--- library_name: setfit tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer metrics: - accuracy widget: - text: 'Can you please send me flight quotations for Mr Mthetho Sovara for travel to Bologna, Italy as per details below: 7 Oct: JHB to Bologna, Italy 14 Oct: Bologna, Italy to JHB' - text: Your warranty is about to expire. Click here to extend it and avoid costly repairs. - text: Family emergency means I won't make my reservation. How can I get my money back? - text: 'Your flight reservation with Delta Airlines has been confirmed. Flight #DL102 from JFK to ATL on November 20th, departure at 5:00 PM.' - text: I need invoice please with Engela Petzer name pipeline_tag: text-classification inference: true base_model: sentence-transformers/all-MiniLM-L6-v2 --- # SetFit with sentence-transformers/all-MiniLM-L6-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co./sentence-transformers/all-MiniLM-L6-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for 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. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co./sentence-transformers/all-MiniLM-L6-v2) - **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance - **Maximum Sequence Length:** 256 tokens - **Number of Classes:** 14 classes ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co./blog/setfit) ### Model Labels | Label | Examples | |:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 12 | | | 11 | | | 8 | | | 7 | | | 13 | | | 3 | | | 6 | | | 1 | | | 5 | | | 4 | | | 2 | | | 9 | | | 0 | | | 10 | | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the 🤗 Hub model = SetFitModel.from_pretrained("mann2107/BCMPIIRAB_ALL_Test") # Run inference preds = model("I need invoice please with Engela Petzer name") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 1 | 26.3827 | 136 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 26 | | 1 | 26 | | 2 | 26 | | 3 | 25 | | 4 | 25 | | 5 | 26 | | 6 | 25 | | 7 | 25 | | 8 | 26 | | 9 | 26 | | 10 | 25 | | 11 | 26 | | 12 | 26 | | 13 | 25 | ### Training Hyperparameters - batch_size: (8, 8) - num_epochs: (1, 1) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 1 - body_learning_rate: (0.0009623401597937572, 0.0009623401597937572) - head_learning_rate: 0.0009623401597937572 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: False - warmup_proportion: 0.1 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: False ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:------:|:----:|:-------------:|:---------------:| | 0.0111 | 1 | 0.2042 | - | | 0.5556 | 50 | 0.1917 | - | ### Framework Versions - Python: 3.11.7 - SetFit: 1.1.0.dev0 - Sentence Transformers: 2.2.2 - Transformers: 4.35.2 - PyTorch: 2.1.1+cu121 - Datasets: 2.14.5 - Tokenizers: 0.15.1 ## Citation ### BibTeX ```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} } ```