Instructions to use marshadbits/athena-functiongemma-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use marshadbits/athena-functiongemma-270m 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 marshadbits/athena-functiongemma-270m:F16
# Run inference directly in the terminal:
llama cli -hf marshadbits/athena-functiongemma-270m:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf marshadbits/athena-functiongemma-270m:F16
# Run inference directly in the terminal:
llama cli -hf marshadbits/athena-functiongemma-270m:F16

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 marshadbits/athena-functiongemma-270m:F16
# Run inference directly in the terminal:
./llama-cli -hf marshadbits/athena-functiongemma-270m:F16

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 marshadbits/athena-functiongemma-270m:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf marshadbits/athena-functiongemma-270m:F16

Use Docker

docker model run hf.co/marshadbits/athena-functiongemma-270m:F16

LM Studio
Jan
Ollama
How to use marshadbits/athena-functiongemma-270m with Ollama:
```
ollama run hf.co/marshadbits/athena-functiongemma-270m:F16
```

Unsloth Studio

How to use marshadbits/athena-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 marshadbits/athena-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 marshadbits/athena-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 marshadbits/athena-functiongemma-270m to start chatting

How to use marshadbits/athena-functiongemma-270m with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marshadbits/athena-functiongemma-270m:F16

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": "marshadbits/athena-functiongemma-270m:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use marshadbits/athena-functiongemma-270m with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marshadbits/athena-functiongemma-270m:F16

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 marshadbits/athena-functiongemma-270m:F16

Run Hermes

hermes

OpenClaw new

How to use marshadbits/athena-functiongemma-270m with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marshadbits/athena-functiongemma-270m:F16

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 "marshadbits/athena-functiongemma-270m:F16" \
  --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"

Docker Model Runner
How to use marshadbits/athena-functiongemma-270m with Docker Model Runner:
```
docker model run hf.co/marshadbits/athena-functiongemma-270m:F16
```

Lemonade

How to use marshadbits/athena-functiongemma-270m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marshadbits/athena-functiongemma-270m:F16

Run and chat with the model

lemonade run user.athena-functiongemma-270m-F16

List all available models

lemonade list

Atomic Chat

athena-functiongemma-270m / README.md

marshadbits

Upload README.md with huggingface_hub

0a4c910 verified 14 days ago

preview code

Raw

History Blame Contribute Delete

1.41 kB

	---
	license: gemma
	base_model: google/functiongemma-270m-it
	tags:
	- gguf
	- function-calling
	- tool-use
	- llama.cpp
	---

	# Athena FunctionGemma-270M (fine-tuned)

	LoRA fine-tune of `google/functiongemma-270m-it` for Athena, the on-device HR
	assistant in [Mis-Genie](https://github.com/MAGSoft/Mis-Genie). Text query ->
	structured tool call (name + arguments) only -- never free-form text.

	- Real-eval launch gate (hand-written, naturally-phrased HR queries, distinct
	from training data): 18/20 correct tool+arguments.
	- Synthetic held-out eval: 43/46.
	- Trained on 458 examples covering 7 read-only data tools + a clarification-
	popup fallback for underspecified queries.

	GGUF file (`athena-functiongemma-270m-f16.gguf`) is ready to serve directly
	with `llama-server` (raw llama.cpp, not Ollama) -- pass an explicit
	`"stop": ["<end_function_call>"]` in requests; llama-server has no built-in
	parser for this model's tool-call syntax and will otherwise keep generating
	past the call.

	Two known, understood gaps (not fixed by more training data):
	- Partial employee names ("Taylor" -> "Taylor Reyes") aren't resolved to full
	names -- an entity-resolution problem for the calling application, not the
	model.
	- One specific day-range phrasing ("between March 1st and March 15th") is
	under-represented in training (12/458 examples) and occasionally fails to
	generate a parseable call.