huggingtweets/mariobrothblog

The model is based on a pre-trained GPT-2 which is fine-tuned on @mariobrothblog's tweets . The data is tracked with W&B artifacts at every step of the pipeline . You can use this model directly with a pipeline for text generation . The model suffers from the same limitations and bias as that of the GPT 2 model . The bot was built by Boris Dayma and was created with huggingtweets. The model uses the following pipeline. The bot is created with a user's tweets. The data present in the tweets further affects the text generated by the model. You can create your own bot based on your favorite user with the demo,