Instructions to use DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT") model = AutoModelForSequenceClassification.from_pretrained("DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT") - Notebooks
- Google Colab
- Kaggle
Add link to Neuron-optimized version
#2
by badaoui HF Staff - opened
README.md
CHANGED
|
@@ -99,4 +99,16 @@ check_text(model, text, list_label)
|
|
| 99 |
year = {2023},
|
| 100 |
url = {https://arxiv.org/abs/2305.11442},
|
| 101 |
}
|
| 102 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
year = {2023},
|
| 100 |
url = {https://arxiv.org/abs/2305.11442},
|
| 101 |
}
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
---
|
| 105 |
+
## 🚀 AWS Neuron Optimized Version Available
|
| 106 |
+
|
| 107 |
+
A Neuron-optimized version of this model is available for improved performance on AWS Inferentia/Trainium instances:
|
| 108 |
+
|
| 109 |
+
**[badaoui/DAMO-NLP-SG-zero-shot-classify-SSTuning-ALBERT-neuron](https://huggingface.co/badaoui/DAMO-NLP-SG-zero-shot-classify-SSTuning-ALBERT-neuron)**
|
| 110 |
+
|
| 111 |
+
The Neuron-optimized version provides:
|
| 112 |
+
- Pre-compiled artifacts for faster loading
|
| 113 |
+
- Optimized performance on AWS Neuron devices
|
| 114 |
+
- Same model capabilities with improved inference speed
|