Instructions to use BansheeTechnologies/HomeDock-OS-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use BansheeTechnologies/HomeDock-OS-3B-Instruct 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 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 serve -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
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
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 serve -hf BansheeTechnologies/HomeDock-OS-3B-Instruct: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": "BansheeTechnologies/HomeDock-OS-3B-Instruct:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- 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
- Hermes Agent
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 serve -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
- Atomic Chat
- OpenClaw
How to use BansheeTechnologies/HomeDock-OS-3B-Instruct with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BansheeTechnologies/HomeDock-OS-3B-Instruct: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 "BansheeTechnologies/HomeDock-OS-3B-Instruct: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"
Update README.md
Browse files|
@@ -1,3 +1,185 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model: Qwen/Qwen2.5-3B-Instruct
|
| 6 |
+
tags:
|
| 7 |
+
- homedock
|
| 8 |
+
- homedock-os
|
| 9 |
+
- self-hosting
|
| 10 |
+
- docker
|
| 11 |
+
- home-server
|
| 12 |
+
- documentation
|
| 13 |
+
- qwen2.5
|
| 14 |
+
- gguf
|
| 15 |
+
- fine-tuned
|
| 16 |
+
library_name: transformers
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
model-index:
|
| 19 |
+
- name: HomeDock-OS-3B-Instruct
|
| 20 |
+
results: []
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# HomeDock-OS-3B-Instruct
|
| 24 |
+
|
| 25 |
+
<img src="https://homedock.cloud/images/homedock-os-icon.png" alt="HomeDock OS" width="120" align="right">
|
| 26 |
+
|
| 27 |
+
A fine-tuned version of **Qwen 2.5 3B Instruct** specialized in [HomeDock OS](https://www.homedock.cloud) documentation, features, for guidance and to make self-hosting easier.
|
| 28 |
+
|
| 29 |
+
## Model Description
|
| 30 |
+
|
| 31 |
+
HomeDock-OS-3B-Instruct is trained on the complete HomeDock OS knowledge base:
|
| 32 |
+
|
| 33 |
+
- **Documentation**: Installation, configuration, SSL, troubleshooting
|
| 34 |
+
- **200+ Applications Features**: Plex, Jellyfin, Nextcloud, Home Assistant, and more
|
| 35 |
+
- **Blog Articles**: Tutorials, comparisons, and best practices
|
| 36 |
+
- **Enterprise Features**: Data Space, Secure Tunnel, Audit Trail, and more
|
| 37 |
+
|
| 38 |
+
### Key Features
|
| 39 |
+
|
| 40 |
+
- Answers questions about HomeDock OS features and configuration
|
| 41 |
+
- Provides guidance on self-hosted application setup
|
| 42 |
+
- Understands Docker containerization concepts
|
| 43 |
+
- Explains App Store applications and their use cases
|
| 44 |
+
|
| 45 |
+
## Quantization
|
| 46 |
+
|
| 47 |
+
| File | Size | Description |
|
| 48 |
+
|------|------|-------------|
|
| 49 |
+
| `HomeDock-OS-3B-Instruct.Q4_K_M.gguf` | ~1.8 GB | Recommended, best balance |
|
| 50 |
+
| `HomeDock-OS-3B-Instruct.Q8_0.gguf` | ~3.2 GB | Higher quality |
|
| 51 |
+
|
| 52 |
+
## Usage
|
| 53 |
+
|
| 54 |
+
### Ollama
|
| 55 |
+
|
| 56 |
+
1. Create a `Modelfile`:
|
| 57 |
+
|
| 58 |
+
```
|
| 59 |
+
FROM ./HomeDock-OS-3B-Instruct.Q4_K_M.gguf
|
| 60 |
+
|
| 61 |
+
TEMPLATE """<|im_start|>system
|
| 62 |
+
{{ .System }}<|im_end|>
|
| 63 |
+
<|im_start|>user
|
| 64 |
+
{{ .Prompt }}<|im_end|>
|
| 65 |
+
<|im_start|>assistant
|
| 66 |
+
"""
|
| 67 |
+
|
| 68 |
+
SYSTEM """You are an expert assistant for HomeDock OS documentation. Provide clear, accurate, and helpful information about HomeDock OS features, configuration, and usage."""
|
| 69 |
+
|
| 70 |
+
PARAMETER stop "<|im_end|>"
|
| 71 |
+
PARAMETER stop "<|im_start|>"
|
| 72 |
+
PARAMETER temperature 0.7
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
2. Create and run:
|
| 76 |
+
|
| 77 |
+
```bash
|
| 78 |
+
ollama create homedock -f Modelfile
|
| 79 |
+
ollama run homedock "What is HomeDock OS?"
|
| 80 |
+
```
|
| 81 |
+
|
| 82 |
+
### llama.cpp
|
| 83 |
+
|
| 84 |
+
```bash
|
| 85 |
+
./llama-cli -m HomeDock-OS-3B-Instruct.Q4_K_M.gguf \
|
| 86 |
+
-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" \
|
| 87 |
+
-n 256
|
| 88 |
+
```
|
| 89 |
+
|
| 90 |
+
### LM Studio
|
| 91 |
+
|
| 92 |
+
1. Download the `.gguf` file
|
| 93 |
+
2. Import into LM Studio
|
| 94 |
+
3. Use the ChatML preset or configure manually
|
| 95 |
+
|
| 96 |
+
### Python (llama-cpp-python)
|
| 97 |
+
|
| 98 |
+
```python
|
| 99 |
+
from llama_cpp import Llama
|
| 100 |
+
|
| 101 |
+
llm = Llama(model_path="HomeDock-OS-3B-Instruct.Q4_K_M.gguf", n_ctx=2048)
|
| 102 |
+
|
| 103 |
+
response = llm.create_chat_completion(
|
| 104 |
+
messages=[
|
| 105 |
+
{"role": "system", "content": "You are an expert assistant for HomeDock OS documentation."},
|
| 106 |
+
{"role": "user", "content": "How do I install Plex on HomeDock OS?"}
|
| 107 |
+
]
|
| 108 |
+
)
|
| 109 |
+
print(response["choices"][0]["message"]["content"])
|
| 110 |
+
```
|
| 111 |
+
|
| 112 |
+
## Example Conversations
|
| 113 |
+
|
| 114 |
+
**User:** What is HomeDock OS?
|
| 115 |
+
|
| 116 |
+
**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.
|
| 117 |
+
|
| 118 |
+
---
|
| 119 |
+
|
| 120 |
+
**User:** How do I configure SSL?
|
| 121 |
+
|
| 122 |
+
**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.
|
| 123 |
+
|
| 124 |
+
---
|
| 125 |
+
|
| 126 |
+
**User:** What is the difference between Plex and Jellyfin?
|
| 127 |
+
|
| 128 |
+
**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.
|
| 129 |
+
|
| 130 |
+
## Training Details
|
| 131 |
+
|
| 132 |
+
| Parameter | Value |
|
| 133 |
+
|-----------|-------|
|
| 134 |
+
| Base Model | Qwen/Qwen2.5-3B-Instruct |
|
| 135 |
+
| Method | LoRA (r=16, alpha=32) |
|
| 136 |
+
| Epochs | 3 |
|
| 137 |
+
| Learning Rate | 2e-4 |
|
| 138 |
+
| Sequence Length | 2048 |
|
| 139 |
+
| Training Examples | 788 |
|
| 140 |
+
| Total Words | ~99,000 |
|
| 141 |
+
|
| 142 |
+
### Training Data
|
| 143 |
+
|
| 144 |
+
The model was trained on the complete HomeDock OS documentation including:
|
| 145 |
+
|
| 146 |
+
- Official documentation (MDX)
|
| 147 |
+
- Application descriptions (200+ apps)
|
| 148 |
+
- Blog posts and tutorials
|
| 149 |
+
- Enterprise feature guides
|
| 150 |
+
|
| 151 |
+
## Limitations
|
| 152 |
+
|
| 153 |
+
- Knowledge is specific to HomeDock OS; may not generalize well to other platforms
|
| 154 |
+
- Training data cutoff corresponds to the documentation version at training time
|
| 155 |
+
- Best suited for English queries
|
| 156 |
+
- May occasionally generate plausible-sounding but incorrect information
|
| 157 |
+
|
| 158 |
+
## License
|
| 159 |
+
|
| 160 |
+
This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), same as the base Qwen 2.5 model.
|
| 161 |
+
|
| 162 |
+
## Links
|
| 163 |
+
|
| 164 |
+
- [HomeDock OS Website](https://homedock.cloud)
|
| 165 |
+
- [HomeDock OS Documentation](https://docs.homedock.cloud)
|
| 166 |
+
- [Base Model: Qwen 2.5 3B Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
|
| 167 |
+
|
| 168 |
+
## Citation
|
| 169 |
+
|
| 170 |
+
```bibtex
|
| 171 |
+
@misc{homedock-os-3b-instruct,
|
| 172 |
+
author = {Banshee Technologies S.L.},
|
| 173 |
+
title = {HomeDock-OS-3B-Instruct: A Fine-tuned LLM for HomeDock OS Documentation},
|
| 174 |
+
year = {2025},
|
| 175 |
+
publisher = {Hugging Face},
|
| 176 |
+
url = {https://huggingface.co/banshee/HomeDock-OS-3B-Instruct}
|
| 177 |
+
}
|
| 178 |
+
```
|
| 179 |
+
|
| 180 |
+
---
|
| 181 |
+
|
| 182 |
+
<p align="center">
|
| 183 |
+
<b>Built with HomeDock OS</b><br>
|
| 184 |
+
<a href="https://homedock.cloud">homedock.cloud</a>
|
| 185 |
+
</p>
|