Instructions to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CycleCoreTechnologies/pq-sift-defender-Q4_K_M",
	filename="pq-sift-defender-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M 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 CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M: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 CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M: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 CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

LM Studio
Jan

vLLM

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CycleCoreTechnologies/pq-sift-defender-Q4_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CycleCoreTechnologies/pq-sift-defender-Q4_K_M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

Ollama
How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with Ollama:
```
ollama run hf.co/CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M
```

Unsloth Studio

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M 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 CycleCoreTechnologies/pq-sift-defender-Q4_K_M 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 CycleCoreTechnologies/pq-sift-defender-Q4_K_M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CycleCoreTechnologies/pq-sift-defender-Q4_K_M to start chatting

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

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 CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

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 "CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M" \
  --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"

Docker Model Runner
How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M
```

Lemonade

How to use CycleCoreTechnologies/pq-sift-defender-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CycleCoreTechnologies/pq-sift-defender-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.pq-sift-defender-Q4_K_M-Q4_K_M

List all available models

lemonade list

pq-sift-defender-Q4_K_M

QLoRA fine-tuned Qwen2.5-1.5B-Instruct for autonomous DFIR incident-response triage. Q4_K_M quantized GGUF for Ollama.

Built by CycleCore Technologies for the SANS FIND EVIL hackathon.

What it does

Reads a security alert (EDR, WAF, IDS, phishing report) and produces a structured verdict: PASS, FLAG, or BLOCK with cited indicators. The model drives the pq-sift-defender agent, which wraps it with a SecurityGates pre-filter and a post-quantum signed audit trail (ML-DSA-65).

Performance

Validated on 136 held-out samples spanning benign events, SSRF, SQL injection, command injection, path traversal, prompt injection, CVE-grounded attacks, boundary recovery, and malware memory dumps.

96.3% accuracy | 100% BLOCK | 94.6% PASS | 11s per triage | CPU-only

Verdict	Accuracy	Count
BLOCK	100%	72/72
FLAG	75%	6/8
PASS	94.6%	53/56

Training

Method: QLoRA (4-bit NF4, LoRA r=64, alpha=16, 5 epochs, lr=1e-4)
Data: 785 unique ShareGPT-format samples across 7 batches (benign PASS, attack BLOCK, boundary recovery, FLAG + format, CVE-grounded, hard PASS)
Two-axis weighting: per-batch oversampling (up to 1.8x for PASS) + per-sample quality-based loss scaling (A/B/C tiers)
Hardware: RTX 5070Ti, 26 minutes
Pipeline: Reproducible via training/ directory in the main repo

Usage with Ollama

# Download the GGUF and Modelfile from this repo, then:
ollama create pq-sift-defender -f Modelfile

# Or point your Modelfile FROM line at the downloaded GGUF path:
# FROM /path/to/pq-sift-defender-Q4_K_M.gguf

Then run with the agent:

pip install -e ".[dev]"  # from the main repo
PQ_SIFT_MODEL=pq-sift-defender pq-sift-defender investigate samples/path_traversal.json

Or test directly:

ollama run pq-sift-defender "Analyze this alert: PowerShell -enc SQBFAFgAIAAoA..."

Files

File	Size	Description
`pq-sift-defender-Q4_K_M.gguf`	986 MB	Q4_K_M quantized model
`Modelfile`	1.6 KB	Ollama import file with ChatML template + system prompt

Quantization

Converted from merged safetensors via llama.cpp/convert_hf_to_gguf.py (external, not Ollama's internal converter). Q4_K_M quantization. 986 MB on disk.

Note: Ollama 0.24.0's internal safetensors-to-GGUF converter has a known bug with transformers 5.9.0 models. Use the external llama.cpp converter if rebuilding from source.

Hardware Requirements

Resource	Requirement
RAM	2-3 GB free
CPU	One modern x86_64 core
Disk	~1 GB
GPU	Not required

CPU	Inference time
Intel Core i9-14900KF	4s
AMD Ryzen 7 7800X3D	11s

License

Apache 2.0

Downloads last month: 4

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for CycleCoreTechnologies/pq-sift-defender-Q4_K_M

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

(215)

this model

Evaluation results

Overall Accuracy
self-reported

96.300
BLOCK Accuracy
self-reported

100.000
PASS Accuracy
self-reported

94.600