Metadata-Version: 2.4
Name: hype-hyps
Version: 0.1.0
Summary: HyPE + HyPS: Hyperbolic Prompt Espial and Sanitization (ICLR 2026)
Author-email: Antonio Emanuele Cinà <acina04@gmail.com>
License-Expression: CC-BY-NC-ND-4.0
Project-URL: Homepage, https://github.com/HyPE-VLM/Hyperbolic-Prompt-Detection-and-Sanitization/
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: torch
Requires-Dist: transformers>=4.31.0
Requires-Dist: accelerate
Requires-Dist: numpy
Requires-Dist: peft
Requires-Dist: bitsandbytes
Requires-Dist: huggingface-hub
Requires-Dist: tokenizers
Requires-Dist: safetensors
Requires-Dist: loguru
Requires-Dist: geoopt
Requires-Dist: captum
Requires-Dist: requests
Dynamic: license-file

# HyPE: Hyperbolic Prompt Espial

The **HyPE** package is the official implementation of the ICLR 2026 paper:

> **"Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization"**

## Overview
HyPE enables high-accuracy detection of harmful prompts using hyperbolic geometry.

### Output format
The model follows a binary classification schema where:
- **1**: Harmless prompt  
- **0**: Harmful prompt  

## Quickstart

### Install
```bash
pip install hype-defense
```

### Run inference
```python
from hype import inference

pred = inference("two birds are flying in the sky")
print(pred)  # 1 = harmless, 0 = harmful
```

## Documentation & code
Full documentation, training code, and additional examples are available here:

[**View GitHub Repository**](https://github.com/HyPE-VLM/Hyperbolic-Prompt-Detection-and-Sanitization/tree/main)
