Instructions to use jqueryjs/gemma-4-E2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use jqueryjs/gemma-4-E2B with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=jqueryjs/gemma-4-E2B \ --prompt="Write me a poem"
- LiteRT
How to use jqueryjs/gemma-4-E2B 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
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
library_name: litert-lm
|
| 4 |
+
tags:
|
| 5 |
+
- android
|
| 6 |
+
- edge-ai
|
| 7 |
+
- on-device
|
| 8 |
+
- litert
|
| 9 |
+
- gemma
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Gemma 4 E2B IT (.litertlm) - Android Application Mirror
|
| 13 |
+
|
| 14 |
+
This repository hosts an unmodified copy of the pre-compiled **Gemma 4 E2B IT** model in the `.litertlm` format.
|
| 15 |
+
|
| 16 |
+
## Purpose
|
| 17 |
+
This repository serves as a dedicated, stable mirror for an Android application backend. Hosting a dedicated copy ensures:
|
| 18 |
+
* **Dependency Stability:** The app's download functionality will not break if upstream repositories are altered or removed.
|
| 19 |
+
* **Direct Asset Delivery:** Provides a clean, direct URL for the Android `DownloadManager` or HTTP client to stream the binary onto the user's device storage.
|
| 20 |
+
|
| 21 |
+
## Original Model Attribution
|
| 22 |
+
This is a duplicate of the official Gemma 4 model optimized for on-device deployment via Google's LiteRT (formerly TensorFlow Lite) infrastructure.
|
| 23 |
+
* **Developer:** Google
|
| 24 |
+
* **Model Architecture:** Gemma 4
|
| 25 |
+
* **Format:** `.litertlm` (Optimized binary bundle including weights, tokenizer, and runtime parameters)
|
| 26 |
+
|
| 27 |
+
## Direct Download URL for Android Apps
|
| 28 |
+
To download this model directly within an Android application, target the following `resolve` URL structure:
|
| 29 |
+
|
| 30 |
+
```text
|
| 31 |
+
https://huggingface.co
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## Terms of Use & Licensing
|
| 35 |
+
By downloading or using this model, you agree to the original **Google Gemma Terms of Use**.
|
| 36 |
+
|
| 37 |
+
This model is subject to the Google Gemma License Agreement. Users are responsible for ensuring compliance with Google's acceptable use policies concerning on-device deployment and application distribution.
|