Model Description
- Based on the uncased BERT pretrained model with a linear output layer.
- Added several commonly-used emoji and tokens to the special token list of the tokenizer.
- Did label smoothing while training.
- Used weighted loss and focal loss to help the cases which trained badly.
Results
Best Result of Macro F1 - 70%
Tutorial Link
- Downloads last month
- 16
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.