Downloads · 30 days
12
31% of all-time downloads
Chantland/Hraf_Multilabel_K-foldsCrossValDemo
Hraf_Multilabel_K-foldsCrossValDemo is a text classification model from Chantland. Use it when you need a label for a piece of text. It is set up for transformers.
Continuation of 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. This version implements 5…
Downloads · 30 days
12
31% of all-time downloads
All-time downloads
39
Public
Repo size
2.1 GB
Likes
0
Public
Click a slice to open those files.
.pt536 MB · 67%
From the Hugging Face model README
Continuation of 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. This version implements 5 fold cross validation to improve model performance. We added additional training sets growing the model to 7277 passages train. The F1 micro score for 1820 passages not used for training or validation (the test set) was .851. individual class f1 scores shown below. <br>EVENT: 0.907 <br>CAUSE: 0.822 <br>ACTION: 0.805 <br>
Compare this to the <a href="https://huggingface.co/Chantland/Hraf_MultiLabel" target="_blank" rel="noopener noreferrer"> old model </a> using the same test set. F1 micro = .828 <br>EVENT: 0.871 <br>CAUSE: 0.81 <br>ACTION: 0.793 <br>
<br><br><br> For a quick demo, try typing in a sentence or even a paragraph in the <b>Hosted inference API</b> then pressing "compute"!