huggingtweets/citizenhush

The model is based on a pre-trained GPT-2 which is fine-tuned on @citizenhush's tweets . You can use this model directly with a pipeline for text generation . The data is tracked with W&B artifacts at every step of the pipeline . At the end of training, the final model is logged and versioned. The model suffers from the same limitations and bias as GPT 2 . The model uses the following pipeline: pipeline('text-generation', model="huggingtweets") model="My dream is", num_return_sequences=5) The model was trained on the user's tweets, and the data present in the,