as mit.
This model performs zero-shot text classification by dynamically integrating knowledge from Wikidata. It classifies text into custom categories without requiring training data.
Downloads · 30 days
38
18% of all-time downloads
All-time downloads
208
Public
Parameters
407M
1.6 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors1.6 GB · 100%
From the Hugging Face model README
This model performs zero-shot text classification by dynamically integrating knowledge from Wikidata. It classifies text into custom categories without requiring training data.
from transformers import pipeline
from wikidata import get_wikidata_labels
classifier = pipeline("zero-shot-classification",
model="your-username/zero-shot-wikidata-classifier")
# Classify with Wikidata expansion
labels = get_wikidata_labels("renewable energy")
result = classifier("Perovskite solar cells achieve 30% efficiency",
candidate_labels=labels)