---
license: mit
base_model: unsloth/Mistral-7B-Instruct-v0.2
tags:
  - crisis-response
  - emergency
  - fine-tuned
  - gguf
  - ai-emergency-kit
  - emergency-assistant
---

# AI Emergency Kit - GGUF Model

**AI Emergency Kit** - Your intelligent crisis response assistant. Fine-tuned Mistral-7B model in GGUF format for efficient local deployment.

## Model Details

- **Base Model**: unsloth/Mistral-7B-Instruct-v0.2
- **Format**: GGUF (Float16)
- **File**: model.gguf
- **File Size**: 13.49 GB

## Usage

### Using llama.cpp

```bash
# Download the model
git lfs install
git clone https://huggingface.co/ianktoo/crisis-agent-gguf

# Run inference
./llama-cli -m model.gguf -p "Your prompt here"
```

### Using LM Studio

1. Download the GGUF file from this repository
2. Import into LM Studio
3. Load and chat!

### Using Ollama

```bash
# Create Modelfile
cat > Modelfile << EOF
FROM model.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.9
EOF

# Create model
ollama create crisis-agent -f Modelfile

# Run
ollama run crisis-agent
```

## About AI Emergency Kit

**AI Emergency Kit** is designed to be your reliable AI companion during crisis situations. It provides structured, JSON-formatted responses with actionable guidance, resource recommendations, and step-by-step instructions to help navigate emergency scenarios.

## Limitations

- Model is trained on synthetic crisis scenarios
- Responses should be validated by human experts
- Not intended for real-time emergency response without human oversight