Emergency_informed_Qwen is a fine-tuned LoRA adapter based on Qwen/Qwen2.5-0.5B-Instruct[cite: 2]. It is specifically trained as the Emergency Understanding Agent for the ResQAI Emergency Response System[cite: 2, 3].

This model can be seamlessly integrated into the development of modern emergency response systems to extract structured key features from raw distress inputs[cite: 2, 3]. These extracted features can then be mapped directly with real-time tools—such as geocoding APIs, routing engines, and dispatch databases—to form a complete, end-to-end intelligent emergency agent.

Model Details

Developed by: ResQAI Project Team[cite: 3]
Model Type: Causal Language Model (Fine-Tuned Adapter via PEFT/LoRA)
Base Model: Qwen/Qwen2.5-0.5B-Instruct
Task: Zero-shot / Few-shot Emergency Classification & Structured JSON Extraction
Fine-Tuning Framework: Hugging Face trl (SFTTrainer) & peft
Language: English (optimized for Indian emergency context)

Intended Use

Primary Use Case

This model acts as an emergency feature extraction engine[cite: 2, 3]. Given an unstructured report (voice transcripts, text messages, citizen distress calls), it extracts[cite: 2, 3]:

Emergency Type & Severity Level
Services Required (EMS, Fire Brigade, Police)
Medical Speciality Needed
Immediate Citizen First-Aid / Action Advice

Output Format

The model strictly outputs only valid JSON adhering to the following schema:

json

{
  "citizen_advice": ["Call emergency services immediately", "Stay clear of smoke"],
  "emergency_type": "Fire",
  "medical_speciality": "Emergency Medicine",
  "services_required": ["Emergency Medical Services (EMS)", "Firefighting"],
  "severity": "High"
}

Devrcb/Emergency_informed_Qwen

Emergency_informed_Qwen

Model Details

Intended Use

Primary Use Case

Output Format

Devrcb/
Emergency_informed_Qwen