add labels to model card.
Browse files
README.md
CHANGED
|
@@ -21,6 +21,15 @@ pipeline_tag: text-classification
|
|
| 21 |
|
| 22 |
Welcome to the Suicidality Detection AI Model! This project aims to provide a machine learning solution for detecting sequences of words indicative of suicidality in text. By utilizing the ELECTRA architecture and fine-tuning on a diverse dataset, we have created a powerful classification model that can distinguish between suicidal and non-suicidal text expressions.
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Training
|
| 25 |
|
| 26 |
The model was fine-tuned using the ELECTRA architecture on a carefully curated dataset. Our training process involved cleaning and preprocessing various text sources to create a comprehensive training set. The training results indicate promising performance, with metrics including:
|
|
|
|
| 21 |
|
| 22 |
Welcome to the Suicidality Detection AI Model! This project aims to provide a machine learning solution for detecting sequences of words indicative of suicidality in text. By utilizing the ELECTRA architecture and fine-tuning on a diverse dataset, we have created a powerful classification model that can distinguish between suicidal and non-suicidal text expressions.
|
| 23 |
|
| 24 |
+
|
| 25 |
+
## Labels
|
| 26 |
+
|
| 27 |
+
The model classifies input text into two labels:
|
| 28 |
+
|
| 29 |
+
- `LABEL_0`: Indicates that the text is non-suicidal.
|
| 30 |
+
- `LABEL_1`: Indicates that the text is indicative of suicidality.
|
| 31 |
+
|
| 32 |
+
|
| 33 |
## Training
|
| 34 |
|
| 35 |
The model was fine-tuned using the ELECTRA architecture on a carefully curated dataset. Our training process involved cleaning and preprocessing various text sources to create a comprehensive training set. The training results indicate promising performance, with metrics including:
|