improved guide
Browse files
README.md
CHANGED
|
@@ -17,18 +17,15 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
| 17 |
Training was done fully local on a PC with a 32GB Nvidia RTX Pro 4500 GPU (comparable to an RTX 5080) and took roughly 25 mins.
|
| 18 |
The script was derived from the [Google Colab example](https://github.com/google-gemini/gemma-cookbook/tree/main/FunctionGemma) and is available at [ai-bits.org's FunctionGemma repo](https://github.com/ai-bits/functiongemma).
|
| 19 |
|
| 20 |
-
## Quick start
|
| 21 |
|
| 22 |
-
Install the Google AI Edge Gallery app from the Play Store.
|
| 23 |
-
In the mobile browser download the litertlm model version from here.
|
| 24 |
-
Click the bottom right plus button to install the litertlm model from Downloads.
|
| 25 |
-
Try.
|
| 26 |
|
| 27 |
## Training procedure
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
This model was trained with SFT.
|
| 33 |
|
| 34 |
### Framework versions
|
|
|
|
| 17 |
Training was done fully local on a PC with a 32GB Nvidia RTX Pro 4500 GPU (comparable to an RTX 5080) and took roughly 25 mins.
|
| 18 |
The script was derived from the [Google Colab example](https://github.com/google-gemini/gemma-cookbook/tree/main/FunctionGemma) and is available at [ai-bits.org's FunctionGemma repo](https://github.com/ai-bits/functiongemma).
|
| 19 |
|
| 20 |
+
## Quick start for the converted-to-litertlm model for Android
|
| 21 |
|
| 22 |
+
Install the Google AI Edge Gallery app from the Play Store. Start Edge Gallery.
|
| 23 |
+
In the mobile browser download the .litertlm model version (just one file) from Files and versions here. (Sorry for the littering with a faulty repo gen.)
|
| 24 |
+
Click the bottom right plus button in the app to install the litertlm model from Downloads.
|
| 25 |
+
Try it in the now populated Mobile Actions widget.
|
| 26 |
|
| 27 |
## Training procedure
|
| 28 |
|
|
|
|
|
|
|
|
|
|
| 29 |
This model was trained with SFT.
|
| 30 |
|
| 31 |
### Framework versions
|