Zero-Shot Classification
sentence-transformers
PyTorch
ONNX
Safetensors
Transformers
English
deberta-v2
text-classification
Instructions to use cross-encoder/nli-deberta-v3-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use cross-encoder/nli-deberta-v3-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("cross-encoder/nli-deberta-v3-base") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use cross-encoder/nli-deberta-v3-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="cross-encoder/nli-deberta-v3-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cross-encoder/nli-deberta-v3-base") model = AutoModelForSequenceClassification.from_pretrained("cross-encoder/nli-deberta-v3-base") - Notebooks
- Google Colab
- Kaggle
| epoch,steps,Accuracy | |
| 0,10000,0.8820267589153991 | |
| 0,20000,0.8944905122856998 | |
| 0,30000,0.9012056773668413 | |
| 0,40000,0.9000356107239151 | |
| 0,50000,0.9013074222923132 | |
| 0,-1,0.9053263468484509 | |
| 1,10000,0.9055807091621305 | |
| 1,20000,0.9055298366993946 | |
| 1,30000,0.9100574858828916 | |
| 1,40000,0.9062929236404335 | |
| 1,50000,0.9110240626748741 | |
| 1,-1,0.9111766800630818 | |
| 2,10000,0.9096505061810042 | |
| 2,20000,0.9126011090196876 | |
| 2,30000,0.9081243322989266 | |
| 2,40000,0.9110240626748741 | |
| 2,50000,0.9113292974512897 | |
| 2,-1,0.9154499669328993 | |
| 3,10000,0.9114819148394974 | |
| 3,20000,0.9113801699140255 | |
| 3,30000,0.9134659408861983 | |
| 3,40000,0.9135676858116701 | |
| 3,50000,0.9157043292465789 | |
| 3,-1,0.9153482220074274 | |