huggingtweets/wallstreetbets

The model is based on a pre-trained GPT-2 which is fine-tuned on @wallstreetbets'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/wallStreetbets' 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 for full transparency and reproducibility . The final model is logged and versioned at the end of training, the final,