huggingtweets/guggersylvain

The model is based on a pre-trained GPT-2 which is fine-tuned on @guggersylvain'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 final model is logged and versioned at the end of training . The model suffers from the same limitations and bias as the model as GPT 2 . The bot was built by Boris Dayma and was created with huggingtweets. The model uses the following pipeline. The data present in the user's tweets further affects the text generated by the model. For more details, visit the project repository,