SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Styling] stylify using ruff (#27144)

Browse Source 
* try to stylify using ruff

* might need to remove these changes?

* use ruf format andruff check

* use isinstance instead of type comparision

* use # fmt: skip

* use # fmt: skip

* nits

* soem styling changes

* update ci job

* nits isinstance

* more files update

* nits

* more nits

* small nits

* check and format

* revert wrong changes

* actually use formatter instead of checker

* nits

* well docbuilder is overwriting this commit

* revert notebook changes

* try to nuke docbuilder

* style

* fix feature exrtaction test

* remve `indent-width = 4`

* fixup

* more nits

* update the ruff version that we use

* style

* nuke docbuilder styling

* leve the print for detected changes

* nits

* Remove file I/O

Co-authored-by: charliermarsh
 <charlie.r.marsh@gmail.com>

* style

* nits

* revert notebook changes

* Add # fmt skip when possible

* Add # fmt skip when possible

* Fix

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* NIts

* more fixes

* fix tapas

* Another way to skip

* Recommended way

* Fix two more fiels

* Remove asynch
Remove asynch

---------

Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>
This commit is contained in:
Arthur
2023-11-16 17:43:19 +01:00
committed by GitHub
parent acb5b4aff5
commit 651408a077
480 changed files with 867 additions and 1059 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/models/llama/test_tokenization_llama.py
View File

@@ -282,9 +282,7 @@ class LlamaTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
@slow
def test_tokenizer_integration(self):
# fmt: off
expected_encoding = {'input_ids': [[1, 4103, 689, 414, 313, 24784, 368, 2998, 408, 282, 3637, 25350, 29899, 9067, 414, 322, 282, 3637, 25350, 29899, 1457, 3018, 1312, 29899, 2151, 29897, 8128, 2498, 29899, 15503, 4220, 6956, 1973, 313, 13635, 29911, 29892, 402, 7982, 29899, 29906, 29892, 1528, 13635, 29911, 29874, 29892, 1060, 26369, 29892, 6652, 309, 29933, 814, 29892, 1060, 29931, 6779, 11410, 363, 18385, 17088, 7634, 11235, 313, 25103, 29965, 29897, 322, 18385, 17088, 28203, 313, 25103, 29954, 29897, 411, 975, 29871, 29941, 29906, 29974, 758, 3018, 1312, 4733, 297, 29871, 29896, 29900, 29900, 29974, 10276, 322, 6483, 1006, 3372, 3097, 1546, 435, 1165, 29892, 10772, 29911, 25350, 322, 323, 6073, 17907, 29889], [1, 350, 20161, 338, 8688, 304, 758, 29899, 14968, 6483, 21000, 8684, 284, 22540, 515, 443, 29880, 24025, 1426, 491, 14002, 368, 4195, 292, 373, 1716, 2175, 322, 1492, 3030, 297, 599, 15359, 29889], [1, 450, 4996, 17354, 1701, 29916, 432, 17204, 975, 278, 17366, 11203, 29889]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}
# fmt: on
expected_encoding = {'input_ids': [[1, 4103, 689, 414, 313, 24784, 368, 2998, 408, 282, 3637, 25350, 29899, 9067, 414, 322, 282, 3637, 25350, 29899, 1457, 3018, 1312, 29899, 2151, 29897, 8128, 2498, 29899, 15503, 4220, 6956, 1973, 313, 13635, 29911, 29892, 402, 7982, 29899, 29906, 29892, 1528, 13635, 29911, 29874, 29892, 1060, 26369, 29892, 6652, 309, 29933, 814, 29892, 1060, 29931, 6779, 11410, 363, 18385, 17088, 7634, 11235, 313, 25103, 29965, 29897, 322, 18385, 17088, 28203, 313, 25103, 29954, 29897, 411, 975, 29871, 29941, 29906, 29974, 758, 3018, 1312, 4733, 297, 29871, 29896, 29900, 29900, 29974, 10276, 322, 6483, 1006, 3372, 3097, 1546, 435, 1165, 29892, 10772, 29911, 25350, 322, 323, 6073, 17907, 29889], [1, 350, 20161, 338, 8688, 304, 758, 29899, 14968, 6483, 21000, 8684, 284, 22540, 515, 443, 29880, 24025, 1426, 491, 14002, 368, 4195, 292, 373, 1716, 2175, 322, 1492, 3030, 297, 599, 15359, 29889], [1, 450, 4996, 17354, 1701, 29916, 432, 17204, 975, 278, 17366, 11203, 29889]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]} # fmt: skip
self.tokenizer_integration_test_util(
expected_encoding=expected_encoding,
@@ -402,8 +400,8 @@ class LlamaIntegrationTest(unittest.TestCase):
self.assertEqual(rust_tokenizer.decode([1, 910, 338, 263, 1243], skip_special_tokens=True), "This is a test")
# bytefallback showcase
self.assertEqual(pyth_tokenizer.encode("生活的真谛是"), [1, 29871, 30486, 31704, 30210, 30848, 235, 179, 158, 30392])
self.assertEqual(rust_tokenizer.encode("生活的真谛是"), [1, 29871, 30486, 31704, 30210, 30848, 235, 179, 158, 30392])
self.assertEqual(pyth_tokenizer.encode("生活的真谛是"), [1, 29871, 30486, 31704, 30210, 30848, 235, 179, 158, 30392]) # fmt: skip
self.assertEqual(rust_tokenizer.encode("生活的真谛是"), [1, 29871, 30486, 31704, 30210, 30848, 235, 179, 158, 30392]) # fmt: skip
self.assertEqual(
pyth_tokenizer.decode(
[1, 29871, 30486, 31704, 30210, 30848, 235, 179, 158, 30392], skip_special_tokens=True