Loading deepchem/feat/tests/test_smiles_tokenizer.py +1 −1 Original line number Diff line number Diff line Loading @@ -13,6 +13,6 @@ class TestSmilesTokenizer(TestCase): model = RobertaForMaskedLM.from_pretrained('seyonec/SMILES_tokenized_PubChem_shard00_50k') model.num_parameters() tokenizer = SmilesTokenizer('tokenizers/vocab.txt', max_len=model.config.max_position_embeddings) tokenizer = SmilesTokenizer('deepchem/feat/tests/data/vocab.txt', max_len=model.config.max_position_embeddings) print(tokenizer.encode("CCC(CC)COC(=O)[C@H](C)N[P@](=O)(OC[C@H]1O[C@](C#N)([C@H](O)[C@@H]1O)C1=CC=C2N1N=CN=C2N)OC1=CC=CC=C1")) Loading
deepchem/feat/tests/test_smiles_tokenizer.py +1 −1 Original line number Diff line number Diff line Loading @@ -13,6 +13,6 @@ class TestSmilesTokenizer(TestCase): model = RobertaForMaskedLM.from_pretrained('seyonec/SMILES_tokenized_PubChem_shard00_50k') model.num_parameters() tokenizer = SmilesTokenizer('tokenizers/vocab.txt', max_len=model.config.max_position_embeddings) tokenizer = SmilesTokenizer('deepchem/feat/tests/data/vocab.txt', max_len=model.config.max_position_embeddings) print(tokenizer.encode("CCC(CC)COC(=O)[C@H](C)N[P@](=O)(OC[C@H]1O[C@](C#N)([C@H](O)[C@@H]1O)C1=CC=C2N1N=CN=C2N)OC1=CC=CC=C1"))
