huggingtweets/prof_jtaylor

The model is based on a pre-trained GPT-2 which is fine-tuned on @prof_jtaylor's tweets . The data is tracked with W&B artifacts at every step of the pipeline . The model suffers from the same limitations and bias as GPT 2 . The bot was built by Boris Dayma and was created with huggingtweets. The model uses the following pipeline: pipeline('text-generation', model('My dream is) model('Huggingtweet/prof_Jtaylor') model="My dream is", num_return_sequences=5. The final model is logged and versioned at the end of training,