Instructions to use hlyn-labs/prompt-injection-judge-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hlyn-labs/prompt-injection-judge-3b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("dphn/Dolphin3.0-Llama3.2-3B")
model = PeftModel.from_pretrained(base_model, "hlyn-labs/prompt-injection-judge-3b")

Transformers

How to use hlyn-labs/prompt-injection-judge-3b with Transformers:

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

pipe = pipeline("text-generation", model="hlyn-labs/prompt-injection-judge-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hlyn-labs/prompt-injection-judge-3b")
model = AutoModelForCausalLM.from_pretrained("hlyn-labs/prompt-injection-judge-3b", device_map="auto")
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 Settings

llama.cpp

How to use hlyn-labs/prompt-injection-judge-3b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hlyn-labs/prompt-injection-judge-3b:F16
# Run inference directly in the terminal:
llama cli -hf hlyn-labs/prompt-injection-judge-3b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hlyn-labs/prompt-injection-judge-3b:F16
# Run inference directly in the terminal:
llama cli -hf hlyn-labs/prompt-injection-judge-3b:F16

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 hlyn-labs/prompt-injection-judge-3b:F16
# Run inference directly in the terminal:
./llama-cli -hf hlyn-labs/prompt-injection-judge-3b:F16

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 hlyn-labs/prompt-injection-judge-3b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hlyn-labs/prompt-injection-judge-3b:F16

Use Docker

docker model run hf.co/hlyn-labs/prompt-injection-judge-3b:F16

LM Studio
Jan

vLLM

How to use hlyn-labs/prompt-injection-judge-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hlyn-labs/prompt-injection-judge-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hlyn-labs/prompt-injection-judge-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hlyn-labs/prompt-injection-judge-3b:F16

SGLang

How to use hlyn-labs/prompt-injection-judge-3b 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 "hlyn-labs/prompt-injection-judge-3b" \
    --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": "hlyn-labs/prompt-injection-judge-3b",
		"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 "hlyn-labs/prompt-injection-judge-3b" \
        --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": "hlyn-labs/prompt-injection-judge-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use hlyn-labs/prompt-injection-judge-3b with Ollama:
```
ollama run hf.co/hlyn-labs/prompt-injection-judge-3b:F16
```
Unsloth Desktop

How to use hlyn-labs/prompt-injection-judge-3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hlyn-labs/prompt-injection-judge-3b:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "hlyn-labs/prompt-injection-judge-3b:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use hlyn-labs/prompt-injection-judge-3b with Docker Model Runner:
```
docker model run hf.co/hlyn-labs/prompt-injection-judge-3b:F16
```

Lemonade

How to use hlyn-labs/prompt-injection-judge-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hlyn-labs/prompt-injection-judge-3b:F16

Run and chat with the model

lemonade run user.prompt-injection-judge-3b-F16

List all available models

lemonade list

Hermes Agent

How to use hlyn-labs/prompt-injection-judge-3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hlyn-labs/prompt-injection-judge-3b:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default hlyn-labs/prompt-injection-judge-3b:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hlyn-labs/prompt-injection-judge-3b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hlyn-labs/prompt-injection-judge-3b:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "hlyn-labs/prompt-injection-judge-3b:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Defender Security Judge — Dolphin 3.0 Llama 3.2 3B

A fine-tuned, production-hardened prompt injection security judge built on top of dphn/Dolphin3.0-Llama3.2-3B.

This model is Stage 2 of the Defender multi-layer LLM security pipeline — a real-time adversarial firewall that intercepts, analyzes, and classifies user prompts before they ever reach a protected LLM.

Benchmark Results

Evaluated against the rogue-security/prompt-injections-benchmark — the industry-standard Qualifire benchmark used to evaluate production prompt injection defenses.

Metric	Score
Accuracy	90.00%
F1 Score	0.9038
Precision	88.68%
Recall	92.16%

A 3B quantized model running entirely offline achieving 90% accuracy on the hardest curated jailbreak benchmark available. No API calls. No latency. No cost.

What Makes This Model Different

Zero refusals. Built on the uncensored Dolphin base, it coldly analyzes any attack — no matter how explicit — without flinching or refusing to process the payload.

Rigid JSON output. DoRA fine-tuning permanently hardwires the model to emit only structured {"decision", "confidence", "reason", "allowed_payload"} JSON. No preamble. No yapping.

Calibrated confidence. Trained with Gaussian confidence noise on ambiguous samples, the model's confidence field is mathematically trustworthy — not the overconfident 0.99 you get from vanilla LLMs.

Long-context immunity. Trained at sequence_len: 8192 with 98.37% sample packing efficiency. The model can read an 8,000-token document and catch an attack buried at token 7,500.

Training Details

Technique: DoRA (Weight-Decomposed LoRA) + NEFTune (α=5.0) + Flash Attention + Sample Packing
Hardware: NVIDIA H100 80GB SXM5
Training Time: ~14 minutes
Loss: 2.30 → 0.18 (converged cleanly across 3 epochs)
Dataset: karan11/defender-judge-fine-tune — 2,700 DeBERTa-scored, calibration-hardened samples

Available Artifacts

File	Description
`adapter_model.safetensors`	Raw LoRA adapter weights
`judge-dolphin3-3b-f16.gguf`	Full merged model in F16 (6.4 GB)
`judge-q4_k_m.gguf`	Production artifact — Q4_K_M quantized (2.0 GB)

Intended Use

This model is strictly a security classifier. It is not a general-purpose assistant.
Load it with llama-cpp-python and pass it the Defender system prompt for correct behavior.

from llama_cpp import Llama

llm = Llama(model_path="judge-q4_k_m.gguf", n_gpu_layers=-1, n_ctx=8192)

Downloads last month: 21

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Model tree for hlyn-labs/prompt-injection-judge-3b

Base model

meta-llama/Llama-3.2-3B

Finetuned

dphn/Dolphin3.0-Llama3.2-3B

Adapter

(2)

this model

hlyn-labs
/

prompt-injection-judge-3b

Defender Security Judge — Dolphin 3.0 Llama 3.2 3B

Benchmark Results

What Makes This Model Different

Training Details

Available Artifacts

Intended Use

Model tree for hlyn-labs/prompt-injection-judge-3b

Dataset used to train hlyn-labs/prompt-injection-judge-3b