Instructions to use DummyTesty/gemmaspark-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use DummyTesty/gemmaspark-model 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
Browse files
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: litert-community/gemma-4-E2B-it-litert-lm
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- hi
|
| 6 |
+
- ta
|
| 7 |
+
- te
|
| 8 |
+
- bn
|
| 9 |
+
- mr
|
| 10 |
+
- gu
|
| 11 |
+
- kn
|
| 12 |
+
- ml
|
| 13 |
+
- or
|
| 14 |
+
- pa
|
| 15 |
+
- ur
|
| 16 |
+
license: gemma
|
| 17 |
+
tags:
|
| 18 |
+
- gemma
|
| 19 |
+
- litert
|
| 20 |
+
- android
|
| 21 |
+
- on-device
|
| 22 |
+
- offline
|
| 23 |
+
- education
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
# Gemma 4 E2B — LiteRT-LM (EdSparkAI)
|
| 27 |
+
|
| 28 |
+
INT4-quantized `.litertlm` model file used by **EdSparkAI**, a fully offline Android AI tutor.
|
| 29 |
+
|
| 30 |
+
Based on [litert-community/gemma-4-E2B-it-litert-lm](https://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm).
|
| 31 |
+
|
| 32 |
+
## File
|
| 33 |
+
|
| 34 |
+
| | |
|
| 35 |
+
|---|---|
|
| 36 |
+
| **Filename** | `model.litertlm` |
|
| 37 |
+
| **Format** | LiteRT-LM (MediaPipe) |
|
| 38 |
+
| **Quantization** | INT4 |
|
| 39 |
+
| **Size** | ~1.4 GB |
|
| 40 |
+
|
| 41 |
+
## Usage
|
| 42 |
+
|
| 43 |
+
This model runs on Android via **MediaPipe LiteRT 0.10.14** on the CPU backend. Used in [EdSparkAI](https://github.com/Destroyer1543/EdSparkAI) — an offline bilingual classroom assistant that explains textbook pages in 12 Indian languages.
|
| 44 |
+
|
| 45 |
+
```kotlin
|
| 46 |
+
val cfg = EngineConfig(
|
| 47 |
+
modelPath = "/path/to/model.litertlm",
|
| 48 |
+
backend = Backend.CPU(),
|
| 49 |
+
maxNumTokens = 2048,
|
| 50 |
+
)
|
| 51 |
+
val engine = Engine(cfg)
|
| 52 |
+
engine.initialize()
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
### Device requirements
|
| 56 |
+
- Android 8.0+ (API 26+)
|
| 57 |
+
- 4 GB RAM minimum
|
| 58 |
+
- 3 GB free storage
|
| 59 |
+
|
| 60 |
+
## License
|
| 61 |
+
|
| 62 |
+
Gemma is a trademark of Google LLC. Use is subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|