Add model documentation
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- gemma
|
| 5 |
+
- mobile
|
| 6 |
+
- offline
|
| 7 |
+
- localbrain
|
| 8 |
+
model_type: gemma
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# LocalBrain Gemma 2B Model
|
| 12 |
+
|
| 13 |
+
This is a Gemma 2B model optimized for mobile devices, designed for the LocalBrain app.
|
| 14 |
+
|
| 15 |
+
## Model Details
|
| 16 |
+
- **Model**: Google Gemma 2B
|
| 17 |
+
- **Format**: TensorFlow Lite
|
| 18 |
+
- **Size**: ~2.5GB
|
| 19 |
+
- **Purpose**: Offline AI chat on mobile devices
|
| 20 |
+
- **App**: LocalBrain - Private AI Assistant
|
| 21 |
+
|
| 22 |
+
## Usage
|
| 23 |
+
This model is specifically packaged for the LocalBrain mobile app, which provides:
|
| 24 |
+
- 100% offline AI conversations
|
| 25 |
+
- Complete privacy (data never leaves device)
|
| 26 |
+
- Fast local processing
|
| 27 |
+
- No API calls required
|
| 28 |
+
|
| 29 |
+
## Download
|
| 30 |
+
The model file `brain-model.bin` can be downloaded directly for use in the LocalBrain app.
|
| 31 |
+
|
| 32 |
+
## License
|
| 33 |
+
This model is released under the Apache 2.0 license, following Google's Gemma licensing terms.
|