Each python notebook includes the usage of 2 models for text classification.
Text_Classification_BERT.ipynb leverages the "bert-base-uncased" model to tokenize, encode and perform text classification on the given dataset. The first section includes dataset analysis to better understand how the data is distributed. The second section involves creating encodings, training and evaluation of the model. In the final section certain text samples are tested with the trained model to predict topic categories.
Text_Classification_GPT2.ipynb notebook is structed in a similar way as mentioned above.