Add link to Neuron-optimized version
#102
by
badaoui
HF Staff
- opened
README.md
CHANGED
|
@@ -344,3 +344,15 @@ The model is licensed under the [MIT license](https://huggingface.co/microsoft/P
|
|
| 344 |
## Trademarks
|
| 345 |
|
| 346 |
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 344 |
## Trademarks
|
| 345 |
|
| 346 |
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
|
| 347 |
+
|
| 348 |
+
---
|
| 349 |
+
## 🚀 AWS Neuron Optimized Version Available
|
| 350 |
+
|
| 351 |
+
A Neuron-optimized version of this model is available for improved performance on AWS Inferentia/Trainium instances:
|
| 352 |
+
|
| 353 |
+
**[badaoui/microsoft-Phi-3-mini-128k-instruct-neuron](https://huggingface.co/badaoui/microsoft-Phi-3-mini-128k-instruct-neuron)**
|
| 354 |
+
|
| 355 |
+
The Neuron-optimized version provides:
|
| 356 |
+
- Pre-compiled artifacts for faster loading
|
| 357 |
+
- Optimized performance on AWS Neuron devices
|
| 358 |
+
- Same model capabilities with improved inference speed
|