agemagician

MLongT5 (transient-global attention, large-sized model) MLongT5 model pre-trained on Multi-language corpus. The model was introduced in the paper mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences by Uthus et al. and first released in the LongT5 repository. All the model architecture and configuration can be found in Flaxformer repository which uses another Google research project repository T5x. Disclaimer: The team releasing MLongT5 did not write a model card for this model so this model card has been written by Ahmed Elnaggar. Model description MLongT5 model is an encoder-decoder transformer pre-trained in a text-to-text denoising generative setting (Pegasus-like generation pre-training). MLongT5 model is an extension of LongT5 model, and it enables using one of the two different efficient attention mechanisms - (1) Local attention, or (2) Transient-Global attention. The usage of attention sparsity patterns allows the model to efficiently handle input sequence. MLongT5 is particularly effective when fine-tuned for text generation (summarization, question answering) which requires handling long input sequences (up to 16,384 tokens). The model is mostly meant to be fine-tuned on a supervised dataset. See the model hub to look for fine-tuned versions on a task that interests you. The following shows how one can extract the last hidden representation for the model. The following shows how one can predict masked passages using the different denoising strategies. For S-Denoising, please make sure to prompt the text with the prefix `[S2S]` as shown below. For R-Denoising, please make sure to prompt the text with the prefix `[NLU]` as shown below. For X-Denoising, please make sure to prompt the text with the prefix `[NLG]` as shown below.