Add link to Neuron-optimized version
#14
by
badaoui
HF Staff
- opened
README.md
CHANGED
|
@@ -91,3 +91,15 @@ year={2021},
|
|
| 91 |
url={https://openreview.net/forum?id=XPZIaotutsD}
|
| 92 |
}
|
| 93 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
url={https://openreview.net/forum?id=XPZIaotutsD}
|
| 92 |
}
|
| 93 |
```
|
| 94 |
+
|
| 95 |
+
---
|
| 96 |
+
## 🚀 AWS Neuron Optimized Version Available
|
| 97 |
+
|
| 98 |
+
A Neuron-optimized version of this model is available for improved performance on AWS Inferentia/Trainium instances:
|
| 99 |
+
|
| 100 |
+
**[badaoui/microsoft-deberta-v3-large-neuron](https://huggingface.co/badaoui/microsoft-deberta-v3-large-neuron)**
|
| 101 |
+
|
| 102 |
+
The Neuron-optimized version provides:
|
| 103 |
+
- Pre-compiled artifacts for faster loading
|
| 104 |
+
- Optimized performance on AWS Neuron devices
|
| 105 |
+
- Same model capabilities with improved inference speed
|