|
--- |
|
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](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: |
|
|
|
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. |
|
2. 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: |
|
|
|
```bash |
|
python -m pip install setfit |
|
``` |
|
|
|
You can then run inference as follows: |
|
|
|
```python |
|
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 |
|
|
|
```bibtex |
|
@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} |
|
} |
|
``` |