Downloads · 30 days
37
35% of all-time downloads
schift-nli
schift-io/schift-nli
schift-nli is a zero-shot classification model from schift-io. Use it when you need labels you did not train the model on. It is set up for transformers.js. The card lists the license as apache-2.0.
ONNX-quantized DeBERTa-v3-xsmall for Natural Language Inference, optimized for Dot local inference.
All-time downloads
106
Public
Repo size
1.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx1.3 GB · 99%
At a glance
- Task
- Zero-Shot Classification
- Library
- transformers.js
- License
- apache-2.0
- Model type
- deberta-v2
- Access
- Public
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026
- SHA
- b150f365
Try a prompt
Base models
Model card
From the Hugging Face model README
schift-nli
ONNX-quantized DeBERTa-v3-xsmall for Natural Language Inference, optimized for Dot local inference.
- Base model: cross-encoder/nli-deberta-v3-xsmall
- ONNX source: Xenova/nli-deberta-v3-xsmall
- Parameters: 70.8M
- Labels: entailment, contradiction, neutral
- Use case: Intent routing, polarity detection, document pair classification
Usage in Dot
Loaded automatically by Dot's local NLI classifier. No manual setup needed.
Usage with Transformers.js
import { pipeline } from '@huggingface/transformers';
const classifier = await pipeline('text-classification', 'schift-io/schift-nli', {
quantized: true,
});
const result = await classifier(
{ text: 'A man is eating pizza', text_pair: 'A man is eating food' },
{ top_k: 3 }
);
// [{ label: 'entailment', score: 0.97 }, ...]
License
Apache 2.0 (inherited from base model)
- Task
- Zero-Shot Classification
- Library
- transformers.js
- Type
- deberta-v2
- License
- apache-2.0
- Languages
- en
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026