huggingtweets/kidmom777

The model is based on a pre-trained GPT-2 which is fine-tuned on @kidmom777'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 the GPT2 model as it does with the data present in the user's tweets, which further affects the text generated by the model . The final model is logged and versioned at the end of training, and the data is logged at every point of the process . The bot was built by Boris Dayma and is available to create your own bot with the demo,