huggingtweets/dkulchar

The model is based on a pre-trained GPT-2 which is fine-tuned on @dkulchar's tweets . Hyperparameters and metrics are recorded in the W&B training run for full transparency and reproducibility . At the end of training, the final model is logged and versioned . You can use this model directly with a pipeline for text generation: pipeline('text-generation', model='huggingtweets/kulchar') model="My dream is", num_return_sequences=5" The model suffers from the same limitations and bias as the model as GPT2 . The data present in the user's tweets further affects the,