metadata

library_name: tflite
license: gemma
pipeline_tag: text-generation
tags:
  - tflite
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
  To access Gemma on Hugging Face, you’re required to review and agree to
  Google’s usage license. To do this, please ensure you’re logged-in to Hugging
  Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license

Gemma Model Card

TensorFlow Lite

Model Page: Gemma

A 4-bit, 8-bit, GPU-compatible and CPU-compatible TensorFlow Lite implementation of the Gemma 2B instruction-tuned model, optimized for on-device machine learning. A 2B parameter base model that has been instruction-tuned to respond to prompts in a conversational manner.

This is Gemma 1.1 2B (IT), an update over the original instruction-tuned Gemma release.

Resources and Technical Documentation:

Responsible Generative AI Toolkit
Gemma on Kaggle
Gemma on Vertex Model Garden

Terms of Use: Terms

Authors: Google