mhammadkhan/negation-categories-classifier

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:

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

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

model = SetFitModel.from_pretrained("mhammadkhan/negation-categories-classifier")

# Define category labels
labels = {0: "dairy-free", 1: "gluten-free", 2: "nut-free", 3: "soy-free", 4: "vegan"}

# Define input recipes
recipes = [
    {"text": "Tacos de Coliflor Vegana", "ingredients":["cauliflower", "taco seasoning", "corn tortillas", "avocado", "salsa", "cilantro", "lime wedges"]},
    {"text": "Pulpo a la Gallega Sin Gluten", "ingredients":["octopus", "potatoes", "paprika", "olive oil", "salt"]},
    {"text": "Creamy Tomato Soup", "ingredients":["tomatoes", "vegetable broth", "onion", "garlic", "coconut milk"]},
    {"text": "Chicken Alfredo Pasta", "ingredients":["chicken breast", "pasta", "broccoli", "mushrooms", "cashew cream"]},
    {"text": "Cheesy Broccoli Casserole", "ingredients":["broccoli", "almond milk", "nutritional yeast", "gluten-free breadcrumbs"]},
    {"text": "Gluten-Free Pizza", "ingredients":["gluten-free pizza crust", "tomato sauce", "mozzarella cheese", "mushrooms", "bell peppers"]},
    {"text": "Quinoa Salad with Roasted Vegetables", "ingredients":["quinoa", "roasted sweet potato", "roasted Brussels sprouts", "dried cranberries", "almonds"]},
    {"text": "Gluten-Free Chocolate Chip Cookies", "ingredients":["gluten-free flour", "brown sugar", "baking soda", "chocolate chips", "coconut oil"]},
    {"text": "Chicken Satay Skewers", "ingredients":["chicken breast", "coconut milk", "peanut butter", "soy sauce", "lime juice"]},
    {"text": "Pesto Pasta Salad", "ingredients":["pasta", "basil", "parmesan cheese", "pine nuts", "olive oil"]},
    {"text": "Maple-Glazed Salmon", "ingredients":["salmon", "maple syrup", "pecans", "butter", "garlic"]},
    {"text": "Beef and Broccoli Stir-Fry", "ingredients":["beef sirloin", "broccoli", "carrots", "garlic", "ginger", "cornstarch"]},
    {"text": "Creamy Mushroom Soup", "ingredients":["mushrooms", "vegetable broth", "onion", "garlic", "cashew cream"]},
    {"text": "Lemon-Garlic Roasted Chicken", "ingredients":["chicken thighs", "lemon juice", "garlic", "olive oil", "rosemary"]},
    {"text": "Vegan Lasagna", "ingredients":["lasagna noodles", "tofu ricotta", "marinara sauce", "spinach", "mushrooms"]},
    {"text": "Chickpea Curry", "ingredients":["chickpeas", "coconut milk", "tomatoes", "spinach", "curry powder"]},
    {"text": "Vegan Banana Bread", "ingredients":["flour", "bananas", "sugar", "baking powder", "almond milk"]},
]

# Run inference
preds = model(recipes)
print(preds)
# Map integer predictions to category labels
preds = [labels[pred.item()] for pred in preds]

print(preds)

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}
}