lbakar/health-log-extraction
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The lbakar/health-log-extraction model is a 0.8 billion parameter information extraction model, fine-tuned from Qwen3.0-0.6b by lbakar. It specializes in extracting structured health information from diary-like user entries using a predefined JSON template. This model is optimized for specific health log data extraction, making it distinct from general-purpose LLMs.
Loading preview...
Overview
The lbakar/health-log-extraction model is a specialized information extraction system built upon a fine-tuned instance of Qwen3.0-0.6b. Developed by lbakar, this model focuses on transforming unstructured, diary-like user entries into structured health information.
Key Capabilities
- Structured Information Extraction: Designed to extract specific health-related entities from free-form text.
- Predefined Template: Utilizes a fixed JSON template to categorize and format extracted data, including:
activity: type, keywords, duration, location, datefood: consumed/missing items, amountmood: description, classification (positive, neutral, negative)symptom: keywords, descriptiontreatment: name, dosage, status (taken, recommended, postponed, missed)
- Fine-tuned Performance: Optimized for this specific task using the
lbakar/health-log-extraction-dataset.
Good For
- Health Diary Analysis: Ideal for applications requiring the extraction of key health metrics and events from personal health logs or journals.
- Data Structuring: Useful for converting qualitative user input about health into quantifiable and analyzable data points.
- Focused Extraction Tasks: Provides a compact and efficient solution for a very specific information extraction problem, rather than general language understanding.