Faster pegasus tokenization test with reduced data size (#7762)
This commit is contained in:
@@ -57,7 +57,7 @@ class PegasusTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
||||
|
||||
@require_torch
|
||||
def test_pegasus_large_seq2seq_truncation(self):
|
||||
src_texts = ["This is going to be way too long" * 10000, "short example"]
|
||||
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.pegasus_large_tokenizer.prepare_seq2seq_batch(src_texts, tgt_texts=tgt_texts, max_target_length=5)
|
||||
assert batch.input_ids.shape == (2, 1024)
|
||||
|
||||
Reference in New Issue
Block a user