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

Libraries

How to use QuantFactory/walledguard-c-GGUF with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/walledguard-c-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/walledguard-c-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/walledguard-c-GGUF",
	filename="walledguard-c.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/walledguard-c-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/walledguard-c-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/walledguard-c-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/walledguard-c-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/walledguard-c-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/walledguard-c-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/walledguard-c-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/walledguard-c-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/walledguard-c-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/walledguard-c-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/walledguard-c-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuantFactory/walledguard-c-GGUF:Q4_K_M

SGLang

How to use QuantFactory/walledguard-c-GGUF 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 "QuantFactory/walledguard-c-GGUF" \
    --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": "QuantFactory/walledguard-c-GGUF",
		"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 "QuantFactory/walledguard-c-GGUF" \
        --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": "QuantFactory/walledguard-c-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/walledguard-c-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/walledguard-c-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/walledguard-c-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/walledguard-c-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/walledguard-c-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/walledguard-c-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/walledguard-c-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/walledguard-c-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/walledguard-c-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/walledguard-c-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.walledguard-c-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/walledguard-c-GGUF

This is quantized version of walledai/walledguard-c created using llama.cpp

Model Description

🔥 WalledGuard comes in two versions: Community and Advanced*. To get access to the advanced version, please contact us at admin@walled.ai
🔥 Please check out our LLM Safety Evaluation One-Stop Center: Walled Eval!

(*More performant, suitable for enterprise use)

Note: We also provide customized guardrails for enterprise-specific use cases, please reach out to us at admin@walled.ai.
Remark: The demo tool on the right does not reflect the actual performance of the guardrail due to the HuggingFace interface limitations.

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
WalledGuard-C (Community Version)	92.00	86.89	87.35	86.78	88.26 ▲ 3.9%
WalledGuard-A (Advanced Version)	92.33	96.44	90.52	90.46	92.94 ▲ 9.4%

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.

LLM Safety Evaluation Hub

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

Model Citation

TO BE ADDED

Model Card Contact

rishabh@walled.ai

Downloads last month: 80

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/walledguard-c-GGUF

Base model

walledai/walledguard-c

Quantized

(1)

this model