huggingtweets/ibjiyongi

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