Runway port of the Transformer-XL Model by CMU/Google Brain using huggingface/transformers
XLNet was introduced in the paper Transformer-XL: Attentive Language Models Beyond a Fixed-Length ContextZihang Dai*, Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov (*: equal contribution) at CMU/Google Brain.
Code was adapted from the excellent run_generation script and weights provided by huggingface/transformers.