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:
# pip install -U transformers accelerate # 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
|
@@ -116,8 +116,11 @@ Using HF trainer
|
|
| 116 |
## Evaluation
|
| 117 |
|
| 118 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 119 |
-
|
| 120 |
-
|
|
|
|
|
|
|
|
|
|
| 121 |
|
| 122 |
|
| 123 |
#### Summary
|
|
|
|
| 116 |
## Evaluation
|
| 117 |
|
| 118 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 119 |
+
The newest version of the model is finetuned on 2 synthetic datasets Atis dataset and parts of clinc_oos in a few shot manner.
|
| 120 |
+
All datasets have 10-20 samples per class.
|
| 121 |
+
|
| 122 |
+
Atis test set evaluation: weighted F1 90%
|
| 123 |
+
Clinc test set is next.
|
| 124 |
|
| 125 |
|
| 126 |
#### Summary
|