Text Generation
PEFT
Safetensors
English
emergency-response
resqai
structured-json
lora
qwen2.5
Indian-emergency-system
Instructions to use Devrcb/Emergency_informed_Qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Devrcb/Emergency_informed_Qwen with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| base_model: Qwen/Qwen2.5-0.5B-Instruct | |
| library_name: peft | |
| pipeline_tag: text-generation | |
| language: | |
| - en | |
| tags: | |
| - emergency-response | |
| - resqai | |
| - structured-json | |
| - lora | |
| - qwen2.5 | |
| - Indian-emergency-system | |
| # Emergency_informed_Qwen | |
| **Emergency_informed_Qwen** is a fine-tuned LoRA adapter based on [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/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]: | |
| 1. **Emergency Type & Severity Level** | |
| 2. **Services Required** (EMS, Fire Brigade, Police) | |
| 3. **Medical Speciality Needed** | |
| 4. **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" | |
| } |