Instructions to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="renhehuang/functiongemma-270m-it-coffee-robot-mcp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("renhehuang/functiongemma-270m-it-coffee-robot-mcp")
model = AutoModelForCausalLM.from_pretrained("renhehuang/functiongemma-270m-it-coffee-robot-mcp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="renhehuang/functiongemma-270m-it-coffee-robot-mcp",
	filename="coffee-robot-functiongemma.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 renhehuang/functiongemma-270m-it-coffee-robot-mcp with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp
# Run inference directly in the terminal:
llama-cli -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp
# Run inference directly in the terminal:
llama-cli -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp

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 renhehuang/functiongemma-270m-it-coffee-robot-mcp
# Run inference directly in the terminal:
./llama-cli -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp

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 renhehuang/functiongemma-270m-it-coffee-robot-mcp
# Run inference directly in the terminal:
./build/bin/llama-cli -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp

Use Docker

docker model run hf.co/renhehuang/functiongemma-270m-it-coffee-robot-mcp

LM Studio
Jan

vLLM

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/renhehuang/functiongemma-270m-it-coffee-robot-mcp

SGLang

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "renhehuang/functiongemma-270m-it-coffee-robot-mcp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "renhehuang/functiongemma-270m-it-coffee-robot-mcp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "renhehuang/functiongemma-270m-it-coffee-robot-mcp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "renhehuang/functiongemma-270m-it-coffee-robot-mcp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with Ollama:
```
ollama run hf.co/renhehuang/functiongemma-270m-it-coffee-robot-mcp
```

Unsloth Studio new

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp 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 renhehuang/functiongemma-270m-it-coffee-robot-mcp 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 renhehuang/functiongemma-270m-it-coffee-robot-mcp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for renhehuang/functiongemma-270m-it-coffee-robot-mcp to start chatting

Pi new

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp

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": "renhehuang/functiongemma-270m-it-coffee-robot-mcp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf renhehuang/functiongemma-270m-it-coffee-robot-mcp

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 renhehuang/functiongemma-270m-it-coffee-robot-mcp

Run Hermes

hermes

Docker Model Runner
How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with Docker Model Runner:
```
docker model run hf.co/renhehuang/functiongemma-270m-it-coffee-robot-mcp
```

Lemonade

How to use renhehuang/functiongemma-270m-it-coffee-robot-mcp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull renhehuang/functiongemma-270m-it-coffee-robot-mcp

Run and chat with the model

lemonade run user.functiongemma-270m-it-coffee-robot-mcp-{{QUANT_TAG}}

List all available models

lemonade list

☕ Coffee Robot MCP - FunctionGemma 270M

基於 google/functiongemma-270m-it 微調的咖啡機器人外送任務 Function Calling 模型。（此為企業內部點餐 api 整合測試模型）

📋 模型描述

此模型專門針對咖啡機器人外送場景進行微調，能夠將自然語言指令轉換為結構化的 Function Call，適用於 MCP (Model Context Protocol) 整合。

主要特點

🎯 專注於咖啡外送任務的 Function Calling
🇹🇼 支援繁體中文自然語言輸入
⚡ 輕量化模型（270M 參數），適合邊緣部署
🔧 相容 MCP 協議格式

🛠️ 支援功能

Function: `send_coffee`

參數	類型	說明	可選值
`baseDrink`	string	飲品種類	`americano`, `latte`, `oat_latte`, `milk`
`floor`	integer	配送樓層	1-11
`temperature`	string	飲品溫度	`hot`, `iced`
`addons`	array	加購選項	`extra_espresso`, `paper_cup`
`quantity`	integer	數量	1-10

📊 模型效能

指標	基礎模型	微調後模型
Function Calling 準確率	95.95%	100.00%
提升幅度	-	+4.05%

訓練配置

訓練輪數: 3
學習率: 1e-05
有效批次大小: 16
訓練樣本數: 625
驗證樣本數: 74

💻 使用方式

基本使用

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

model_id = "renhehuang/functiongemma-270m-it-coffee-robot-mcp"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

tools = [
    {
        "type": "function",
        "function": {
            "name": "send_coffee",
            "description": "送咖啡到指定樓層",
            "parameters": {
                "type": "object",
                "properties": {
                    "baseDrink": {"type": "string", "enum": ["americano", "latte", "oat_latte", "milk"]},
                    "floor": {"type": "integer", "minimum": 1, "maximum": 11},
                    "temperature": {"type": "string", "enum": ["hot", "iced"]},
                    "addons": {"type": "array", "items": {"type": "string", "enum": ["extra_espresso", "paper_cup"]}},
                    "quantity": {"type": "integer", "minimum": 1, "maximum": 10},
                },
                "required": ["baseDrink", "floor", "temperature", "quantity"],
            },
        },
    }
]

messages = [{"role": "user", "content": "幫我送一杯熱美式到五樓"}]

prompt = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    tokenize=False,
    add_generation_prompt=True,
)

out = pipe(prompt, max_new_tokens=256, do_sample=False)
print(out[0]["generated_text"][len(prompt):])

輸出範例

輸入: "幫我送一杯熱美式到五樓"

輸出:

<start_function_call>call: send_coffee{baseDrink:<escape>americano<escape>, floor:<escape>5<escape>, temperature:<escape>hot<escape>, quantity:<escape>1<escape>}<end_function_call>

🔗 MCP 整合

此模型可與 MCP Server 整合，實現自動化咖啡外送流程：

# 解析 Function Call
import re

def parse_function_call(output):
    pattern = r"<start_function_call>(.*?)<end_function_call>"
    matches = re.findall(pattern, output, re.DOTALL)
    # 解析並回傳結構化資料
    return matches

⚠️ 限制與注意事項

領域限制: 此模型專為咖啡外送場景設計，不適用於其他 Function Calling 任務
語言支援: 主要支援繁體中文，其他語言效果可能不佳
樓層範圍: 僅支援 1-11 樓
飲品種類: 僅支援 4 種飲品類型

📝 引用

@misc{coffee-robot-mcp-2025,
  title={Coffee Robot MCP - FunctionGemma Fine-tuned Model},
  author={renhehuang},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/renhehuang/functiongemma-270m-it-coffee-robot-mcp}
}

📄 授權

本模型基於 Gemma License 授權。使用前請確認已接受 Google Gemma 的使用條款。

🙏 致謝

Google - 提供 FunctionGemma 基礎模型
Hugging Face - 提供模型託管與訓練工具

Downloads last month: 94

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for renhehuang/functiongemma-270m-it-coffee-robot-mcp

Base model

google/functiongemma-270m-it

Quantized

(48)

this model

Evaluation results

Accuracy on Coffee Robot MCP Dataset
self-reported

1.000