Instructions to use dinushiTJ/action-gemma-2-2b-it-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use dinushiTJ/action-gemma-2-2b-it-gguf 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 dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dinushiTJ/action-gemma-2-2b-it-gguf: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 dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf dinushiTJ/action-gemma-2-2b-it-gguf: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 dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

Use Docker

docker model run hf.co/dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use dinushiTJ/action-gemma-2-2b-it-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dinushiTJ/action-gemma-2-2b-it-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dinushiTJ/action-gemma-2-2b-it-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

Ollama
How to use dinushiTJ/action-gemma-2-2b-it-gguf with Ollama:
```
ollama run hf.co/dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M
```
Unsloth Desktop

How to use dinushiTJ/action-gemma-2-2b-it-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dinushiTJ/action-gemma-2-2b-it-gguf: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": "dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use dinushiTJ/action-gemma-2-2b-it-gguf with Docker Model Runner:
```
docker model run hf.co/dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M
```

Lemonade

How to use dinushiTJ/action-gemma-2-2b-it-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

Run and chat with the model

lemonade run user.action-gemma-2-2b-it-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use dinushiTJ/action-gemma-2-2b-it-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dinushiTJ/action-gemma-2-2b-it-gguf: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 dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dinushiTJ/action-gemma-2-2b-it-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dinushiTJ/action-gemma-2-2b-it-gguf: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 "dinushiTJ/action-gemma-2-2b-it-gguf: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"

ActionGemma 2B: GGUF (run it locally)

GGUF builds of ActionGemma 2B, a Gemma 2 2B model fine-tuned for function calling. Use these files to run it on a laptop or CPU with llama.cpp, Ollama or LM Studio. No cloud API is needed, and your data stays on your machine.

Compared with the base model, ActionGemma reaches 93.74% macro F1 (+7.82%), cuts hallucinated function calls from 16% to 6.7%, and uses about 17% fewer tokens. See the main model card for full results, training details and limitations.

Files

File	Quantisation	Size	Notes
`unsloth.Q4_K_M.gguf`	4-bit	1.71 GB	Recommended: best size/quality balance
`unsloth.Q5_K_M.gguf`	5-bit	1.92 GB
`unsloth.Q6_K.gguf`	6-bit	2.15 GB
`unsloth.Q8_0.gguf`	8-bit	2.78 GB	near-lossless
`unsloth.F16.gguf`	16-bit	5.24 GB	full precision

Run it

# Ollama
ollama run hf.co/dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

# llama.cpp
llama-cli -hf dinushiTJ/action-gemma-2-2b-it-gguf:Q4_K_M

Prompt format

The model was trained with the prompt below. Put it at the start of the first user message, with your function definitions (JSON Schema) inside the <functions> tags:

You have access to the following functions enclosed within <functions></functions> tags. Use them if required.
<functions>
{"name": "get_weather", "description": "Get the current weather in a given location",
 "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]}}
</functions>

To call a function, respond using the following format:
<functioncall> {"name": "function_name", "arguments": {"arg_1": "value_1", "arg_2": "value_2", ...}} </functioncall>

If no available function matches the user request, respond politely that you cannot assist with the request.

The model replies with <functioncall> {...} </functioncall>, which is easy to parse with a regex.

LoRA adapter and full model card: dinushiTJ/action-gemma-2-2b-it-lora
Merged FP16 weights for vLLM: dinushiTJ/action-gemma-2-2b-it-vllm-f16
Collection with the training and evaluation datasets

Use of this model is subject to the Gemma Terms of Use. Author: Dinushi Jayasinghe.

Downloads last month: 296

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for dinushiTJ/action-gemma-2-2b-it-gguf

Base model

unsloth/gemma-2-2b-it-bnb-4bit

Adapter

dinushiTJ/action-gemma-2-2b-it-lora

Quantized

(1)

this model

Dataset used to train dinushiTJ/action-gemma-2-2b-it-gguf

Collection including dinushiTJ/action-gemma-2-2b-it-gguf

Action Gemma FT for Function Calling

Collection

Gemma 2 2B fine-tuned for function calling with QLoRA: 93.7% F1, 6% hallucination. LoRA, GGUF and vLLM builds plus train/eval data. • 5 items • Updated 20 days ago

dinushiTJ
/

action-gemma-2-2b-it-gguf

ActionGemma 2B: GGUF (run it locally)

Files

Run it

Prompt format

Related

Model tree for dinushiTJ/action-gemma-2-2b-it-gguf

Dataset used to train dinushiTJ/action-gemma-2-2b-it-gguf

Collection including dinushiTJ/action-gemma-2-2b-it-gguf

Action Gemma FT for Function Calling