add tokenizer

config.json

@@ -1,7 +1,6 @@
 {
-  "_name_or_path": "data/saved_models/our_90epochs_saved_model",
   "architectures": [
-    "RobertaForSelfiesClassification"
+    "RobertaForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -10,19 +9,13 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 8,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

merges.txt

@@ -0,0 +1,162 @@
+#version: 0.2 - Trained by `huggingface/tokenizers`
+B r
+a n
+c h
+Br an
+Bran ch
+Branch 1
+= C
+R i
+n g
+Ri ng
+Ring 1
+= Branch1
+Branch 2
+= O
+Ring 2
+H 1
+C @
+= N
+# Branch1
+C@ @
+= Branch2
+C@ H1
+C@@ H1
+# Branch2
+C l
+# C
+/ C
+N H1
++ 1
+- 1
+= Ring1
+O -1
+N +1
+\ C
+/ N
+# N
+= Ring2
+= S
+=N +1
+N a
+Na +1
+\ N
+S +1
+/ O
+\ S
+\ O
+Br -1
+I -1
+Cl -1
+/ C@H1
+Branch 3
+/ C@@H1
+= P
+/ S
+=N -1
+S i
+K +1
+N -1
+S e
+L i
+Li +1
++ 3
+Cl +3
+\ C@H1
+Ring 3
+\ C@@H1
+/ N+1
+/ P
+\ F
+P @
+2 H
+P H1
+/ Br
+N @
+P +1
+/ Cl
+\ NH1
+\ Br
+@ +1
+/ I
+/ C@
+T e
+\ N+1
+P@ @
+1 2
+5 I
+\ O-1
+12 5I
+/ F
+# N+1
+\ Cl
+N@ +1
+\ I
+- /
+/ C@@
+N@ @
+N@ @+1
+-/ Ring2
+- \
+1 4
+B -1
+C -1
+S @+1
+14 C
+H 2
+H 4
+I +1
+S -1
+\ P
+=S +1
+=P @
+Si H4
++ 2
+3 H
+@ @+1
+A g
+C +1
+S @@+1
+Cl +1
+=S e
+-\ Ring1
+H 0
+O H0
+1 1
+= Branch3
+= Te
+M g
+O +1
+Z n
+\ C@
+\ S+1
+H1 -1
+Se H1
+P@ +1
+-\ Ring2
+11 C
+=Te +1
+Zn +2
+/ NH1
+1 8
+A s
+B H2
+B H1-1
+C a
+H 3
+O H1-1
+S H2
+=O +1
+Se +1
+Te H2
+125I H1
+-/ Ring1
+14C H2
+Ag +1
+=Se +1
+Mg H2
+Mg +2
+11C H3
+18 F
+BH2 -1
+Ca +2

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer.json

@@ -0,0 +1 @@
+{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":0,"special":true,"content":"<unk>","single_word":false,"lstrip":false,"rstrip":false,"normalized":true},{"id":1,"special":true,"content":"<s>","single_word":false,"lstrip":false,"rstrip":false,"normalized":true},{"id":2,"special":true,"content":"</s>","single_word":false,"lstrip":false,"rstrip":false,"normalized":true},{"id":3,"special":true,"content":"<pad>","single_word":false,"lstrip":false,"rstrip":false,"normalized":true},{"id":4,"special":true,"content":"<mask>","single_word":false,"lstrip":true,"rstrip":false,"normalized":true}],"normalizer":null,"pre_tokenizer":{"type":"ByteLevel","add_prefix_space":false,"trim_offsets":true},"post_processor":{"type":"RobertaProcessing","sep":["</s>",2],"cls":["<s>",1],"trim_offsets":true,"add_prefix_space":false},"decoder":{"type":"ByteLevel","add_prefix_space":true,"trim_offsets":true},"model":{"type":"BPE","dropout":null,"unk_token":null,"continuing_subword_prefix":"","end_of_word_suffix":"","fuse_unk":false,"vocab":{"<unk>":0,"<s>":1,"</s>":2,"<pad>":3,"<mask>":4,"\n":5,"#":6,"+":7,"-":8,".":9,"/":10,"0":11,"1":12,"2":13,"3":14,"4":15,"5":16,"8":17,"=":18,"@":19,"A":20,"B":21,"C":22,"F":23,"H":24,"I":25,"K":26,"L":27,"M":28,"N":29,"O":30,"P":31,"R":32,"S":33,"T":34,"Z":35,"\\":36,"a":37,"c":38,"e":39,"g":40,"h":41,"i":42,"l":43,"n":44,"r":45,"s":46,"Br":47,"an":48,"ch":49,"Bran":50,"Branch":51,"Branch1":52,"=C":53,"Ri":54,"ng":55,"Ring":56,"Ring1":57,"=Branch1":58,"Branch2":59,"=O":60,"Ring2":61,"H1":62,"C@":63,"=N":64,"#Branch1":65,"C@@":66,"=Branch2":67,"C@H1":68,"C@@H1":69,"#Branch2":70,"Cl":71,"#C":72,"/C":73,"NH1":74,"+1":75,"-1":76,"=Ring1":77,"O-1":78,"N+1":79,"\\C":80,"/N":81,"#N":82,"=Ring2":83,"=S":84,"=N+1":85,"Na":86,"Na+1":87,"\\N":88,"S+1":89,"/O":90,"\\S":91,"\\O":92,"Br-1":93,"I-1":94,"Cl-1":95,"/C@H1":96,"Branch3":97,"/C@@H1":98,"=P":99,"/S":100,"=N-1":101,"Si":102,"K+1":103,"N-1":104,"Se":105,"Li":106,"Li+1":107,"+3":108,"Cl+3":109,"\\C@H1":110,"Ring3":111,"\\C@@H1":112,"/N+1":113,"/P":114,"\\F":115,"P@":116,"2H":117,"PH1":118,"/Br":119,"N@":120,"P+1":121,"/Cl":122,"\\NH1":123,"\\Br":124,"@+1":125,"/I":126,"/C@":127,"Te":128,"\\N+1":129,"P@@":130,"12":131,"5I":132,"\\O-1":133,"125I":134,"/F":135,"#N+1":136,"\\Cl":137,"N@+1":138,"\\I":139,"-/":140,"/C@@":141,"N@@":142,"N@@+1":143,"-/Ring2":144,"-\\":145,"14":146,"B-1":147,"C-1":148,"S@+1":149,"14C":150,"H2":151,"H4":152,"I+1":153,"S-1":154,"\\P":155,"=S+1":156,"=P@":157,"SiH4":158,"+2":159,"3H":160,"@@+1":161,"Ag":162,"C+1":163,"S@@+1":164,"Cl+1":165,"=Se":166,"-\\Ring1":167,"H0":168,"OH0":169,"11":170,"=Branch3":171,"=Te":172,"Mg":173,"O+1":174,"Zn":175,"\\C@":176,"\\S+1":177,"H1-1":178,"SeH1":179,"P@+1":180,"-\\Ring2":181,"11C":182,"=Te+1":183,"Zn+2":184,"/NH1":185,"18":186,"As":187,"BH2":188,"BH1-1":189,"Ca":190,"H3":191,"OH1-1":192,"SH2":193,"=O+1":194,"Se+1":195,"TeH2":196,"125IH1":197,"-/Ring1":198,"14CH2":199,"Ag+1":200,"=Se+1":201,"MgH2":202,"Mg+2":203,"11CH3":204,"18F":205,"BH2-1":206,"Ca+2":207},"merges":["B r","a n","c h","Br an","Bran ch","Branch 1","= C","R i","n g","Ri ng","Ring 1","= Branch1","Branch 2","= O","Ring 2","H 1","C @","= N","# Branch1","C@ @","= Branch2","C@ H1","C@@ H1","# Branch2","C l","# C","/ C","N H1","+ 1","- 1","= Ring1","O -1","N +1","\\ C","/ N","# N","= Ring2","= S","=N +1","N a","Na +1","\\ N","S +1","/ O","\\ S","\\ O","Br -1","I -1","Cl -1","/ C@H1","Branch 3","/ C@@H1","= P","/ S","=N -1","S i","K +1","N -1","S e","L i","Li +1","+ 3","Cl +3","\\ C@H1","Ring 3","\\ C@@H1","/ N+1","/ P","\\ F","P @","2 H","P H1","/ Br","N @","P +1","/ Cl","\\ NH1","\\ Br","@ +1","/ I","/ C@","T e","\\ N+1","P@ @","1 2","5 I","\\ O-1","12 5I","/ F","# N+1","\\ Cl","N@ +1","\\ I","- /","/ C@@","N@ @","N@ @+1","-/ Ring2","- \\","1 4","B -1","C -1","S @+1","14 C","H 2","H 4","I +1","S -1","\\ P","=S +1","=P @","Si H4","+ 2","3 H","@ @+1","A g","C +1","S @@+1","Cl +1","=S e","-\\ Ring1","H 0","O H0","1 1","= Branch3","= Te","M g","O +1","Z n","\\ C@","\\ S+1","H1 -1","Se H1","P@ +1","-\\ Ring2","11 C","=Te +1","Zn +2","/ NH1","1 8","A s","B H2","B H1-1","C a","H 3","O H1-1","S H2","=O +1","Se +1","Te H2","125I H1","-/ Ring1","14C H2","Ag +1","=Se +1","Mg H2","Mg +2","11C H3","18 F","BH2 -1","Ca +2"]}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "./data/bpe/", "tokenizer_class": "RobertaTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<unk>":0,"<s>":1,"</s>":2,"<pad>":3,"<mask>":4,"\n":5,"#":6,"+":7,"-":8,".":9,"/":10,"0":11,"1":12,"2":13,"3":14,"4":15,"5":16,"8":17,"=":18,"@":19,"A":20,"B":21,"C":22,"F":23,"H":24,"I":25,"K":26,"L":27,"M":28,"N":29,"O":30,"P":31,"R":32,"S":33,"T":34,"Z":35,"\\":36,"a":37,"c":38,"e":39,"g":40,"h":41,"i":42,"l":43,"n":44,"r":45,"s":46,"Br":47,"an":48,"ch":49,"Bran":50,"Branch":51,"Branch1":52,"=C":53,"Ri":54,"ng":55,"Ring":56,"Ring1":57,"=Branch1":58,"Branch2":59,"=O":60,"Ring2":61,"H1":62,"C@":63,"=N":64,"#Branch1":65,"C@@":66,"=Branch2":67,"C@H1":68,"C@@H1":69,"#Branch2":70,"Cl":71,"#C":72,"/C":73,"NH1":74,"+1":75,"-1":76,"=Ring1":77,"O-1":78,"N+1":79,"\\C":80,"/N":81,"#N":82,"=Ring2":83,"=S":84,"=N+1":85,"Na":86,"Na+1":87,"\\N":88,"S+1":89,"/O":90,"\\S":91,"\\O":92,"Br-1":93,"I-1":94,"Cl-1":95,"/C@H1":96,"Branch3":97,"/C@@H1":98,"=P":99,"/S":100,"=N-1":101,"Si":102,"K+1":103,"N-1":104,"Se":105,"Li":106,"Li+1":107,"+3":108,"Cl+3":109,"\\C@H1":110,"Ring3":111,"\\C@@H1":112,"/N+1":113,"/P":114,"\\F":115,"P@":116,"2H":117,"PH1":118,"/Br":119,"N@":120,"P+1":121,"/Cl":122,"\\NH1":123,"\\Br":124,"@+1":125,"/I":126,"/C@":127,"Te":128,"\\N+1":129,"P@@":130,"12":131,"5I":132,"\\O-1":133,"125I":134,"/F":135,"#N+1":136,"\\Cl":137,"N@+1":138,"\\I":139,"-/":140,"/C@@":141,"N@@":142,"N@@+1":143,"-/Ring2":144,"-\\":145,"14":146,"B-1":147,"C-1":148,"S@+1":149,"14C":150,"H2":151,"H4":152,"I+1":153,"S-1":154,"\\P":155,"=S+1":156,"=P@":157,"SiH4":158,"+2":159,"3H":160,"@@+1":161,"Ag":162,"C+1":163,"S@@+1":164,"Cl+1":165,"=Se":166,"-\\Ring1":167,"H0":168,"OH0":169,"11":170,"=Branch3":171,"=Te":172,"Mg":173,"O+1":174,"Zn":175,"\\C@":176,"\\S+1":177,"H1-1":178,"SeH1":179,"P@+1":180,"-\\Ring2":181,"11C":182,"=Te+1":183,"Zn+2":184,"/NH1":185,"18":186,"As":187,"BH2":188,"BH1-1":189,"Ca":190,"H3":191,"OH1-1":192,"SH2":193,"=O+1":194,"Se+1":195,"TeH2":196,"125IH1":197,"-/Ring1":198,"14CH2":199,"Ag+1":200,"=Se+1":201,"MgH2":202,"Mg+2":203,"11CH3":204,"18F":205,"BH2-1":206,"Ca+2":207}