funnel-transformer/xlarge

The team releasing Funnel Transformer did not write a model card for this model so this model card has been written by the Hugging Face team . The model is uncased: it does not make a difference between English and English . It's mostly intended to be fine-tuned on tasks that use the whole sentence (potentially masked)to make decisions, such as sequence classification, token classification or question answering . For tasks such as text-generation you should look at model like GPT2. See the model hub to look for details on a task that interests you. For tasks like sequence classification or token classification, you should instead look at GPT1. For example, GPT,