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

Replace as_target context managers by direct calls (#18325)

Browse Source 
* Preliminary work on tokenizers

* Quality + fix tests

* Treat processors

* Fix pad

* Remove all uses of  in tests, docs and examples

* Replace all as_target_tokenizer

* Fix tests

* Fix quality

* Update examples/flax/image-captioning/run_image_captioning_flax.py

Co-authored-by: amyeroberts <amy@huggingface.co>

* Style

Co-authored-by: amyeroberts <amy@huggingface.co>
This commit is contained in:
Sylvain Gugger
2022-07-29 08:09:09 -04:00
committed by GitHub
parent a64bcb564d
commit 986526a0e4
80 changed files with 725 additions and 550 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
tests/models/pegasus/test_tokenization_pegasus.py
View File

@@ -109,10 +109,9 @@ class PegasusTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
src_texts = ["This is going to be way too long." * 150, "short example"]
tgt_texts = ["not super long but more than 5 tokens", "tiny"]
batch = self._large_tokenizer(src_texts, padding=True, truncation=True, return_tensors="pt")
with self._large_tokenizer.as_target_tokenizer():
targets = self._large_tokenizer(
tgt_texts, max_length=5, padding=True, truncation=True, return_tensors="pt"
)
targets = self._large_tokenizer(
text_target=tgt_texts, max_length=5, padding=True, truncation=True, return_tensors="pt"
)
assert batch.input_ids.shape == (2, 1024)
assert batch.attention_mask.shape == (2, 1024)
@@ -174,10 +173,9 @@ class BigBirdPegasusTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
src_texts = ["This is going to be way too long." * 1000, "short example"]
tgt_texts = ["not super long but more than 5 tokens", "tiny"]
batch = self._large_tokenizer(src_texts, padding=True, truncation=True, return_tensors="pt")
with self._large_tokenizer.as_target_tokenizer():
targets = self._large_tokenizer(
tgt_texts, max_length=5, padding=True, truncation=True, return_tensors="pt"
)
targets = self._large_tokenizer(
text_target=tgt_texts, max_length=5, padding=True, truncation=True, return_tensors="pt"
)
assert batch.input_ids.shape == (2, 4096)
assert batch.attention_mask.shape == (2, 4096)