usc_dae
usc_dae copied to clipboard
Repository for Unsupervised Sentence Compression using Denoising Auto-Encoders
 why i get this error?
I wanted to experiment with longer training schedules. How do I re-start a run from it’s fine-tuned checkpoint?
Should be three outputs to unpack from the function self.dictionary.sentences2ids(...)
Not putting all tensor to gpu will cause an error.
Bumps [torch](https://github.com/pytorch/pytorch) from 0.3.1 to 2.2.0. Release notes Sourced from torch's releases. PyTorch 2.2: FlashAttention-v2, AOTInductor PyTorch 2.2 Release Notes Highlights Backwards Incompatible Changes Deprecations New Features Improvements Bug fixes...