Commits · a3daabfe14d374081e3abff736e41569e701bf60 · chenpangpang / transformers

"...lm-evaluation-harness.git" did not exist on "72d619ffdb075be0261e60d3bcd2d91e155b5580"

30 Apr, 2021 1 commit
- Update README.md (#11489) · 58c789e3
  Manuel Romero authored Apr 30, 2021
```
Add link to code
```
  58c789e3
02 Apr, 2021 1 commit
- fixed typo: logging instead of logger (#11025) · 335c0ca3
  versis authored Apr 02, 2021
  
  335c0ca3
15 Mar, 2021 1 commit
- zero-shot pipeline multi_class -> multi_label (#10727) · 966ba081
  Joe Davison authored Mar 15, 2021
  
  966ba081
19 Feb, 2021 1 commit
- Zero shot distillation script cuda patch (#10284) · cbadb524
  Joe Davison authored Feb 19, 2021
  
  cbadb524
18 Feb, 2021 1 commit

Script for distilling zero-shot classifier to more efficient student (#10244) · c6fe1755

Joe Davison authored Feb 18, 2021



* add zero-shot distillation script

* readme wordsmithing

* clean up code

* add multi-gpu teacher inference
plus tidying up more code

* add use_fast_tokenizer arg

* update results in readme

* more readme wordsmithing

* style

* Add handle to readme
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* fix code block

* add error+docs about distributed & tpu

* add @sgugger format requests

* xla -> tpu

* support fp16 for teacher preds

* no checkpoint by default

* add demo colab link

* add model sharing prompt + model link

* correct resulting acc of example
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

c6fe1755