add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "model_max_length": 128, "tokenizer_file": null, "name_or_path": "data/drug/molecule_tokenizer", "tokenizer_class": "BertTokenizer"}

vocab.txt

@@ -0,0 +1,69 @@
+[PAD]
+[UNK]
+[CLS]
+[SEP]
+[MASK]
+(
+)
+[
+]
++
+-
+/
+\
+%
+=
+.
+#
+@
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
+A
+B
+C
+D
+E
+F
+G
+H
+I
+K
+L
+M
+N
+O
+P
+R
+S
+T
+U
+V
+W
+Y
+Z
+a
+b
+c
+d
+e
+f
+g
+h
+i
+l
+m
+o
+n
+r
+s
+t
+u
+y