Instructions to use cpxavier2/codegemma-7b-it-int4-litertlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use cpxavier2/codegemma-7b-it-int4-litertlm with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
CodeGemma 7B IT (INT4 LiteRT LM Model for Android)
This repository contains Google's CodeGemma 7B Instruction-Tuned (google/codegemma-7b-it) quantized to INT4 and packaged into the .litertlm format for on-device execution on Android using Google's LiteRT runtime.
Model Details
- Base Model: google/codegemma-7b-it
- Format:
.litertlm(LiteRT LM Model Bundle) - Quantization: INT4 (
dynamic_wi4_afp32) - Target Runtime: Android LiteRT C++/Kotlin SDK
Usage on Android
Download the .litertlm bundle into your Android app's assets or internal storage and load it via LiteRT-LM:
val modelPath = File(context.filesDir, "codegemma-7b-it-int4.litertlm").absolutePath
val options = ModelOptions.builder()
.setModelPath(modelPath)
.build()
val engine = LiteRtLmEngine.create(options)
val response = engine.generate("Write a Kotlin function to check prime numbers.")
println(response)
- Downloads last month
- -
Model tree for cpxavier2/codegemma-7b-it-int4-litertlm
Base model
google/codegemma-7b-it