huggingtweets/shape_nato

The model is based on a pre-trained GPT-2 which is fine-tuned on @shape_nato'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/shape-nato') model="My dream is", num_return_sequences=5" You can also create your own bot based on your favorite user's tweets with the demo . The model suffers from the same limitations and bias as the GPT2 model as well as the data present in the tweets further affects the text generated,