Instructions to use acon96/Home-FunctionGemma-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use acon96/Home-FunctionGemma-270m with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="acon96/Home-FunctionGemma-270m",
	filename="Home-FunctionGemma-270m.bf16.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 acon96/Home-FunctionGemma-270m with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf acon96/Home-FunctionGemma-270m:BF16
# Run inference directly in the terminal:
llama-cli -hf acon96/Home-FunctionGemma-270m:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf acon96/Home-FunctionGemma-270m:BF16
# Run inference directly in the terminal:
llama-cli -hf acon96/Home-FunctionGemma-270m:BF16

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 acon96/Home-FunctionGemma-270m:BF16
# Run inference directly in the terminal:
./llama-cli -hf acon96/Home-FunctionGemma-270m:BF16

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 acon96/Home-FunctionGemma-270m:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf acon96/Home-FunctionGemma-270m:BF16

Use Docker

docker model run hf.co/acon96/Home-FunctionGemma-270m:BF16

LM Studio
Jan

vLLM

How to use acon96/Home-FunctionGemma-270m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "acon96/Home-FunctionGemma-270m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "acon96/Home-FunctionGemma-270m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/acon96/Home-FunctionGemma-270m:BF16

Ollama
How to use acon96/Home-FunctionGemma-270m with Ollama:
```
ollama run hf.co/acon96/Home-FunctionGemma-270m:BF16
```

Unsloth Studio new

How to use acon96/Home-FunctionGemma-270m 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 acon96/Home-FunctionGemma-270m 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 acon96/Home-FunctionGemma-270m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for acon96/Home-FunctionGemma-270m to start chatting

Pi new

How to use acon96/Home-FunctionGemma-270m with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf acon96/Home-FunctionGemma-270m:BF16

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": "acon96/Home-FunctionGemma-270m:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use acon96/Home-FunctionGemma-270m with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf acon96/Home-FunctionGemma-270m:BF16

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 acon96/Home-FunctionGemma-270m:BF16

Run Hermes

hermes

Docker Model Runner
How to use acon96/Home-FunctionGemma-270m with Docker Model Runner:
```
docker model run hf.co/acon96/Home-FunctionGemma-270m:BF16
```

Lemonade

How to use acon96/Home-FunctionGemma-270m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull acon96/Home-FunctionGemma-270m:BF16

Run and chat with the model

lemonade run user.Home-FunctionGemma-270m-BF16

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Home-FunctionGemma-270m

The "Home" model is a fine tuning of the FunctionGemma model from Google. The model is able to control devices in the user's house via the "Assist" API, as well as perform basic question answering about the provided home's state.

The model is quantized using Lama.cpp in order to enable running the model in super low resource environments that are common with Home Assistant installations such as Rapsberry Pis.

Training

Datasets

Home Assistant Requests V2 - https://huggingface.co/datasets/acon96/Home-Assistant-Requests-V2

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 16
total_train_batch_size: 32
total_eval_batch_size: 2
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 59
training_steps: 597

License

The model is licensed under the Gemma license as it is a fine-tuning of the FunctionGemma model.

Downloads last month: 1,207

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for acon96/Home-FunctionGemma-270m

Base model

google/functiongemma-270m-it

Finetuned

(410)

this model

Finetunes

1 model

Quantizations