Spaces:

cpllab
/

syntaxgym

Running

App Files Files Community

Ctrl+K

Ctrl+K

2 contributors

History: 20 commits

Jon Gauthier

fall back to GPT2TokenizerFast for models which don't have a fast tokenizer (like OPT)

0d58633 over 2 years ago

.gitattributes

1.17 kB

initial commit almost 3 years ago
.gitignore

12 Bytes

move metric and tests from dataset repo almost 3 years ago
README.md

7.88 kB

document accuracy property almost 3 years ago
app.py

138 Bytes

stage template files almost 3 years ago
prediction.py

7.46 kB

move metric and tests from dataset repo almost 3 years ago
requirements.txt

58 Bytes

update evaluate dependency over 2 years ago
syntaxgym.py
13.9 kB

fall back to GPT2TokenizerFast for models which don't have a fast tokenizer (like OPT) over 2 years ago
test.py

21.9 kB

interface change: use namedtuple for metric result so that we can add an `accuracy` property and have dot-access almost 3 years ago