OmniGuard-7B/README.md

---
license: apache-2.0
language:
- en
- zh
tags:
- safety
- moderation
- multimodal
- omniguard
pipeline_tag: text-generation
---

# OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning

OmniGuard is a multimodal safety evaluation model designed to assess content safety across text, images, audio, and video. Built on the Qwen2.5-Omni architecture, it provides structured safety reasoning and policy enforcement.

## Model Information

- **Model Name**: OmniGuard-7B
- **Base Model**: Qwen2.5-Omni-7B
- **Model Type**: Multimodal Safety Moderation
- **Supported Languages**: English, Chinese
- **Supported Modalities**: Text, Image, Audio, Video
- **License**: Apache-2.0

## Model Variants

We provide two model sizes:

- **[OmniGuard-7B](https://huggingface.co/anonymous-omniguard/OmniGuard-7B)** — 7B parameters for high-accuracy safety evaluation
- **[OmniGuard-3B](https://huggingface.co/anonymous-omniguard/OmniGuard-3B)** — 3B parameters for resource-constrained environments

## Features

- **Omni-Modal Safety Assessment**: Evaluate safety across text, images, audio, and video inputs
- **Structured Reasoning**: Provides deliberate, structured safety analysis beyond binary classification

## Installation

### Quick Setup

```bash
# Install core dependencies
pip install torch transformers accelerate

# Install Qwen2.5-Omni support
pip uninstall transformers -y
pip install git+https://github.com/huggingface/transformers@v4.51.3-Qwen2.5-Omni-preview
```

### Requirements

- Python 3.8+
- PyTorch 2.0+
- CUDA-compatible GPU (recommended)
- 16GB+ GPU memory for 7B model
- Flash Attention 2 (optional, for better performance)

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "anonymous-omniguard/OmniGuard-7B"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    attn_implementation="flash_attention_2"  # Recommended
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Text-only safety evaluation
messages = [
    {"role": "user", "content": "Please analyze the safety of this content: [Your content here]"}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    do_sample=False
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```

## Ethical Considerations

- This model is designed for safety evaluation and content moderation
- Should be used as part of a comprehensive safety strategy
- May reflect biases present in training data
- Continuous monitoring and updates recommended for production use
- Users are responsible for compliance with applicable laws and regulations

## License

This model is released under the Apache-2.0 license.

## Acknowledgments

- Built on [Qwen2.5-Omni](https://github.com/QwenLM/Qwen2.5-Omni) by Alibaba Cloud
- Uses [LLaMA Guard 3](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) safety framework
- Trained on diverse multimodal safety datasets

## Support

For issues, questions, or contributions:
- Repository: https://github.com/anonymous-2654a/neurips-2026-sub
- HuggingFace: https://huggingface.co/anonymous-omniguard

---

*Anonymous release accompanying a paper currently under peer review.*