Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: meta-llama/Llama-3-8B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- torchchat
|
| 6 |
+
- executorch
|
| 7 |
+
- pte
|
| 8 |
+
- mobile
|
| 9 |
+
- on-device
|
| 10 |
+
---
|
| 11 |
+
# Llama 3 8B Instruct PTE
|
| 12 |
+
|
| 13 |
+
This model is a mobile optimized, quantized version of llama 3 8b instruct for use with executorch and torchchat.
|
| 14 |
+
|
| 15 |
+
# Android
|
| 16 |
+
|
| 17 |
+
use this guide to install [torchchat & executorch](https://github.com/pytorch/torchchat)
|
| 18 |
+
|
| 19 |
+
# iOS
|
| 20 |
+
|
| 21 |
+
Available using XCode, iPhone 13 Pro+ and newer. this method also requires install of [torchchat & executorch](https://github.com/pytorch/torchchat)
|
| 22 |
+
|
| 23 |
+
# Eval
|
| 24 |
+
|
| 25 |
+
coming soon
|
| 26 |
+
|
| 27 |
+
## Recreate using other supported models
|
| 28 |
+
|
| 29 |
+
[colab - coming soon]()
|