---
language:
- en
datasets:
- mnli
- anli
- fever
- wanli
- ling
- amazonpolarity
- imdb
- appreviews
inference: false
pipeline_tag: zero-shot-classification
tags:
- NLI
- deberta-v3
license: mit
---

# ONNX version of MoritzLaurer/deberta-v3-base-zeroshot-v1

**This model is a conversion of [MoritzLaurer/deberta-v3-base-zeroshot-v1](https://huggingface.co/MoritzLaurer/deberta-v3-base-zeroshot-v1) to ONNX** format using the [🤗 Optimum](https://huggingface.co/docs/optimum/index) library.

`MoritzLaurer/deberta-v3-large-zeroshot-v1` is designed for zero-shot classification, capable of determining whether a hypothesis is `true` or `not_true` based on a text, a format based on Natural Language Inference (NLI).

## Usage

Loading the model requires the [🤗 Optimum](https://huggingface.co/docs/optimum/index) library installed.

```python
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer, pipeline


tokenizer = AutoTokenizer.from_pretrained("laiyer/deberta-v3-base-zeroshot-v1-onnx")
model = ORTModelForSequenceClassification.from_pretrained("laiyer/deberta-v3-base-zeroshot-v1-onnx")
classifier = pipeline(
    task="zero-shot-classification",
    model=model,
    tokenizer=tokenizer,
    top_k=None,
)

classifier_output = classifier("Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.", ["mobile", "website", "billing", "account access"])
print(classifier_output)
```