eaboouf55/FoodExtract-gemma-3-270m-fine-tune-v1
The eaboouf55/FoodExtract-gemma-3-270m-fine-tune-v1 is a 0.3 billion parameter language model, fine-tuned from Google's Gemma 3 270M, specifically designed for food and drink extraction from raw text. It classifies text as food or drink, tags it with relevant categories, and extracts lists of edible food and drink items. This model is optimized for filtering large text datasets, such as image captions, to identify food and drink-related content.
Loading preview...
Model Overview
The eaboouf55/FoodExtract-gemma-3-270m-fine-tune-v1 is a specialized language model built upon the Gemma 3 270M architecture. It is fine-tuned for the precise task of extracting food and drink-related information from raw text inputs. The model processes text to determine if it contains food or drink, assigns specific tags, and identifies individual food and drink items.
Key Capabilities
- Food/Drink Classification: Accurately identifies whether a given text describes food or drink items.
- Tagging: Applies predefined tags (e.g.,
nutrition_panel,ingredient list,food_items,drink_items) for quick categorization and filtering. - Item Extraction: Extracts specific food and drink items mentioned in the text into separate lists.
- Efficient Output: Generates condensed, structured outputs to minimize token generation, with helper functions provided for easy conversion to and from a more detailed dictionary format.
Training Details
The model was trained using Supervised Fine-Tuning (SFT) via Hugging Face's TRL library on the FoodExtract-1k dataset. This dataset comprises 1400 samples of raw text paired with structured food extractions generated by gpt-oss-120b.
Use Cases
This model is particularly well-suited for:
- Data Filtering: Filtering large text datasets, such as image captions (e.g., DataComp-1B), to isolate food and drink-related entries.
- Content Analysis: Analyzing text for the presence and specifics of food and drink mentions.
- Structured Data Generation: Converting unstructured text about food and drink into a structured, machine-readable format.