---
base_model: microsoft/Phi-3-mini-4k-instruct
language:
- en
license: mit
tags:
- phi-3
- fine-tuned
- intent-classification
- mobile-security
- flutter
- qlora
- peft
pipeline_tag: text-generation
---

# SafeScan Phi-3 Mini — Intent Routing Model

Fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) for the **SafeScan** mobile security utility app (Flutter).

## What it does
Given a natural language security query, returns a structured JSON object routing the request to the correct SafeScan module.

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch

model = AutoModelForCausalLM.from_pretrained("MuhammadSanan99989/safescan-phi3-mini-intent-gemini", torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("MuhammadSanan99989/safescan-phi3-mini-intent-gemini", trust_remote_code=True)
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer)

prompt = "<|user|>\nCheck if my WiFi is secure<|end|>\n<|assistant|>"
result = pipe(prompt, max_new_tokens=128, do_sample=False)
print(result[0]['generated_text'][len(prompt):])
```