transformers/examples/research_projects
Stas Bekman f284089ec4
[examples tests on multigpu] resolving require_torch_non_multi_gpu_but_fix_me (#10561)
* batch 1

* this is tpu

* deebert attempt

* the rest
2021-03-08 11:11:40 -08:00
..
adversarial Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00
bert-loses-patience [examples tests on multigpu] resolving require_torch_non_multi_gpu_but_fix_me (#10561) 2021-03-08 11:11:40 -08:00
bertabs Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00
bertology Line endings should be LF across repo and not CRLF (#10119) 2021-02-10 10:50:00 -05:00
deebert [examples tests on multigpu] resolving require_torch_non_multi_gpu_but_fix_me (#10561) 2021-03-08 11:11:40 -08:00
distillation Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00
longform-qa Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00
lxmert [research proj] [lxmert] rm bleach dependency (#9970) 2021-02-03 05:24:40 -05:00
mlm_wwm Fit chinese wwm to new datasets (#9887) 2021-02-01 03:37:59 -05:00
mm-imdb Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00
movement-pruning Remove nested lxmert (#9440) 2021-01-07 04:10:41 -05:00
performer Adding performer fine-tuning research exampke (#9239) 2020-12-21 21:19:41 +01:00
pplm Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00
rag [examples tests on multigpu] resolving require_torch_non_multi_gpu_but_fix_me (#10561) 2021-03-08 11:11:40 -08:00
seq2seq-distillation [examples tests on multigpu] resolving require_torch_non_multi_gpu_but_fix_me (#10561) 2021-03-08 11:11:40 -08:00
wav2vec2 fix run seq2seq (#10547) 2021-03-05 18:17:12 +03:00
zero-shot-distillation Zero shot distillation script cuda patch (#10284) 2021-02-19 14:06:57 -05:00
README.md Reorganize examples (#9010) 2020-12-11 10:07:02 -05:00

Research projects

This folder contains various research projects using 🤗 Transformers. They are not maintained and require a specific version of 🤗 Transformers that is indicated in the requirements file of each folder. Updating them to the most recent version of the library will require some work.

To use any of them, just run the command

pip install -r requirements.txt

inside the folder of your choice.

If you need help with any of those, contact the author(s), indicated at the top of the README of each folder.