Instructions to use BansheeTechnologies/HomeDock-OS-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="BansheeTechnologies/HomeDock-OS-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BansheeTechnologies/HomeDock-OS-3B-Instruct", dtype="auto")

llama-cpp-python

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BansheeTechnologies/HomeDock-OS-3B-Instruct",
	filename="HomeDock-OS-3B-Instruct.Q4_K_M.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 BansheeTechnologies/HomeDock-OS-3B-Instruct with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BansheeTechnologies/HomeDock-OS-3B-Instruct: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 BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BansheeTechnologies/HomeDock-OS-3B-Instruct: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 BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M

LM Studio
Jan

vLLM

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M

SGLang

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct 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 "BansheeTechnologies/HomeDock-OS-3B-Instruct" \
    --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": "BansheeTechnologies/HomeDock-OS-3B-Instruct",
		"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 "BansheeTechnologies/HomeDock-OS-3B-Instruct" \
        --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": "BansheeTechnologies/HomeDock-OS-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with Ollama:
```
ollama run hf.co/BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M
```

Unsloth Studio new

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct 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 BansheeTechnologies/HomeDock-OS-3B-Instruct 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 BansheeTechnologies/HomeDock-OS-3B-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BansheeTechnologies/HomeDock-OS-3B-Instruct to start chatting

Pi new

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BansheeTechnologies/HomeDock-OS-3B-Instruct: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": "BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BansheeTechnologies/HomeDock-OS-3B-Instruct: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 BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M
```

Lemonade

How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.HomeDock-OS-3B-Instruct-Q4_K_M

List all available models

lemonade list

HomeDock-OS-3B-Instruct

A fine-tuned version of Qwen 2.5 3B Instruct specialized in HomeDock OS documentation, features, for guidance and to make self-hosting easier.

Model Description

HomeDock-OS-3B-Instruct is trained on the complete HomeDock OS knowledge base:

Documentation: Installation, configuration, SSL, troubleshooting
200+ Applications Features: Plex, Jellyfin, Nextcloud, Home Assistant, and more
Blog Articles: Tutorials, comparisons, and best practices
Enterprise Features: Data Space, Secure Tunnel, Audit Trail, and more

Key Features

Answers questions about HomeDock OS features and configuration
Provides guidance on self-hosted application setup
Understands Docker containerization concepts
Explains App Store applications and their use cases

Quantization

File	Size	Description
`HomeDock-OS-3B-Instruct.Q4_K_M.gguf`	~1.8 GB	Recommended, best balance
`HomeDock-OS-3B-Instruct.Q8_0.gguf`	~3.2 GB	Higher quality

Usage

Ollama

Create a Modelfile:

FROM ./HomeDock-OS-3B-Instruct.Q4_K_M.gguf

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

SYSTEM """You are an expert assistant for HomeDock OS documentation. Provide clear, accurate, and helpful information about HomeDock OS features, configuration, and usage."""

PARAMETER stop "<|im_end|>"
PARAMETER stop "<|im_start|>"
PARAMETER temperature 0.7

Create and run:

ollama create homedock -f Modelfile
ollama run homedock "What is HomeDock OS?"

llama.cpp

./llama-cli -m HomeDock-OS-3B-Instruct.Q4_K_M.gguf \
  -p "<|im_start|>system\nYou are an expert assistant for HomeDock OS documentation.<|im_end|>\n<|im_start|>user\nWhat is Drop Zone?<|im_end|>\n<|im_start|>assistant\n" \
  -n 256

LM Studio

Download the .gguf file
Import into LM Studio
Use the ChatML preset or configure manually

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(model_path="HomeDock-OS-3B-Instruct.Q4_K_M.gguf", n_ctx=2048)

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are an expert assistant for HomeDock OS documentation."},
        {"role": "user", "content": "How do I install Plex on HomeDock OS?"}
    ]
)
print(response["choices"][0]["message"]["content"])

Example Conversations

User: What is HomeDock OS?

Assistant: HomeDock OS is a complete home cloud operating system that simplifies self-hosting. It provides a desktop-like interface in your browser with features like the App Store (200+ pre-configured applications), Drop Zone (encrypted file storage), Control Hub (container management), and automatic SSL configuration. It runs on Linux, Windows, macOS, and as a Docker container.

User: How do I configure SSL?

Assistant: HomeDock OS supports automatic SSL configuration. Navigate to Settings > SSL/HTTPS, enter your domain name, and HomeDock OS will automatically obtain and configure Let's Encrypt certificates. Applications installed through the App Store inherit SSL configuration automatically.

User: What is the difference between Plex and Jellyfin?

Assistant: Both are media server solutions available in the HomeDock OS App Store. Plex offers a polished interface with premium features like hardware transcoding and mobile sync (requires Plex Pass). Jellyfin is fully open-source and free, with no premium tier required. For most self-hosters, Jellyfin provides excellent functionality without subscription costs.

Training Details

Parameter	Value
Base Model	Qwen/Qwen2.5-3B-Instruct
Method	LoRA (r=16, alpha=32)
Epochs	3
Learning Rate	2e-4
Sequence Length	2048
Training Examples	788
Total Words	~99,000

Training Data

The model was trained on the complete HomeDock OS documentation including:

Official documentation (MDX)
Application descriptions (200+ apps)
Blog posts and tutorials
Enterprise feature guides

Limitations

Knowledge is specific to HomeDock OS; may not generalize well to other platforms
Training data cutoff corresponds to the documentation version at training time
Best suited for English queries
May occasionally generate plausible-sounding but incorrect information

License

This model is released under the Apache 2.0 License, same as the base Qwen 2.5 model.

Citation

@misc{homedock-os-3b-instruct,
  author = {Banshee Technologies S.L.},
  title = {HomeDock-OS-3B-Instruct: A Fine-tuned LLM for HomeDock OS Documentation},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/banshee/HomeDock-OS-3B-Instruct}
}

Built with HomeDock OS
homedock.cloud

Downloads last month: 4

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for BansheeTechnologies/HomeDock-OS-3B-Instruct

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(216)

this model

BansheeTechnologies
/

HomeDock-OS-3B-Instruct

HomeDock-OS-3B-Instruct

Model Description

Key Features

Quantization

Usage

Ollama

llama.cpp

LM Studio

Python (llama-cpp-python)

Example Conversations

Training Details

Training Data

Limitations

License

Links

Citation

Model tree for BansheeTechnologies/HomeDock-OS-3B-Instruct