Instructions to use Chantland/HRAF_Multilabel_SubClasses with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chantland/HRAF_Multilabel_SubClasses with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Chantland/HRAF_Multilabel_SubClasses")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Chantland/HRAF_Multilabel_SubClasses") model = AutoModelForSequenceClassification.from_pretrained("Chantland/HRAF_Multilabel_SubClasses") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,12 +15,12 @@ widget:
|
|
| 15 |
---
|
| 16 |
Multi-Label Text classification model used to decode if passages contain a misfortunate event, a cause for misfortune, and/or an action to mollify or prevent some misfortune. Note that at this moment, some labels have been excluded as they are not relevant for the final use of the model
|
| 17 |
8293 passages were used for Training and split into 5 folds (~6634 for train set, ~1659 for validation set over 5 folds). Although multiple parameters were tested, the current model uses:
|
| 18 |
-
learning rate: 2e-5
|
| 19 |
-
weight decay: .01
|
| 20 |
-
Dropout: .1
|
| 21 |
-
Batch Size: 8
|
| 22 |
-
Epochs: 15 (epoch 13 used here)
|
| 23 |
-
The current F1 micro score of 2074 passages not used for training is .637. individual class f1 scores shown below.
|
| 24 |
<ul>
|
| 25 |
<li>EVENT: -
|
| 26 |
<ul>
|
|
|
|
| 15 |
---
|
| 16 |
Multi-Label Text classification model used to decode if passages contain a misfortunate event, a cause for misfortune, and/or an action to mollify or prevent some misfortune. Note that at this moment, some labels have been excluded as they are not relevant for the final use of the model
|
| 17 |
8293 passages were used for Training and split into 5 folds (~6634 for train set, ~1659 for validation set over 5 folds). Although multiple parameters were tested, the current model uses:
|
| 18 |
+
<br>learning rate: 2e-5
|
| 19 |
+
<br>weight decay: .01
|
| 20 |
+
<br>Dropout: .1
|
| 21 |
+
<br>Batch Size: 8
|
| 22 |
+
<br>Epochs: 15 (epoch 13 used here)
|
| 23 |
+
<br><br>The current F1 micro score of 2074 passages not used for training is .637. individual class f1 scores shown below.
|
| 24 |
<ul>
|
| 25 |
<li>EVENT: -
|
| 26 |
<ul>
|