huggingtweets/theneedledrop

The model is based on a pre-trained GPT-2 which is fine-tuned on @theneedledrop'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/theneedlingrop') model="My dream is", num_return_sequences=5) The model suffers from the same limitations and bias as GPT2 . The model was trained on the user's tweets, and the data present in the tweets further affects the text generated by the model . For more details, visit the project,