Instructions to use frodo21/briefly-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use frodo21/briefly-models 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
Add model card and Gemma license notice
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
base_model: google/gemma-3n-E2B-it-litert-preview
|
| 4 |
+
tags:
|
| 5 |
+
- litert
|
| 6 |
+
- mediapipe
|
| 7 |
+
- on-device
|
| 8 |
+
- android
|
| 9 |
+
- gemma-3n
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# briefly-models
|
| 13 |
+
|
| 14 |
+
Mirror of the LiteRT / MediaPipe `.task` build of **Gemma 3n E2B (int4)**, re-hosted for
|
| 15 |
+
on-device download by the **Briefly** Android news reader.
|
| 16 |
+
|
| 17 |
+
This is an unmodified copy of the file published by Google. Nothing has been fine-tuned,
|
| 18 |
+
re-quantised or otherwise changed. It lives here only because the app's release channel
|
| 19 |
+
cannot serve files larger than 2 GB.
|
| 20 |
+
|
| 21 |
+
## Files
|
| 22 |
+
|
| 23 |
+
| File | Size | SHA-256 |
|
| 24 |
+
|---|---|---|
|
| 25 |
+
| `gemma-3n-e2b-it-int4.task` | 3,136,226,711 bytes | `a7f544cfee68f579fabadb22aa9284faa4020a0f5358d0e15b49fdd4cefe4200` |
|
| 26 |
+
|
| 27 |
+
Source: [`google/gemma-3n-E2B-it-litert-preview`](https://huggingface.co/google/gemma-3n-E2B-it-litert-preview) → `gemma-3n-E2B-it-int4.task`
|
| 28 |
+
|
| 29 |
+
Direct download:
|
| 30 |
+
`https://huggingface.co/frodo21/briefly-models/resolve/main/gemma-3n-e2b-it-int4.task`
|
| 31 |
+
|
| 32 |
+
## Intended use
|
| 33 |
+
|
| 34 |
+
Fetched at runtime by Briefly and executed locally through the MediaPipe LLM Inference API
|
| 35 |
+
to summarise articles on the device, without sending article text to any server.
|
| 36 |
+
|
| 37 |
+
## License
|
| 38 |
+
|
| 39 |
+
Gemma is provided under and subject to the Gemma Terms of Use found at
|
| 40 |
+
[ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms).
|
| 41 |
+
|
| 42 |
+
By downloading or using this file you agree to those terms and to the
|
| 43 |
+
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
|
| 44 |
+
|
| 45 |
+
Gemma is a trademark of Google LLC. This repository is an independent mirror and is not
|
| 46 |
+
affiliated with, sponsored by, or endorsed by Google.
|