Model for predicting ingredient density. Has been trained on USDA FoodData Central data. Outputs a single logit that can directly be used as density without further processing.
Prompt format:
FOOD: {food}
COMMENTS: {comments}
where food is a food description in the USDA FoodData Central format and comments is either an array of comments in the form of [comment1, comment2] or none.
Citation: U.S. Department of Agriculture, Agricultural Research Service, Beltsville Human Nutrition Research Center. FoodData Central. [Internet]. [cited 2026]. Available from https://fdc.nal.usda.gov/.
- Downloads last month
- 23
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Forkulous/tf-forkulous-density
Base model
microsoft/deberta-v3-large