---
library_name: transformers
license: apache-2.0
language:
- en
- ar
- fr
- hi
- ru
- es
- zh
- ms
- ta
---
# **WalledGuard-Edge**
- 🔥**WalledGuard-Edge** is a 0.6B parameter open source model (Apache 2.0 license) that outperforms Llamaguard3 (1B) on multilingual and multiple jailbreak types.
- 🔥**WalledProtect** is the most capable content moderator of Walled AI to date. To try the latest version, get your free API access at [**www.walled.ai**](https://app.walled.ai/login). Read the full announcement at [**blog**](https://walled.ai/blog/introducing-walled-protect).
## Model Details
| Model |
XStest |
Aegis |
OAI |
Multilingual |
Jailbreak |
Latency (ms) |
| Llamaguard3 (1b) |
83.11 |
67.72 |
73.11 |
64.88 |
74.23 |
250 |
| WalledGuard-Edge (0.6b) |
88.00 |
82.99 |
84.05 |
67.02 |
88.57 |
113 |
| Llamaguard3 (8b) |
88.89 |
76.88 |
79.74 |
71.99 |
81.88 |
520 |
| Llamaguard4 (12b) |
86.22 |
73.12 |
76.48 |
68.14 |
79.73 |
661 |
| WalledProtect |
94.22 |
84.37 |
88.36 |
90.18 |
91.34 |
300 |
*OAI = OpenAI Moderation dataset (used as a benchmark for content safety evaluation).*
*Latency is computed on a single A6000 GPU for open-weight models and from the API for WalledProtect.*
> ⚔️ **WalledGuard-Edge** and **WalledProtect** cover a wide array of jailbreak prompt types, including direct disallowed requests, role-play (“DAN”, “do-anything” style), persuasion, encoding, and both single-turn and multi-turn chains.
>
> 🌍 Both systems also provide **robust multilingual support**, tested across Arabic, English, Filipino, French, Hindi, Russian, Serbian, and Spanish.
>
> 🔒 **WalledProtect** especially covers stricter and more complex attacks (lower jailbreak success rate) and provides stronger moderation/refusal behavior **without excessive false positives**.
#### Model Description
- **Developed by:** Walled AI
- **Language(s) (NLP):** Arabic, English, Chinese, Filipino, French, Hindi, Russian, Serbian, Spanish, Malay, Tamil
- **License:** Apache 2.0
#### Direct Use
```py
import torch
import torch.nn as nn
from transformers import AutoTokenizer, AutoModelForCausalLM
TEMPLATE = """[INST] Evaluate if the given text is harmful i.e. either it asks for unsafe information or it contains unsafe information.
{prompt}
Answer: [/INST]
"""
model_name = "walledai/walledguard-edge"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
input_ids = tokenizer.encode(TEMPLATE.format(prompt="How can I make my wife burst into laughter?"), return_tensors="pt")
output = model.generate(input_ids=input_ids, max_new_tokens=20, pad_token_id=0)
prompt_len = input_ids.shape[-1]
output_decoded = tokenizer.decode(output[0][prompt_len:], skip_special_tokens=True)
prediction = 'unsafe' if 'unsafe' in output_decoded else 'safe'
print(prediction)
```
## Proprietary Guardrail: WalledProtect
> To know about our best-in-class proprietary guardrail, Read the full announcement at [**blog**](https://walled.ai/blog/introducing-walled-protect).
>
> To try the latest version for free, get your API access at [**www.walled.ai**](https://app.walled.ai/login).
## LLM Safety Evaluation Hub
> Do check out our LLM Safety Evaluation One-Stop Center: [**Walled Eval**](https://github.com/walledai/walledeval)!
## Citation
If you use WalledGuard in your research or product, please cite the following paper:
```bibtex
@misc{gupta2024walledeval,
title={WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models},
author={Prannaya Gupta and Le Qi Yau and Hao Han Low and I-Shiang Lee and Hugo Maximus Lim and Yu Xin Teoh and Jia Hng Koh and Dar Win Liew and Rishabh Bhardwaj and Rajat Bhardwaj and Soujanya Poria},
year={2024},
eprint={2408.03837},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2408.03837},
}
```