
inseq/wmt21-mlqe-ru-en
Translation
β’
Updated
β’
145
β’
1
Interpretability for Generative Language Models π π
Inseq
π is a Pytorch-based hackable toolkit to democratize access to common post-hoc interpretability analyses for
decoder-only and encoder-decoder sequence generation models.
The Inseq organization on the π€ Hub aims to host valuable models, datasets and demos to improve the
reproducibility of interpretability studies in the field of natural language generation.