Zero-Shot Classification
sentence-transformers
PyTorch
JAX
ONNX
Safetensors
OpenVINO
Transformers
English
roberta
text-classification
Instructions to use cross-encoder/nli-distilroberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use cross-encoder/nli-distilroberta-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("cross-encoder/nli-distilroberta-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-distilroberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="cross-encoder/nli-distilroberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cross-encoder/nli-distilroberta-base") model = AutoModelForSequenceClassification.from_pretrained("cross-encoder/nli-distilroberta-base") - Notebooks
- Google Colab
- Kaggle
| epoch,steps,Accuracy | |
| 0,10000,0.8128608857121055 | |
| 0,20000,0.8258336936891105 | |
| 0,30000,0.8371785414493933 | |
| 0,40000,0.849668048737059 | |
| 0,50000,0.8555439676442906 | |
| 0,-1,0.854857171927861 | |
| 1,10000,0.8612418284028184 | |
| 1,20000,0.8619540609976344 | |
| 1,30000,0.8658459033907359 | |
| 1,40000,0.8682115330806603 | |
| 1,50000,0.8688474550403175 | |
| 1,-1,0.8696614351486786 | |