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}}
}