kallantis/Humor-Recognition_Greek-twhin-bert-large

The model is based on TwHIN-BERT large ("Twitter/twhin-bert-large") fine-tuned for Humor Recognition in Greek language.

TwHIN-BERT is a large pre-trained language model for Multilingual Tweets that is trained on 7 billion Tweets from over 100 distinct languages

Model Details

The model was pre-trained over 10 epochs on Greek Humorous Dataset

Pre-processing details

The text needs to be pre-processed by removing all greek diacritics and punctuation and converting all letters to lowercase

Load Pretrained Model

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("kallantis/Humor-Recognition-Greek-twhin-bert-large")
model = AutoModelForSequenceClassification.from_pretrained("kallantis/Humor-Recognition-Greek-twhin-bert-large", num_labels=2, ignore_mismatched_sizes=True)