huggingtweets/praticoslo

The model is based on a pre-trained GPT-2 which is fine-tuned on @praticoslo'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/praticooslo') The model suffers from the same limitations and bias as GPT2. The data present in the user's tweets further affects the text generated by the model . For more details, visit the project repository . The model was built by Boris Dayma and is available to download and use for training purposes only .,