huggingtweets/texttheater

The model is based on a pre-trained GPT-2 which is fine-tuned on @texttheater'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: pipeline('text-generation', model='huggingtweets/text theater) model="My dream is", num_return_sequences=5) The model suffers from the same limitations and bias as GPT2 . The model uses the following pipeline. The model was trained on the user's tweets. The data present in the tweets further affects the text generated by the model. The final model,