metadata
language: en
license: mit
datasets:
- glue/rte
tags:
- text-classification
- glue
- bert
BertLinearClassifier for RTE
This model is a fine-tuned version of bert-base-uncased on the RTE task from GLUE.
Model Architecture
I've implemented a custom architecture with multiple linear layers on top of BERT:
- Uses BERT base model for feature extraction
- Multiple linear layers with ReLU activations instead of attention
- Simple and efficient classification approach
Usage
This model can be used for textual entailment classification (whether one text logically follows from another).