huggingtweets/cylinderlife

The model is based on a pre-trained GPT-2 which is fine-tuned on @cylinderlife's tweets . The data is tracked with W&B artifacts at every step of the pipeline . The model uses the following pipeline: "Huggingtweets/Cylinder" and "My dream is" The model suffers from the same limitations and bias as GPT 2 . The final model is logged and versioned at the end of the training run for full transparency and reproducibility . You can use this model directly with a pipeline for text generation: 'Hugingtweet/cylinder life' The model was trained on the user's tweets,