|
--- |
|
license: apache-2.0 |
|
tags: |
|
- setfit |
|
- sentence-transformers |
|
- text-classification |
|
pipeline_tag: text-classification |
|
--- |
|
|
|
# moshew/gte_tiny_setfit-sst2-english |
|
|
|
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) ("TaylorAI/gte-tiny") with contrastive learning. |
|
2. Training a classification head with features from the fine-tuned Sentence Transformer. |
|
|
|
## Training code |
|
|
|
```python |
|
from setfit import SetFitModel |
|
|
|
from datasets import load_dataset |
|
from setfit import SetFitModel, SetFitTrainer |
|
|
|
# Load a dataset from the Hugging Face Hub |
|
dataset = load_dataset("SetFit/sst2") |
|
|
|
# Upload Train and Test data |
|
num_classes = 2 |
|
test_ds = dataset["test"] |
|
train_ds = dataset["train"] |
|
|
|
model = SetFitModel.from_pretrained("TaylorAI/gte-tiny") |
|
trainer = SetFitTrainer(model=model, train_dataset=train_ds, eval_dataset=test_ds) |
|
|
|
# Train and evaluate |
|
trainer.train() |
|
trainer.evaluate()['accuracy'] |
|
|
|
``` |
|
|
|
## 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("moshew/gte_tiny_setfit-sst2-english") |
|
# Run inference |
|
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) |
|
``` |
|
|
|
## Accuracy |
|
On SST-2 dev set: |
|
90.7% SetFit |
|
85.5% (no Fine-Tuning) |
|
|
|
## 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} |
|
} |
|
``` |
|
|
