From 3815cb3bb4695e83094534d3412514007b1156af Mon Sep 17 00:00:00 2001 From: Allen Goodman Date: Fri, 19 Jul 2024 15:45:55 -0400 Subject: [PATCH] tokenizers --- .../beignet/tokenizers/test__protein_tokenizer.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/tests/beignet/tokenizers/test__protein_tokenizer.py b/tests/beignet/tokenizers/test__protein_tokenizer.py index 5f66411547..45088ecd3d 100644 --- a/tests/beignet/tokenizers/test__protein_tokenizer.py +++ b/tests/beignet/tokenizers/test__protein_tokenizer.py @@ -8,7 +8,12 @@ class TestProteinmMLMTokenizer: def test_3Di_tokenizer(self): inputs = ["GdPfQaPfIlSvRvLvEcQvClGpId"] - path = importlib.resources.files("lobster") / "assets" / "3di_tokenizer" + path = ( + importlib.resources.files("beignet") + / "data" + / "tokenizers" + / "3di_tokenizer" + ) tokenizer = ProteinTokenizerTransform.from_pretrained(path) tokenized_inputs = tokenizer(inputs) @@ -21,7 +26,12 @@ def test_3Di_tokenizer(self): def test_cdna_tokenizer(self): inputs = 4 * ["ATCGTACGATCGTACGATCGUN"] - path = importlib.resources.files("lobster") / "assets" / "cdna_tokenizer" + path = ( + importlib.resources.files("beignet") + / "data" + / "tokenizers" + / "cdna_tokenizer" + ) tokenizer = ProteinTokenizerTransform.from_pretrained(path) tokenized_inputs = tokenizer(inputs)