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

Libraries

How to use BrinqAI/functiongemma-270m-physical-ai with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BrinqAI/functiongemma-270m-physical-ai",
	filename="functiongemma-physical-ai-Q4_K_M.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 BrinqAI/functiongemma-270m-physical-ai with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BrinqAI/functiongemma-270m-physical-ai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BrinqAI/functiongemma-270m-physical-ai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BrinqAI/functiongemma-270m-physical-ai: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 BrinqAI/functiongemma-270m-physical-ai:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BrinqAI/functiongemma-270m-physical-ai: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 BrinqAI/functiongemma-270m-physical-ai:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

Use Docker

docker model run hf.co/BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

LM Studio
Jan

vLLM

How to use BrinqAI/functiongemma-270m-physical-ai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

Ollama
How to use BrinqAI/functiongemma-270m-physical-ai with Ollama:
```
ollama run hf.co/BrinqAI/functiongemma-270m-physical-ai:Q4_K_M
```

Unsloth Studio new

How to use BrinqAI/functiongemma-270m-physical-ai 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 BrinqAI/functiongemma-270m-physical-ai 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 BrinqAI/functiongemma-270m-physical-ai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BrinqAI/functiongemma-270m-physical-ai to start chatting

Pi new

How to use BrinqAI/functiongemma-270m-physical-ai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

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": "BrinqAI/functiongemma-270m-physical-ai:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BrinqAI/functiongemma-270m-physical-ai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BrinqAI/functiongemma-270m-physical-ai: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 BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use BrinqAI/functiongemma-270m-physical-ai with Docker Model Runner:
```
docker model run hf.co/BrinqAI/functiongemma-270m-physical-ai:Q4_K_M
```

Lemonade

How to use BrinqAI/functiongemma-270m-physical-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BrinqAI/functiongemma-270m-physical-ai:Q4_K_M

Run and chat with the model

lemonade run user.functiongemma-270m-physical-ai-Q4_K_M

List all available models

lemonade list

hmahadik commited on 18 days ago

Commit

6d659ec

verified ·

1 Parent(s): 85c8c4c

docs: README updated for v6 (11 tools, Q5_K_M, single-tool 95.5%)

Browse files

Files changed (1) hide show

README.md +21 -18

README.md CHANGED Viewed

@@ -20,33 +20,36 @@ inference: false
 # FunctionGemma 270M — Physical AI
 Fine-tuned [`google/functiongemma-270m-it`](https://huggingface.co/google/functiongemma-270m-it)
-for voice-controlled physical-AI / household-IoT actions. 13 callable tools
-(lights, neopixel patterns, buzzer, alarms, camera, scene description, system
-status, plus a `respond` natural-language fallback for ambiguous or
-out-of-scope prompts). Reference deployment: Synaptics SL2619 "Coral" edge
-board, Google IO 2026 demo.
-The full 13-tool schema ships with this repo as
-[`tools.json`](./tools.json). Token-to-tool mapping is in
-[`token_map.json`](./token_map.json).
 ## Output format — function tokens
-This model emits tool calls as **function tokens**: each tool name is
-compiled to a single special-vocabulary token (`<tool_0>` … `<tool_12>`)
-and a single `<end>` terminator. A complete call decodes in roughly 8–15
-output tokens, vs ~30–80 for native FunctionGemma's
 `<start_function_call>call:NAME{...}<end_function_call>` syntax. On a
 2-core Cortex-A55 this is the difference between sub-second and 2–5 s
 voice-UX latency.
-| File | Sample output | Output tokens |
-|------|---------------|---------------|
-| `functiongemma-physical-ai-Q4_K_M.gguf` | `<tool_3>(3,"red")<end>` | ~8–15 |
-The mapping is maintained in [`token_map.json`](./token_map.json) (e.g.
-`<tool_0>` → `turn_on_lights`, `<tool_3>` → `blink_lights`, `<tool_12>` →
-`respond`).
 ## Quick start (Ollama)

 # FunctionGemma 270M — Physical AI
 Fine-tuned [`google/functiongemma-270m-it`](https://huggingface.co/google/functiongemma-270m-it)
+for voice-controlled physical-AI / household-IoT actions on a Synaptics
+SL2619 "Coral" edge board (Google IO 2026 demo).
+| Revision | File | Tool count | Notes |
+|----------|------|-----------:|-------|
+| **v6 (current)** | [`functiongemma-physical-ai-v6-Q5_K_M.gguf`](./functiongemma-physical-ai-v6-Q5_K_M.gguf) | 11 | Camera + vision dropped. Single-tool routing **95.5%**, multi-tool exact-match 23.9%. |
+| v4c (legacy) | [`functiongemma-physical-ai-Q4_K_M.gguf`](./functiongemma-physical-ai-Q4_K_M.gguf) | 13 | Earlier checkpoint, includes camera/scene tools. |
+Schema ships as [`tools.json`](./tools.json) (11 tools, current). Token-to-tool
+mapping is in [`token_map.json`](./token_map.json).
 ## Output format — function tokens
+Tool calls emit as **function tokens**: each tool name compiles to a single
+special-vocabulary token (`<tool_0>` … `<tool_10>` for v6) and a single
+`<end>` terminator. A complete call decodes in roughly 8–15 output tokens,
+vs ~30–80 for native FunctionGemma's
 `<start_function_call>call:NAME{...}<end_function_call>` syntax. On a
 2-core Cortex-A55 this is the difference between sub-second and 2–5 s
 voice-UX latency.
+Sample output: `<tool_3>(3,"red")<end>` for `blink_lights(count=3, color="red")`.
+`<tool_0>` → `turn_on_lights`, `<tool_3>` → `blink_lights`,
+`<tool_9>` → `get_system_status`, `<tool_10>` → `respond` (v6 numbering).
+Full mapping in [`token_map.json`](./token_map.json).
+> ⚠️ Inference servers MUST stop generation on `<end_of_turn>` (or `<eos>`),
+> NOT on `<end>`. Multi-tool sequences emit `<tool_A>(args)<end><tool_B>(args)<end>`,
+> so stopping at the first `<end>` truncates legitimate multi-tool output.
 ## Quick start (Ollama)