Instructions to use oxyapi/albert-moderation-001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oxyapi/albert-moderation-001 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="oxyapi/albert-moderation-001")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("oxyapi/albert-moderation-001") model = AutoModelForSequenceClassification.from_pretrained("oxyapi/albert-moderation-001") - Notebooks
- Google Colab
- Kaggle
Add link to Neuron-optimized version
#1
by badaoui HF Staff - opened
README.md
CHANGED
|
@@ -65,4 +65,16 @@ If you find Albert Moderation 001 useful in your research or applications, pleas
|
|
| 65 |
year={2024},
|
| 66 |
howpublished={\url{https://huggingface.co/oxyapi/albert-moderation-001}},
|
| 67 |
}
|
| 68 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
year={2024},
|
| 66 |
howpublished={\url{https://huggingface.co/oxyapi/albert-moderation-001}},
|
| 67 |
}
|
| 68 |
+
```
|
| 69 |
+
|
| 70 |
+
---
|
| 71 |
+
## 🚀 AWS Neuron Optimized Version Available
|
| 72 |
+
|
| 73 |
+
A Neuron-optimized version of this model is available for improved performance on AWS Inferentia/Trainium instances:
|
| 74 |
+
|
| 75 |
+
**[badaoui/oxyapi-albert-moderation-001-neuron](https://huggingface.co/badaoui/oxyapi-albert-moderation-001-neuron)**
|
| 76 |
+
|
| 77 |
+
The Neuron-optimized version provides:
|
| 78 |
+
- Pre-compiled artifacts for faster loading
|
| 79 |
+
- Optimized performance on AWS Neuron devices
|
| 80 |
+
- Same model capabilities with improved inference speed
|