Big fan of this work. The headline is only slightly misleading: you'll still need a CUDA-enabled GPU to generate text at a reasonably interactive speed. But you don't have to fine tune a language model beforehand, which…
Big fan of this work. The headline is only slightly misleading: you'll still need a CUDA-enabled GPU to generate text at a reasonably interactive speed. But you don't have to fine tune a language model beforehand, which…