Instructions to use aashishk029/shinobu-7b-v13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use aashishk029/shinobu-7b-v13 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 aashishk029/shinobu-7b-v13:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aashishk029/shinobu-7b-v13:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aashishk029/shinobu-7b-v13:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aashishk029/shinobu-7b-v13:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf aashishk029/shinobu-7b-v13:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf aashishk029/shinobu-7b-v13:Q4_K_M

Use Docker

docker model run hf.co/aashishk029/shinobu-7b-v13:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use aashishk029/shinobu-7b-v13 with Ollama:
```
ollama run hf.co/aashishk029/shinobu-7b-v13:Q4_K_M
```
Unsloth Desktop

How to use aashishk029/shinobu-7b-v13 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aashishk029/shinobu-7b-v13:Q4_K_M

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": "aashishk029/shinobu-7b-v13:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use aashishk029/shinobu-7b-v13 with Docker Model Runner:
```
docker model run hf.co/aashishk029/shinobu-7b-v13:Q4_K_M
```

Lemonade

How to use aashishk029/shinobu-7b-v13 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aashishk029/shinobu-7b-v13:Q4_K_M

Run and chat with the model

lemonade run user.shinobu-7b-v13-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use aashishk029/shinobu-7b-v13 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aashishk029/shinobu-7b-v13: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 aashishk029/shinobu-7b-v13:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use aashishk029/shinobu-7b-v13 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aashishk029/shinobu-7b-v13: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 "aashishk029/shinobu-7b-v13: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"

Shinobu 7B v13 — on-prem security triage copilot

Qwen2.5-7B-Instruct + Shinobu LoRA v13, Q4_K_M GGUF (4.4 GB). The L2 triage brain of Shinobu — a privacy-first, 100% local security copilot. Detects, triages (MITRE ATT&CK-mapped verdicts with abstain), and recommends operator-approved responses. Nothing auto-executes.

87% verdict accuracy on probes_v11 (TP 9/10, FP 9/10, abstain 8/10) — up from v10's 80%
Abstains rather than fabricating verdicts on thin telemetry
sha256: cf493ea6178a52802c18796d41be71b52e7d8ca8c0b48fe14fed1fd3099cf75c
Runs via ollama on 16 GB RAM / 8-core CPU, no GPU

Install + full product: https://github.com/aashishk029/shinobu — created by Aashish Kumar.

Downloads last month: 18

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for aashishk029/shinobu-7b-v13

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2880)

this model