huggingtweets/prisonplanet

The model is based on a pre-trained GPT-2 which is fine-tuned on @prisonplanet'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/prisonplanet') model="My dream is", num_return_sequences=5 . The model suffers from the same limitations and bias as GPT2 . The final model is logged and versioned at the end of training, and the model is versioned . For more details, visit the project repository. The model was built by Boris Day,