Instructions to use Abdelkareem/functiongemma-ar-toolcall with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abdelkareem/functiongemma-ar-toolcall with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Abdelkareem/functiongemma-ar-toolcall", dtype="auto")

llama-cpp-python

How to use Abdelkareem/functiongemma-ar-toolcall with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Abdelkareem/functiongemma-ar-toolcall",
	filename="functiongemma_merged_q4km.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Abdelkareem/functiongemma-ar-toolcall 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 Abdelkareem/functiongemma-ar-toolcall
# Run inference directly in the terminal:
llama cli -hf Abdelkareem/functiongemma-ar-toolcall

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abdelkareem/functiongemma-ar-toolcall
# Run inference directly in the terminal:
llama cli -hf Abdelkareem/functiongemma-ar-toolcall

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 Abdelkareem/functiongemma-ar-toolcall
# Run inference directly in the terminal:
./llama-cli -hf Abdelkareem/functiongemma-ar-toolcall

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 Abdelkareem/functiongemma-ar-toolcall
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abdelkareem/functiongemma-ar-toolcall

Use Docker

docker model run hf.co/Abdelkareem/functiongemma-ar-toolcall

LM Studio
Jan
Ollama
How to use Abdelkareem/functiongemma-ar-toolcall with Ollama:
```
ollama run hf.co/Abdelkareem/functiongemma-ar-toolcall
```

Unsloth Studio

How to use Abdelkareem/functiongemma-ar-toolcall 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 Abdelkareem/functiongemma-ar-toolcall 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 Abdelkareem/functiongemma-ar-toolcall to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abdelkareem/functiongemma-ar-toolcall to start chatting

How to use Abdelkareem/functiongemma-ar-toolcall with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abdelkareem/functiongemma-ar-toolcall

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": "Abdelkareem/functiongemma-ar-toolcall"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abdelkareem/functiongemma-ar-toolcall with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abdelkareem/functiongemma-ar-toolcall

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 Abdelkareem/functiongemma-ar-toolcall

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Abdelkareem/functiongemma-ar-toolcall with Docker Model Runner:
```
docker model run hf.co/Abdelkareem/functiongemma-ar-toolcall
```

Lemonade

How to use Abdelkareem/functiongemma-ar-toolcall with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abdelkareem/functiongemma-ar-toolcall

Run and chat with the model

lemonade run user.functiongemma-ar-toolcall-{{QUANT_TAG}}

List all available models

lemonade list

Uploaded model

Developed by: Abdelkareem
License: apache-2.0
Finetuned from model : unsloth/functiongemma-270m-it-unsloth-bnb-4bit

This gemma3_text model was trained 2x faster with Unsloth

Downloads last month: 14

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for Abdelkareem/functiongemma-ar-toolcall

Base model

google/functiongemma-270m-it

Finetuned

unsloth/functiongemma-270m-it-unsloth-bnb-4bit

Quantized

(1)

this model