Setfit Model Paraphrase MiniLM L6 V2

🚀 SetFit with sentence-transformers/paraphrase-MiniLM-L6-v2

This is a SetFit model designed for text classification. It leverages the sentence-transformers/paraphrase-MiniLM-L6-v2 as its sentence transformer embedding model and a LogisticRegression instance for classification. The model is trained using an efficient few-shot learning technique, which includes fine-tuning a Sentence Transformer with contrastive learning and training a classification head with features from the fine-tuned Sentence Transformer.

✨ Features

• Few-shot Learning: Trained using an efficient few-shot learning technique.
• Text Classification: Capable of performing text classification tasks.

📦 Installation

First, install the SetFit library:

pip install setfit

💻 Usage Examples

Basic Usage

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("systemctl stop apache2")

📚 Documentation

Model Details

Model Description

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Evaluation

Metrics

Training Details

Training Set Metrics

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Framework Versions

• Python: 3.13.2
• SetFit: 1.1.2
• Sentence Transformers: 4.0.2
• Transformers: 4.51.0
• PyTorch: 2.6.0
• Datasets: 3.5.0
• Tokenizers: 0.21.1

📄 License

Citation

@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}
}