Gemma on Android

This project is an implementation of fine-tuning the Gemma 2b-it model on a custom dataset and deploy the fine-tuned model on Android

Pipeline:

Demo Output:

Steps to run:

1. Clone the repository on your local machine.
2. Open the project in Android Studio.
3. Edit InferenceModel.kt file on Line 44 by replacing YOUR_MODE_NAME.bin with the actual name of your model.
4. Build the project.
5. Install the Android app on your phone and enjoy using SciGemma.

Resources:

1. Follow along three blog series explaining the code in detail:

   Part 1: Step-by-Step Dataset Creation- Unstructured to Structured

   Part 2: Fine Tune - Gemma 2b-it model

   Part 3: Deploying SciGemma on Android

2. Fine-tuned model on 🤗: https://huggingface.co/NSTiwari/fine_tuned_science_gemma2b-it

3. Try our model on HFSpaces: https://huggingface.co/spaces/Aashi/NSTiwari-fine_tuned_science_gemma2b-it?logs=container

4. Checkout demo video on YouTube: https://www.youtube.com/watch?v=T_HDsVHTrwg

Acknowledgment:

This project was developed during Google's ML Developer Programs Gemma sprint. We thank the MLDP team for the opportunity.