huggingtweets/harry

The model is based on a pre-trained GPT-2 which is fine-tuned on @harry'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/harry") model="HuggingTweets. (My dream is))" model="My dream is", num_return_sequences=5) Model="harry," model('Harry', model('harry,