Instructions to use ef-dai-team/functiongemma-270m-wallet-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use ef-dai-team/functiongemma-270m-wallet-ft with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ef-dai-team/functiongemma-270m-wallet-ft 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 ef-dai-team/functiongemma-270m-wallet-ft:Q8_0
# Run inference directly in the terminal:
llama cli -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0
# Run inference directly in the terminal:
llama cli -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

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 ef-dai-team/functiongemma-270m-wallet-ft:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

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 ef-dai-team/functiongemma-270m-wallet-ft:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

Use Docker

docker model run hf.co/ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

LM Studio
Jan

vLLM

How to use ef-dai-team/functiongemma-270m-wallet-ft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

Ollama
How to use ef-dai-team/functiongemma-270m-wallet-ft with Ollama:
```
ollama run hf.co/ef-dai-team/functiongemma-270m-wallet-ft:Q8_0
```

Unsloth Studio

How to use ef-dai-team/functiongemma-270m-wallet-ft 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 ef-dai-team/functiongemma-270m-wallet-ft 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 ef-dai-team/functiongemma-270m-wallet-ft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ef-dai-team/functiongemma-270m-wallet-ft to start chatting

How to use ef-dai-team/functiongemma-270m-wallet-ft with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

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": "ef-dai-team/functiongemma-270m-wallet-ft:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ef-dai-team/functiongemma-270m-wallet-ft with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

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 "ef-dai-team/functiongemma-270m-wallet-ft:Q8_0" \
  --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 ef-dai-team/functiongemma-270m-wallet-ft with Docker Model Runner:
```
docker model run hf.co/ef-dai-team/functiongemma-270m-wallet-ft:Q8_0
```

Lemonade

How to use ef-dai-team/functiongemma-270m-wallet-ft with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

Run and chat with the model

lemonade run user.functiongemma-270m-wallet-ft-Q8_0

List all available models

lemonade list

Hermes Agent

How to use ef-dai-team/functiongemma-270m-wallet-ft with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

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 ef-dai-team/functiongemma-270m-wallet-ft:Q8_0

Run Hermes

hermes

Atomic Chat

functiongemma-270m-wallet-ft / README.md

gabrielfior

License: gemma, inherited from the base model

96de29c verified 7 days ago

preview code

Raw

History Blame Contribute Delete

2.43 kB

	---
	license: gemma
	base_model: unsloth/functiongemma-270m-it
	library_name: peft
	pipeline_tag: text-generation
	tags:
	- function-calling
	- tool-use
	- ethereum
	- wallet
	- lora
	- sft
	- gguf
	datasets:
	- ef-dai-team/wallet-tool-calling-ft
	---

	# functiongemma-270m-wallet-ft

	A LoRA fine-tune of `unsloth/functiongemma-270m-it` intended to turn a
	natural-language wallet request into the exact structured tool call a macOS
	Ethereum wallet can execute.

	## ⚠️ This fine-tune did not work

	On the 307-case evaluation set it scores 8.8%, against 8.1% for the
	untuned base model. Every one of its 27 passing cases is a case where the correct
	answer is not to emit a tool call:

	\| Category \| Cases \| Score \|
	\| --- \| --- \| --- \|
	\| transfers \| 101 \| 0% \|
	\| swaps \| 96 \| 0% \|
	\| multi-turn \| 75 \| 0% \|
	\| ablation (clarifying question expected) \| 28 \| 82.1% \|
	\| refusal (no call expected) \| 7 \| 57.1% \|

	Asked to "Send 0.1 ETH to vitalik.eth" it emits `executeTx` with hallucinated
	argument names (`afterQuotes`, `callerName`, `callerString`). Fine-tuning moved
	the core task by nothing.

	Do not deploy this. It is published as a reproducible negative result.

	## What worked instead

	The same dataset and the same LoRA recipe take Gemma-4 E4B from 9.8% to
	80.1% — see [`ef-dai-team/gemma-4-E4B-wallet-ft`](https://huggingface.co/ef-dai-team/gemma-4-E4B-wallet-ft).
	The binding constraint is model capacity, not training data.

	## Contents

	- `functiongemma-270m-wallet-ft.Q8_0.gguf` — merged + quantised, 291 MB, runs via
	`llama-cpp-python`
	- `adapter/` — the LoRA adapter (r=16, α=16) and training state

	## Training data

	[`ef-dai-team/wallet-tool-calling-ft`](https://huggingface.co/datasets/ef-dai-team/wallet-tool-calling-ft)
	— 1739 SFT examples, disjoint from the evaluation set by construction.

	## Evaluation

	Scored by a deterministic binary scorer: a case passes only if every field of
	every emitted call matches gold exactly. Full per-case results, including this
	model's actual output on all 307 cases, are in the
	[eval report Space](https://huggingface.co/spaces/ef-dai-team/wallet-tool-calling-eval).

	## License

	`gemma` — inherited from the base model [`unsloth/functiongemma-270m-it`](https://huggingface.co/unsloth/functiongemma-270m-it). Use is governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
	The training data is Apache-2.0 and licensed separately.