Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<bos>",
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "added_tokens_decoder": {},
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "cls_df": "<cls_sf>",
+  "cls_dna": "<cls_dna>",
+  "cls_prot": "<cls_prot>",
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "MgmTokenizer",
+  "unk_token": "<unk>"
+}

vocab.txt

@@ -0,0 +1,68 @@
+<bos>
+<cls>
+<cls_aa>
+<cls_nt>
+<cls_sf>
+<cls_struct>
+<eos>
+<mask>
+<null_1>
+<pad>
+<reserved>
+<sep>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+a
+c
+g
+t
+n
+u
+[Branch3]
+[C@@H1]
+[P]
+[#Branch1]
+[C]
+[Branch2]
+[O]
+[S]
+[Branch1]
+[=O]
+[#C]
+[C@H1]
+[=Branch1]
+[=N]
+[#Branch2]
+[N]
+[=C]
+[Ring1]
+[NH1]
+[Branch4]
+[Ring2]
+[=Branch2]