huggingtweets/johnchildren

The model is based on a pre-trained GPT-2 which is fine-tuned on @johnchildren's tweets . Hyperparameters and metrics are recorded in the W&B training run for full transparency and reproducibility . The model suffers from the same limitations and bias as that of the model . You can use this model directly with a pipeline for text generation: pipeline('text-generation) model='huggingtweets/johnchildren') model="My dream is", num_return_sequences=5" The model uses the following pipeline. The model was trained on the user's tweets. The data is tracked with WandB artifacts at every step of,