Instructions to use rleo/function-gemma-finetuned-tool-call with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rleo/function-gemma-finetuned-tool-call with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rleo/function-gemma-finetuned-tool-call",
	filename="function-gemma-finetuned-tool-call.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 rleo/function-gemma-finetuned-tool-call with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rleo/function-gemma-finetuned-tool-call
# Run inference directly in the terminal:
llama-cli -hf rleo/function-gemma-finetuned-tool-call

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rleo/function-gemma-finetuned-tool-call
# Run inference directly in the terminal:
llama-cli -hf rleo/function-gemma-finetuned-tool-call

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 rleo/function-gemma-finetuned-tool-call
# Run inference directly in the terminal:
./llama-cli -hf rleo/function-gemma-finetuned-tool-call

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 rleo/function-gemma-finetuned-tool-call
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rleo/function-gemma-finetuned-tool-call

Use Docker

docker model run hf.co/rleo/function-gemma-finetuned-tool-call

LM Studio
Jan

vLLM

How to use rleo/function-gemma-finetuned-tool-call with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rleo/function-gemma-finetuned-tool-call

Ollama
How to use rleo/function-gemma-finetuned-tool-call with Ollama:
```
ollama run hf.co/rleo/function-gemma-finetuned-tool-call
```

Unsloth Studio new

How to use rleo/function-gemma-finetuned-tool-call 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 rleo/function-gemma-finetuned-tool-call 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 rleo/function-gemma-finetuned-tool-call to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rleo/function-gemma-finetuned-tool-call to start chatting

Pi new

How to use rleo/function-gemma-finetuned-tool-call with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rleo/function-gemma-finetuned-tool-call

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": "rleo/function-gemma-finetuned-tool-call"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rleo/function-gemma-finetuned-tool-call with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rleo/function-gemma-finetuned-tool-call

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 rleo/function-gemma-finetuned-tool-call

Run Hermes

hermes

Docker Model Runner
How to use rleo/function-gemma-finetuned-tool-call with Docker Model Runner:
```
docker model run hf.co/rleo/function-gemma-finetuned-tool-call
```

Lemonade

How to use rleo/function-gemma-finetuned-tool-call with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rleo/function-gemma-finetuned-tool-call

Run and chat with the model

lemonade run user.function-gemma-finetuned-tool-call-{{QUANT_TAG}}

List all available models

lemonade list

function-gemma-finetuned-tool-call

Fine-tuned Function-Gemma 270M model for bilingual (English/French) tool-calling.

Files

function-gemma-finetuned-tool-call.gguf (F16 merged GGUF)

Base Model

unsloth/functiongemma-270m-it

Training Summary

Method: SFT + LoRA, then merged into full weights
Dataset: custom bilingual EN/FR tool-calling set (dataset_80tools_en_fr.json)
Target behavior: structured function/tool calls with argument extraction and no-tool abstention when appropriate

Local Evaluation (checkpoint benchmark)

From outputs/eval_checkpoint_report.json:

Total cases: 16
Pass rate: 0.8125
Decision accuracy: 0.8125
Tool name accuracy: 0.8125
Argument presence accuracy: 1.0
Tool-call recall: 1.0
No-tool precision: 0.5

Usage (llama.cpp)

llama.cpp/build/bin/llama-cli \
  --model function-gemma-finetuned-tool-call.gguf \
  --ctx-size 32768 \
  --n-gpu-layers 99 \
  --seed 3407 \
  --top-k 64 \
  --top-p 0.95 \
  --temp 1.0 \
  --jinja

For one-shot test:

llama.cpp/build/bin/llama-cli \
  --model function-gemma-finetuned-tool-call.gguf \
  --ctx-size 32768 \
  --n-gpu-layers 99 \
  --seed 3407 \
  --top-k 64 \
  --top-p 0.95 \
  --temp 1.0 \
  --jinja \
  --single-turn \
  --simple-io \
  --prompt "What is the weather in Paris?"

Prompt / Output Format

This model was fine-tuned for Function-Gemma style tool tags (e.g. <start_function_call>...). When used with --jinja, llama.cpp applies the chat template stored in GGUF metadata.

Limitations

Small model (270M): can still over-call tools in ambiguous no-tool prompts.
Best results require strong tool schema prompts and clear user intent.

Intended Use

Lightweight local assistant prototypes
Tool-routing and structured argument extraction tasks
EN/FR bilingual demos and experimentation

Downloads last month: 21

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for rleo/function-gemma-finetuned-tool-call

Base model

google/functiongemma-270m-it

Finetuned

unsloth/functiongemma-270m-it

Quantized

(8)

this model