FunctionGemma Mobile Actions v6

A fine-tuned version of FunctionGemma 270M optimized for mobile device function calling. This model excels at understanding natural language commands and mapping them to structured function calls for common mobile actions.

Model Description

  • Base Model: google/gemma-3-1b-it (270M parameters)
  • Fine-tuning Method: LoRA (r=128, alpha=128)
  • Training Data: google/mobile-actions + synthetic augmentation
  • Optimized For: Mobile assistant function calling

Supported Functions

Function Description Example Input
set_alarm Set alarms "Wake me up at 7am"
create_reminder Create reminders "Remind me to buy milk"
set_timer Set countdown timers "Timer for 10 minutes"
make_call Make phone calls "Call Mom"
send_message Send text messages "Text John I'm running late"
create_calendar_event Schedule events "Schedule meeting at 3pm"
play_music Play music "Play some jazz"
get_weather Get weather info "What's the weather like?"
open_app Open applications "Open the camera"
navigate Get directions "Navigate to the airport"
set_volume Adjust volume "Turn the volume up"
calculator Math calculations "What's 15 times 23?"

Usage

from vllm import LLM, SamplingParams

llm = LLM(model="essobi/functiongemma-mobile-actions-v6-16bit", trust_remote_code=True)

# See full documentation for prompt format and tool definitions

Output Format

<start_function_call>call:function_name{param1:<escape>value1<escape>,param2:<escape>value2<escape>}<end_function_call>

License

This model is released under the Gemma License.

Downloads last month
7
Safetensors
Model size
0.3B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for essobi/functiongemma-mobile-actions-v6-16bit

Finetuned
(425)
this model

Dataset used to train essobi/functiongemma-mobile-actions-v6-16bit