ningpy/redflag-detection-V3.0

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 15, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

ningpy/redflag-detection-V3.0 is a 7.6 billion parameter medical red-flag symptom extraction model, fine-tuned from Qwen2.5-7B-Instruct. It is designed to extract structured medical information, such as symptoms, conditions, and modifiers, from user messages. This model excels at identifying emergency red-flag rules, achieving 90.0% exact match on out-of-distribution test sets and supporting both English and Bahasa Melayu.

Loading preview...

Model Overview

ningpy/redflag-detection-V3.0 is a specialized 7.6 billion parameter language model, fine-tuned from Qwen2.5-7B-Instruct, for medical red-flag symptom extraction. Its primary function is to parse user messages and extract structured medical data, which can then feed into a rule engine to identify potential emergency conditions.

Key Capabilities

  • Structured Information Extraction: Extracts detailed medical information including age, patient type (self/third-party), conditions, symptoms (including denied ones), and various modifiers (e.g., onset, fever temperature).
  • High Performance: Achieves a 90.0% exact match and 0.950 Micro F1 score on a 100-case out-of-distribution test set for red-flag detection.
  • Multilingual Support: Trained on data covering both English and Bahasa Melayu, enabling extraction from messages in these languages.
  • Comprehensive Coverage: Trained on 8355 samples to cover 70 distinct red-flag rules (RF-001 to RF-070).
  • JSON Output: Provides extracted information in a standardized JSON schema, facilitating integration with downstream systems.

Good For

  • Automated Medical Triage: Identifying critical symptoms from patient descriptions to flag urgent cases.
  • Clinical Decision Support: Structuring unstructured patient input for analysis by rule-based systems.
  • Healthcare Applications: Any system requiring the precise extraction of medical red-flag indicators from free-text input.