|
Merge internal changes (#283)
|
Myle Ott
|
|
5 years ago |
|
Merge internal changes (#422)
|
Myle Ott
|
|
5 years ago |
|
fixed torch 0.4.0 , "RuntimeError: Expected object of type torch.cuda… (#393)
|
linkerr
|
|
5 years ago |
|
fbshipit-source-id: 6a835d32f9dc5e0de118f1b46d365d0e0cc85e11
|
myleott
|
|
5 years ago |
|
core changes to support latte collab
|
Alexei Baevski
|
|
5 years ago |
|
Pass encoder_input to generator, rather than src_tokens/src_lengths.
|
Stephen Roller
|
|
5 years ago |
|
Revert sequence generator changes
|
Myle Ott
|
|
5 years ago |
|
Sequence generator bug fix.
|
Stephen Roller
|
|
5 years ago |
|
Generator: net_input instead of manual src_tokens.
|
Stephen Roller
|
|
5 years ago |
|
Diverse Beam Search
|
Myle Ott
|
|
5 years ago |
|
Factor out search logic in SequenceGenerator
|
Myle Ott
|
|
5 years ago |
|
Iterate on need_attn and fix tests
|
Myle Ott
|
|
5 years ago |
|
disable printing alignment by default (for perf) and add a flag to enable it
|
Alexei Baevski
|
|
5 years ago |
|
Move reorder_encoder_out to FairseqEncoder and fix non-incremental decoding
|
Myle Ott
|
|
5 years ago |
|
Faster generation when using a single model (rather than ensemble)
|
Myle Ott
|
|
6 years ago |
|
Fix tests
|
Myle Ott
|
|
6 years ago |
|
Updates for latest PyTorch
|
Myle Ott
|
|
6 years ago |
|
Add FairseqTask
|
Myle Ott
|
|
6 years ago |
|
Fix length penalty when combined with --no-early-stop
|
Myle Ott
|
|
6 years ago |
|
Nits
|
Myle Ott
|
|
6 years ago |
|
added multiscale gated self attention layer with multiple heads, and pretrained fusion models
|
Angela Fan
|
|
6 years ago |
|
Conv lm implementation
|
alexeib
|
|
6 years ago |
|
fix alignment when using uneven batches and left pad
|
Alexei Baevski
|
|
6 years ago |
|
Fix --prefix-size
|
Myle Ott
|
|
6 years ago |
|
make sure tensor used to index is cuda if on gpu
|
Alexei Baevski
|
|
6 years ago |
|
Remove src-padding from generation output
|
Myle Ott
|
|
6 years ago |
|
remove completed sentences from batch
|
Alexei Baevski
|
|
6 years ago |
|
Merge internal changes (#136)
|
Myle Ott
|
|
6 years ago |
|
Enforce upper-bound on maximum generation length (#121)
|
Myle Ott
|
|
6 years ago |
|
Allow more flexible pre-processing and generation (#227)
|
Sergey Edunov
|
|
6 years ago |