huggingtweets/ericrichards22

The model is based on a pre-trained GPT-2 which is fine-tuned on @ericrichards22'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('My dream is) model="Huggingtweets/ericrichard22') model="My dream is", num_return_sequences=5" Model is trained on the same limitations and bias as GPT2 . The model suffers from the same limitation and bias that the model suffers as well as the data present in the user's tweets further affects,