Instructions to use UtkarshSinghShrinet/swarmhunter-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use UtkarshSinghShrinet/swarmhunter-v2 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 UtkarshSinghShrinet/swarmhunter-v2:Q8_0
# Run inference directly in the terminal:
llama cli -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0
# Run inference directly in the terminal:
llama cli -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

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 UtkarshSinghShrinet/swarmhunter-v2:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

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 UtkarshSinghShrinet/swarmhunter-v2:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

Use Docker

docker model run hf.co/UtkarshSinghShrinet/swarmhunter-v2:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use UtkarshSinghShrinet/swarmhunter-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UtkarshSinghShrinet/swarmhunter-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UtkarshSinghShrinet/swarmhunter-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UtkarshSinghShrinet/swarmhunter-v2:Q8_0

Ollama
How to use UtkarshSinghShrinet/swarmhunter-v2 with Ollama:
```
ollama run hf.co/UtkarshSinghShrinet/swarmhunter-v2:Q8_0
```
Unsloth Desktop

How to use UtkarshSinghShrinet/swarmhunter-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

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": "UtkarshSinghShrinet/swarmhunter-v2:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use UtkarshSinghShrinet/swarmhunter-v2 with Docker Model Runner:
```
docker model run hf.co/UtkarshSinghShrinet/swarmhunter-v2:Q8_0
```

Lemonade

How to use UtkarshSinghShrinet/swarmhunter-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UtkarshSinghShrinet/swarmhunter-v2:Q8_0

Run and chat with the model

lemonade run user.swarmhunter-v2-Q8_0

List all available models

lemonade list

Hermes Agent

How to use UtkarshSinghShrinet/swarmhunter-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

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 UtkarshSinghShrinet/swarmhunter-v2:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use UtkarshSinghShrinet/swarmhunter-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UtkarshSinghShrinet/swarmhunter-v2:Q8_0

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 "UtkarshSinghShrinet/swarmhunter-v2:Q8_0" \
  --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"

🛡️ SwarmHunter v2 (DPO Aligned)

SwarmHunter v2 is an advanced, high-precision cybersecurity reasoning and autonomous exploit verification model developed by Utkarsh Singh Shrinet.

Built directly on top of UtkarshSinghShrinet/swarmhunter-3b (Mega SFT across 2.28M samples), v2 underwent complete Direct Preference Optimization (DPO) across 18,000 rigorous cybersecurity alignment pairs to eliminate false positives, adhere strictly to protocol specifications (RFC 9110, RFC 6749, RFC 7519), and deliver reproducible, executable Proof-of-Concept verification artifacts.

📊 Model Specifications

Creator & Lead Developer: Utkarsh Singh Shrinet
Base Architecture: Qwen/Qwen2.5-Coder-3B-Instruct
SFT Foundation: UtkarshSinghShrinet/swarmhunter-3b (2,280,000 multi-turn samples)
Alignment Stage: Direct Preference Optimization (18,000 chosen/rejected cybersecurity pairs, 2,250 global steps)
Training Progression: DPO Loss reduced by 99.4% (0.561 → 0.00339), Reward Accuracy: 1.0 (100.0%), Reward Margin: +5.83
Precision: 16-bit Full Precision BF16 / FP16 Safetensors + Standalone Q8_0 GGUF Binary
Context Length: 4,096 tokens (ChatML format)

🚀 Quickstart: Local Ollama Run

ollama run hf.co/UtkarshSinghShrinet/swarmhunter-v2:swarmhunter-v2.Q8_0.gguf

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

F16

Model tree for UtkarshSinghShrinet/swarmhunter-v2

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Finetuned

UtkarshSinghShrinet/swarmhunter-3b

Quantized

(2)

this model

Quantizations

2 models