LM Playground is designed as a universal platform for experimenting with various types of Large Language Models (LLMs) on Android device. It allows users to download different LLMs, load them onto the application, and converse with these models.
- Qwen2.5 0.5B
- Qwen2.5 1.5B
- Llama3.2 1B
- Llama3.2 3B
- Google Gemma2 2B
- Microsoft Phi3.5 mini
- Llama3.1 7B
- Mistral 7B
- Google Gemma2 9B
If you're just looking to install LM Playground, you can find it on Google Play. If you're a developer wanting to contribute, read on.
Prerequisites:
- Android Studio: 2024.1.1+
- NDK: 26.2.11394342
- Clone the repository:
git clone https://github.com/andriydruk/LMPlayground.git
- Open the project in Android Studio:
File>Open> Select the cloned repository. - Connect an Android device or start an emulator.
- Run the application using
Run>Run 'app'or the play button in Android Studio.
This project is licensed under the MIT License.
This project was built based on llama.cpp project. The application uses GGUF-format models with Q4KM quantization from Hugging Face.
If you have any questions, suggestions, or issues, feel free to open an issue or contact me directly at [email protected].