metadata

license: apache-2.0
tags:
  - setfit
  - text-classification
pipeline_tag: text-classification
datasets:
  - banking77
widget:
  - text: 'Can I track the card you sent to me? '
    example_title: Card Arrival Example
  - text: Can you explain your exchange rate policy to me?
    example_title: Exchange Rate Example
  - text: I can't pay by my credit card
    example_title: Card Not Working Example
metrics:
  - accuracy
  - f1

nickprock/setfit-banking77

This is a SetFit model that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:

Fine-tuning a Sentence Transformer with contrastive learning.
Training a classification head with features from the fine-tuned Sentence Transformer.

Train Hyperparameters

Simulate the few-shot regime by sampling 25 examples per class
Sentence Transformer checkpoint: "sentence-transformers/paraphrase-distilroberta-base-v2"
Number of text pairs to generate for contrastive learning: 10
Epochs: 1
Batch size: 32

Metrics on Evaluation set

accuracy score: 0.8529
f1 score: 0.8527

Usage

To use this model for inference, first install the SetFit library:

python -m pip install setfit

You can then run inference as follows:

from setfit import SetFitModel

# Download from Hub and run inference
model = SetFitModel.from_pretrained("nickprock/setfit-banking77")
# Run inference
preds = model(["I can't pay by my credit card"])

BibTeX entry and citation info

@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}