Instructions to use Serj/intent-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Serj/intent-classifier with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Serj/intent-classifier") model = AutoModelForSeq2SeqLM.from_pretrained("Serj/intent-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,16 @@ widget:
|
|
| 8 |
example_title: "Open Label Intent Classification"
|
| 9 |
---
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
# Model Card for Model ID
|
| 13 |
|
|
|
|
| 8 |
example_title: "Open Label Intent Classification"
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# Prompt Structure
|
| 12 |
+
Topic %% Customer: text.
|
| 13 |
+
END MESSAGE
|
| 14 |
+
OPTIONS:
|
| 15 |
+
each class separated by %
|
| 16 |
+
Choose one topic that matches customer's issue.
|
| 17 |
+
Class name:
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
You have to have a period after the end of the text, otherwise you'll get funky results. That's how the model was trained.
|
| 21 |
|
| 22 |
# Model Card for Model ID
|
| 23 |
|