huggingtweets/cnstnce_

The model is based on a pre-trained GPT-2 which is fine-tuned on @cnstnce_'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 is available for download . For more details, visit the project repository. The model was trained on @cnnstnce's tweets. The data present in the user's tweets further affects the text generated by,