Instructions to use gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm with Transformers:

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

pipe = pipeline("text-generation", model="gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm")
model = AutoModelForCausalLM.from_pretrained("gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm

SGLang

How to use gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm 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 "gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm" \
    --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": "gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm",
		"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 "gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm" \
        --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": "gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm with Docker Model Runner:
```
docker model run hf.co/gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm
```

Model Card for funcgemma-mobile-actions

This model is a fine-tuned version of google/functiongemma-270m-it, coverted to the edge-friendly, quantized .litertlm format.
It has been trained using TRL.

Training was done fully local on a PC with a 32GB Nvidia RTX Pro 4500 GPU (comparable to an RTX 5080) and took roughly 25 mins.
The script was derived from the Google Colab example and is available at ai-bits.org's FunctionGemma repo.

Quick start for the converted-to-litertlm model for Android

Install the Google AI Edge Gallery app from the Play Store. Start Edge Gallery.
In the mobile browser download the .litertlm model version (just one file) from Files and versions here. (Sorry for the littering with a faulty repo gen.)
Click the bottom right plus button in the app to install the litertlm model from Downloads.
Try it in the now populated Mobile Actions widget.

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.25.1
Transformers: 4.57.1
Pytorch: 2.9.1
Datasets: 4.4.1
Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 10

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for gue22/functiongemma-mobile-actions_q8_ekv1024.litertlm

Base model

google/functiongemma-270m-it

Finetuned

(440)

this model