huggingface/tflite-android-transformers
Android demo apps that run DistilBERT and GPT-2 models on-device using TensorFlow Lite for offline question answering and text generation.
Not currently ranked — collecting fresh signals.
star history
This repository provides Android demo applications and conversion scripts for running transformer models on mobile devices. It includes a DistilBERT model fine-tuned on SQuAD for question answering and a GPT-2/DistilGPT2 model for text generation, both optimized via TensorFlow Lite for on-device inference. The models can run entirely offline on Android devices with GPU acceleration.
Frequently asked
- What is huggingface/tflite-android-transformers?
- Android demo apps that run DistilBERT and GPT-2 models on-device using TensorFlow Lite for offline question answering and text generation.
- Is tflite-android-transformers open source?
- Yes — huggingface/tflite-android-transformers is open source, released under the Apache-2.0 license.
- What language is tflite-android-transformers written in?
- huggingface/tflite-android-transformers is primarily written in Java.
- How popular is tflite-android-transformers?
- huggingface/tflite-android-transformers has 421 stars on GitHub.
- Where can I find tflite-android-transformers?
- huggingface/tflite-android-transformers is on GitHub at https://github.com/huggingface/tflite-android-transformers.