Downloads · 30 days
308
9% of all-time downloads
deberta-v3-base-tasksource-nli
Xenova/deberta-v3-base-tasksource-nli
deberta-v3-base-tasksource-nli is a zero-shot classification model from Xenova. Use it when you need labels you did not train the model on. It is set up for transformers.js.
https://huggingface.co/sileod/deberta-v3-base-tasksource-nli with ONNX weights to be compatible with Transformers.js.
All-time downloads
3.4K
Public
Repo size
3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx3 GB · 100%
At a glance
- Task
- Zero-Shot Classification
- Library
- transformers.js
- Model type
- deberta-v2
- Access
- Public
- Created
- Aug 8, 2023
- Updated
- Jul 11, 2025
- SHA
- b2f7405d
Try a prompt
Base models
Model card
From the Hugging Face model README
https://huggingface.co/sileod/deberta-v3-base-tasksource-nli with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformers
Example: Zero-shot text classification.
import { pipeline } from '@huggingface/transformers';
const classifier = await pipeline('zero-shot-classification', 'Xenova/deberta-v3-base-tasksource-nli');
const output = await classifier('I love transformers!', {
candidate_labels: ['positive', 'negative']
});
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
- Task
- Zero-Shot Classification
- Library
- transformers.js
- Type
- deberta-v2
- Created
- Aug 8, 2023
- Updated
- Jul 11, 2025