Instructions to use walledai/walledguard-c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use walledai/walledguard-c with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="walledai/walledguard-c")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("walledai/walledguard-c")
model = AutoModelForCausalLM.from_pretrained("walledai/walledguard-c")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use walledai/walledguard-c with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "walledai/walledguard-c"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walledai/walledguard-c",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/walledai/walledguard-c

SGLang

How to use walledai/walledguard-c with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "walledai/walledguard-c" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walledai/walledguard-c",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "walledai/walledguard-c" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walledai/walledguard-c",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use walledai/walledguard-c with Docker Model Runner:
```
docker model run hf.co/walledai/walledguard-c
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Walled Guard

🔥WalledGuard comes in two versions: Community and Advanced*.
🔥📣[New] 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. Read the full announcement at blog.
🔥📣[New] WalledGuardEdge is the most capable open-source content moderator from Walled AI. Try it here: WalledGuard-Edge.

Note: The Advanced version is now named as WalledProtect. Get your free API access at www.walled.ai. Latest scores can be found here.

Model Details

Model Description

Developed by: Walled AI
Language(s) (NLP): English
License: Apache 2.0

Direct Use

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.

<START TEXT>
{prompt}
<END TEXT>

Answer: [/INST]
"""

model_name = "walledai/walledguard-c"

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)

Inference Speed

- WalledGuard Community: ~0.1 sec/sample (4bit, on A100/A6000)
- Llama Guard 2: ~0.4 sec/sample (4bit, on A100/A6000)

Results

Model	DynamoBench	XSTest	P-Safety	R-Safety	Average Scores
Llama Guard 1	77.67	85.33	71.28	86.13	80.10
Llama Guard 2	82.67	87.78	79.69	89.64	84.95
Llama Guard 3	83.00	88.67	80.99	89.58	85.56
WalledGuard-C (Community Version)	92.00	86.89	87.35	86.78	88.26 ▲ 3.2%
WalledGuard-A (Advanced Version)	92.33	96.44	90.52	90.46	92.94 ▲ 8.1%

Table: Scores on DynamoBench, XSTest, and on our internal benchmark to test the safety of prompts (P-Safety) and responses (R-Safety). We report binary classification accuracy.

Note: The Advanced version is now named as WalledProtect. Get your free API access at www.walled.ai. Latest scores can be found here.

LLM Safety Evaluation Hub

Please check out our LLM Safety Evaluation One-Stop Center: Walled Eval!

Citation

If you use the data, please cite the following paper:

@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}, 
}

Model Card Contact

Walled AI

Downloads last month: 5

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for walledai/walledguard-c

Quantizations

1 model

Space using walledai/walledguard-c 1

Paper for walledai/walledguard-c

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models

Paper • 2408.03837 • Published Aug 7, 2024 • 18