huggingtweets/donwinslow

The model is based on a pre-trained GPT-2 which is fine-tuned on @donwinslow'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: pipeline('text-generation') model='huggingtweets/donwanslow') model="HuggingTweets" model="My dream is", num_return_sequences=5" Model="HUGINGtweet" is trained on the user's tweets, and the model suffers from the same limitations and bias as GPT2 . For more details, visit the,