huggingtweets/cyberglyphic

The model is based on a pre-trained GPT-2 which is fine-tuned on @cyberglyphic'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: pipeline('text-generation', model('My dream is), num_return_sequences=5) The model was trained on the user's tweets. The final model is logged and versioned,