tlhoang commited on
Commit
00a075b
·
0 Parent(s):

Clean history

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
Examples.ipynb ADDED
@@ -0,0 +1,366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 2,
6
+ "id": "a1af2321-8860-4a3e-8406-a9ae587b97bf",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
11
+ "import selfies as sf\n",
12
+ "from rdkit import Chem\n",
13
+ "from typing import Optional\n",
14
+ "import numpy as np\n",
15
+ "import py3Dmol\n",
16
+ "from rdkit import Chem, DataStructs\n",
17
+ "from rdkit.Chem import AllChem\n",
18
+ "import torch\n",
19
+ "\n",
20
+ "def smiles_to_3d(smiles_list, width=400, height=300):\n",
21
+ " # Visualize the 3D structure using py3Dmol\n",
22
+ " view = py3Dmol.view(width=width, height=height)\n",
23
+ " for smiles in smiles_list:\n",
24
+ " # Generate the RDKit molecule object\n",
25
+ " mol = Chem.MolFromSmiles(smiles)\n",
26
+ " if mol is None:\n",
27
+ " raise ValueError(\"Invalid SMILES string\")\n",
28
+ "\n",
29
+ " # Add hydrogens to the molecule\n",
30
+ " mol = Chem.AddHs(mol)\n",
31
+ "\n",
32
+ " # Generate 3D coordinates\n",
33
+ " AllChem.EmbedMolecule(mol, randomSeed=42)\n",
34
+ " AllChem.UFFOptimizeMolecule(mol)\n",
35
+ "\n",
36
+ " # Generate the 3D structure in the form of a pdb string\n",
37
+ " pdb = Chem.MolToPDBBlock(mol)\n",
38
+ " view.addModel(pdb, 'pdb')\n",
39
+ " view.setStyle({'stick': {}})\n",
40
+ " view.zoomTo()\n",
41
+ " return view\n",
42
+ "\n",
43
+ " \n",
44
+ "# Load the checkpoint and the tokenizer\n",
45
+ "checkpoint_path = \"lamthuy/SelfiesGen\"\n",
46
+ "model = AutoModelForCausalLM.from_pretrained(checkpoint_path)\n",
47
+ "tokenizer = AutoTokenizer.from_pretrained(checkpoint_path)"
48
+ ]
49
+ },
50
+ {
51
+ "cell_type": "code",
52
+ "execution_count": 9,
53
+ "id": "9b7066a4-6637-4d45-a0d9-3cc5e2ca0409",
54
+ "metadata": {},
55
+ "outputs": [
56
+ {
57
+ "data": {
58
+ "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_1753263966683991\" style=\"position: relative; width: 400px; height: 300px;\">\n <p id=\"3dmolwarning_1753263966683991\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason. Please check your browser console for error messages.<br></p>\n </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n return new Promise((resolve, reject) => {\n //this is to ignore the existence of requirejs amd\n var savedexports, savedmodule;\n if (typeof exports !== 'undefined') savedexports = exports;\n else exports = {}\n if (typeof module !== 'undefined') savedmodule = module;\n else module = {}\n\n var tag = document.createElement('script');\n tag.src = uri;\n tag.async = true;\n tag.onload = () => {\n exports = savedexports;\n module = savedmodule;\n resolve();\n };\n var firstScriptTag = document.getElementsByTagName('script')[0];\n firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n}\n\nvar viewer_1753263966683991 = null;\nvar warn = document.getElementById(\"3dmolwarning_1753263966683991\");\nif(warn) {\n warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_1753263966683991 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1753263966683991\"),{backgroundColor:\"white\"});\nviewer_1753263966683991.zoomTo();\n\tviewer_1753263966683991.addModel(\"HETATM 1 C1 UNL 1 -2.975 -2.217 0.190 1.00 0.00 C \\nHETATM 2 C2 UNL 1 -2.096 -1.150 -0.368 1.00 0.00 C \\nHETATM 3 O1 UNL 1 -2.392 -0.615 -1.471 1.00 0.00 O \\nHETATM 4 O2 UNL 1 -0.898 -0.839 0.288 1.00 0.00 O \\nHETATM 5 C3 UNL 1 -0.095 0.284 0.025 1.00 0.00 C \\nHETATM 6 C4 UNL 1 -0.671 1.501 -0.391 1.00 0.00 C \\nHETATM 7 C5 UNL 1 0.129 2.617 -0.638 1.00 0.00 C \\nHETATM 8 C6 UNL 1 1.509 2.540 -0.463 1.00 0.00 C \\nHETATM 9 C7 UNL 1 2.094 1.348 -0.032 1.00 0.00 C \\nHETATM 10 C8 UNL 1 1.307 0.209 0.223 1.00 0.00 C \\nHETATM 11 C9 UNL 1 1.972 -1.038 0.682 1.00 0.00 C \\nHETATM 12 O3 UNL 1 1.307 -2.087 0.898 1.00 0.00 O \\nHETATM 13 O4 UNL 1 3.351 -1.062 0.878 1.00 0.00 O \\nHETATM 14 H1 UNL 1 -4.038 -1.995 -0.040 1.00 0.00 H \\nHETATM 15 H2 UNL 1 -2.850 -2.271 1.291 1.00 0.00 H \\nHETATM 16 H3 UNL 1 -2.699 -3.195 -0.257 1.00 0.00 H \\nHETATM 17 H4 UNL 1 -1.742 1.599 -0.498 1.00 0.00 H \\nHETATM 18 H5 UNL 1 -0.324 3.547 -0.957 1.00 0.00 H \\nHETATM 19 H6 UNL 1 2.126 3.408 -0.653 1.00 0.00 H \\nHETATM 20 H7 UNL 1 3.168 1.322 0.102 1.00 0.00 H \\nHETATM 21 H8 UNL 1 3.818 -1.905 1.190 1.00 0.00 H \\nCONECT 1 2 14 15 16\\nCONECT 2 3 3 4\\nCONECT 4 5\\nCONECT 5 6 6 10\\nCONECT 6 7 17\\nCONECT 7 8 8 18\\nCONECT 8 9 19\\nCONECT 9 10 10 20\\nCONECT 10 11\\nCONECT 11 12 12 13\\nCONECT 13 21\\nEND\\n\",\"pdb\");\n\tviewer_1753263966683991.setStyle({\"stick\": {}});\n\tviewer_1753263966683991.zoomTo();\nviewer_1753263966683991.render();\n});\n</script>",
59
+ "text/html": [
60
+ "<div id=\"3dmolviewer_1753263966683991\" style=\"position: relative; width: 400px; height: 300px;\">\n",
61
+ " <p id=\"3dmolwarning_1753263966683991\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason. Please check your browser console for error messages.<br></p>\n",
62
+ " </div>\n",
63
+ "<script>\n",
64
+ "\n",
65
+ "var loadScriptAsync = function(uri){\n",
66
+ " return new Promise((resolve, reject) => {\n",
67
+ " //this is to ignore the existence of requirejs amd\n",
68
+ " var savedexports, savedmodule;\n",
69
+ " if (typeof exports !== 'undefined') savedexports = exports;\n",
70
+ " else exports = {}\n",
71
+ " if (typeof module !== 'undefined') savedmodule = module;\n",
72
+ " else module = {}\n",
73
+ "\n",
74
+ " var tag = document.createElement('script');\n",
75
+ " tag.src = uri;\n",
76
+ " tag.async = true;\n",
77
+ " tag.onload = () => {\n",
78
+ " exports = savedexports;\n",
79
+ " module = savedmodule;\n",
80
+ " resolve();\n",
81
+ " };\n",
82
+ " var firstScriptTag = document.getElementsByTagName('script')[0];\n",
83
+ " firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n",
84
+ "});\n",
85
+ "};\n",
86
+ "\n",
87
+ "if(typeof $3Dmolpromise === 'undefined') {\n",
88
+ "$3Dmolpromise = null;\n",
89
+ " $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n",
90
+ "}\n",
91
+ "\n",
92
+ "var viewer_1753263966683991 = null;\n",
93
+ "var warn = document.getElementById(\"3dmolwarning_1753263966683991\");\n",
94
+ "if(warn) {\n",
95
+ " warn.parentNode.removeChild(warn);\n",
96
+ "}\n",
97
+ "$3Dmolpromise.then(function() {\n",
98
+ "viewer_1753263966683991 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1753263966683991\"),{backgroundColor:\"white\"});\n",
99
+ "viewer_1753263966683991.zoomTo();\n",
100
+ "\tviewer_1753263966683991.addModel(\"HETATM 1 C1 UNL 1 -2.975 -2.217 0.190 1.00 0.00 C \\nHETATM 2 C2 UNL 1 -2.096 -1.150 -0.368 1.00 0.00 C \\nHETATM 3 O1 UNL 1 -2.392 -0.615 -1.471 1.00 0.00 O \\nHETATM 4 O2 UNL 1 -0.898 -0.839 0.288 1.00 0.00 O \\nHETATM 5 C3 UNL 1 -0.095 0.284 0.025 1.00 0.00 C \\nHETATM 6 C4 UNL 1 -0.671 1.501 -0.391 1.00 0.00 C \\nHETATM 7 C5 UNL 1 0.129 2.617 -0.638 1.00 0.00 C \\nHETATM 8 C6 UNL 1 1.509 2.540 -0.463 1.00 0.00 C \\nHETATM 9 C7 UNL 1 2.094 1.348 -0.032 1.00 0.00 C \\nHETATM 10 C8 UNL 1 1.307 0.209 0.223 1.00 0.00 C \\nHETATM 11 C9 UNL 1 1.972 -1.038 0.682 1.00 0.00 C \\nHETATM 12 O3 UNL 1 1.307 -2.087 0.898 1.00 0.00 O \\nHETATM 13 O4 UNL 1 3.351 -1.062 0.878 1.00 0.00 O \\nHETATM 14 H1 UNL 1 -4.038 -1.995 -0.040 1.00 0.00 H \\nHETATM 15 H2 UNL 1 -2.850 -2.271 1.291 1.00 0.00 H \\nHETATM 16 H3 UNL 1 -2.699 -3.195 -0.257 1.00 0.00 H \\nHETATM 17 H4 UNL 1 -1.742 1.599 -0.498 1.00 0.00 H \\nHETATM 18 H5 UNL 1 -0.324 3.547 -0.957 1.00 0.00 H \\nHETATM 19 H6 UNL 1 2.126 3.408 -0.653 1.00 0.00 H \\nHETATM 20 H7 UNL 1 3.168 1.322 0.102 1.00 0.00 H \\nHETATM 21 H8 UNL 1 3.818 -1.905 1.190 1.00 0.00 H \\nCONECT 1 2 14 15 16\\nCONECT 2 3 3 4\\nCONECT 4 5\\nCONECT 5 6 6 10\\nCONECT 6 7 17\\nCONECT 7 8 8 18\\nCONECT 8 9 19\\nCONECT 9 10 10 20\\nCONECT 10 11\\nCONECT 11 12 12 13\\nCONECT 13 21\\nEND\\n\",\"pdb\");\n",
101
+ "\tviewer_1753263966683991.setStyle({\"stick\": {}});\n",
102
+ "\tviewer_1753263966683991.zoomTo();\n",
103
+ "viewer_1753263966683991.render();\n",
104
+ "});\n",
105
+ "</script>"
106
+ ]
107
+ },
108
+ "metadata": {},
109
+ "output_type": "display_data"
110
+ },
111
+ {
112
+ "data": {
113
+ "text/plain": [
114
+ "<py3Dmol.view at 0x2afd09c40>"
115
+ ]
116
+ },
117
+ "execution_count": 9,
118
+ "metadata": {},
119
+ "output_type": "execute_result"
120
+ }
121
+ ],
122
+ "source": [
123
+ "# Given a SMILES, get its fingerpint\n",
124
+ "smiles = \"CC(=O)OC1=CC=CC=C1C(=O)O\"\n",
125
+ "smiles_to_3d([smiles])"
126
+ ]
127
+ },
128
+ {
129
+ "cell_type": "code",
130
+ "execution_count": 12,
131
+ "id": "05f9bf21-c998-4d63-870e-c1033ff91b31",
132
+ "metadata": {},
133
+ "outputs": [
134
+ {
135
+ "name": "stderr",
136
+ "output_type": "stream",
137
+ "text": [
138
+ "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
139
+ "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
140
+ ]
141
+ },
142
+ {
143
+ "name": "stdout",
144
+ "output_type": "stream",
145
+ "text": [
146
+ "[C][C][=Branch1][C][=O][O][C][=C][C][=C][C][=C][Ring1][=Branch1][C][=Branch1][C][=S][O][SEP]\n",
147
+ "[C][C][=Branch1][C][=O][O][C][=C][C][=C][C][=C][Ring1][=Branch1][C][=Branch1][C][=NH2+1][O]\n",
148
+ "CC(=O)OC1=CC=CC=C1C(=[NH2+1])O\n"
149
+ ]
150
+ },
151
+ {
152
+ "data": {
153
+ "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_1753264053659028\" style=\"position: relative; width: 400px; height: 300px;\">\n <p id=\"3dmolwarning_1753264053659028\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason. Please check your browser console for error messages.<br></p>\n </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n return new Promise((resolve, reject) => {\n //this is to ignore the existence of requirejs amd\n var savedexports, savedmodule;\n if (typeof exports !== 'undefined') savedexports = exports;\n else exports = {}\n if (typeof module !== 'undefined') savedmodule = module;\n else module = {}\n\n var tag = document.createElement('script');\n tag.src = uri;\n tag.async = true;\n tag.onload = () => {\n exports = savedexports;\n module = savedmodule;\n resolve();\n };\n var firstScriptTag = document.getElementsByTagName('script')[0];\n firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n}\n\nvar viewer_1753264053659028 = null;\nvar warn = document.getElementById(\"3dmolwarning_1753264053659028\");\nif(warn) {\n warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_1753264053659028 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1753264053659028\"),{backgroundColor:\"white\"});\nviewer_1753264053659028.zoomTo();\n\tviewer_1753264053659028.addModel(\"HETATM 1 C1 UNL 1 2.411 -2.582 -1.327 1.00 0.00 C \\nHETATM 2 C2 UNL 1 1.777 -1.233 -1.311 1.00 0.00 C \\nHETATM 3 O1 UNL 1 1.971 -0.444 -2.275 1.00 0.00 O \\nHETATM 4 O2 UNL 1 0.887 -0.908 -0.278 1.00 0.00 O \\nHETATM 5 C3 UNL 1 0.406 0.380 0.005 1.00 0.00 C \\nHETATM 6 C4 UNL 1 1.187 1.525 -0.250 1.00 0.00 C \\nHETATM 7 C5 UNL 1 0.691 2.798 0.033 1.00 0.00 C \\nHETATM 8 C6 UNL 1 -0.580 2.947 0.586 1.00 0.00 C \\nHETATM 9 C7 UNL 1 -1.357 1.822 0.866 1.00 0.00 C \\nHETATM 10 C8 UNL 1 -0.876 0.529 0.582 1.00 0.00 C \\nHETATM 11 C9 UNL 1 -1.702 -0.662 0.905 1.00 0.00 C \\nHETATM 12 N1 UNL 1 -2.996 -0.640 0.776 1.00 0.00 N1+\\nHETATM 13 O3 UNL 1 -1.073 -1.826 1.349 1.00 0.00 O \\nHETATM 14 H1 UNL 1 1.780 -3.281 -1.914 1.00 0.00 H \\nHETATM 15 H2 UNL 1 2.512 -2.964 -0.290 1.00 0.00 H \\nHETATM 16 H3 UNL 1 3.421 -2.524 -1.787 1.00 0.00 H \\nHETATM 17 H4 UNL 1 2.190 1.435 -0.643 1.00 0.00 H \\nHETATM 18 H5 UNL 1 1.299 3.672 -0.166 1.00 0.00 H \\nHETATM 19 H6 UNL 1 -0.957 3.936 0.813 1.00 0.00 H \\nHETATM 20 H7 UNL 1 -2.325 1.965 1.329 1.00 0.00 H \\nHETATM 21 H8 UNL 1 -3.567 -1.482 1.010 1.00 0.00 H \\nHETATM 22 H9 UNL 1 -3.499 0.198 0.408 1.00 0.00 H \\nHETATM 23 H10 UNL 1 -1.599 -2.662 1.576 1.00 0.00 H \\nCONECT 1 2 14 15 16\\nCONECT 2 3 3 4\\nCONECT 4 5\\nCONECT 5 6 6 10\\nCONECT 6 7 17\\nCONECT 7 8 8 18\\nCONECT 8 9 19\\nCONECT 9 10 10 20\\nCONECT 10 11\\nCONECT 11 12 12 13\\nCONECT 12 21 22\\nCONECT 13 23\\nEND\\n\",\"pdb\");\n\tviewer_1753264053659028.setStyle({\"stick\": {}});\n\tviewer_1753264053659028.zoomTo();\nviewer_1753264053659028.render();\n});\n</script>",
154
+ "text/html": [
155
+ "<div id=\"3dmolviewer_1753264053659028\" style=\"position: relative; width: 400px; height: 300px;\">\n",
156
+ " <p id=\"3dmolwarning_1753264053659028\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason. Please check your browser console for error messages.<br></p>\n",
157
+ " </div>\n",
158
+ "<script>\n",
159
+ "\n",
160
+ "var loadScriptAsync = function(uri){\n",
161
+ " return new Promise((resolve, reject) => {\n",
162
+ " //this is to ignore the existence of requirejs amd\n",
163
+ " var savedexports, savedmodule;\n",
164
+ " if (typeof exports !== 'undefined') savedexports = exports;\n",
165
+ " else exports = {}\n",
166
+ " if (typeof module !== 'undefined') savedmodule = module;\n",
167
+ " else module = {}\n",
168
+ "\n",
169
+ " var tag = document.createElement('script');\n",
170
+ " tag.src = uri;\n",
171
+ " tag.async = true;\n",
172
+ " tag.onload = () => {\n",
173
+ " exports = savedexports;\n",
174
+ " module = savedmodule;\n",
175
+ " resolve();\n",
176
+ " };\n",
177
+ " var firstScriptTag = document.getElementsByTagName('script')[0];\n",
178
+ " firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n",
179
+ "});\n",
180
+ "};\n",
181
+ "\n",
182
+ "if(typeof $3Dmolpromise === 'undefined') {\n",
183
+ "$3Dmolpromise = null;\n",
184
+ " $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n",
185
+ "}\n",
186
+ "\n",
187
+ "var viewer_1753264053659028 = null;\n",
188
+ "var warn = document.getElementById(\"3dmolwarning_1753264053659028\");\n",
189
+ "if(warn) {\n",
190
+ " warn.parentNode.removeChild(warn);\n",
191
+ "}\n",
192
+ "$3Dmolpromise.then(function() {\n",
193
+ "viewer_1753264053659028 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1753264053659028\"),{backgroundColor:\"white\"});\n",
194
+ "viewer_1753264053659028.zoomTo();\n",
195
+ "\tviewer_1753264053659028.addModel(\"HETATM 1 C1 UNL 1 2.411 -2.582 -1.327 1.00 0.00 C \\nHETATM 2 C2 UNL 1 1.777 -1.233 -1.311 1.00 0.00 C \\nHETATM 3 O1 UNL 1 1.971 -0.444 -2.275 1.00 0.00 O \\nHETATM 4 O2 UNL 1 0.887 -0.908 -0.278 1.00 0.00 O \\nHETATM 5 C3 UNL 1 0.406 0.380 0.005 1.00 0.00 C \\nHETATM 6 C4 UNL 1 1.187 1.525 -0.250 1.00 0.00 C \\nHETATM 7 C5 UNL 1 0.691 2.798 0.033 1.00 0.00 C \\nHETATM 8 C6 UNL 1 -0.580 2.947 0.586 1.00 0.00 C \\nHETATM 9 C7 UNL 1 -1.357 1.822 0.866 1.00 0.00 C \\nHETATM 10 C8 UNL 1 -0.876 0.529 0.582 1.00 0.00 C \\nHETATM 11 C9 UNL 1 -1.702 -0.662 0.905 1.00 0.00 C \\nHETATM 12 N1 UNL 1 -2.996 -0.640 0.776 1.00 0.00 N1+\\nHETATM 13 O3 UNL 1 -1.073 -1.826 1.349 1.00 0.00 O \\nHETATM 14 H1 UNL 1 1.780 -3.281 -1.914 1.00 0.00 H \\nHETATM 15 H2 UNL 1 2.512 -2.964 -0.290 1.00 0.00 H \\nHETATM 16 H3 UNL 1 3.421 -2.524 -1.787 1.00 0.00 H \\nHETATM 17 H4 UNL 1 2.190 1.435 -0.643 1.00 0.00 H \\nHETATM 18 H5 UNL 1 1.299 3.672 -0.166 1.00 0.00 H \\nHETATM 19 H6 UNL 1 -0.957 3.936 0.813 1.00 0.00 H \\nHETATM 20 H7 UNL 1 -2.325 1.965 1.329 1.00 0.00 H \\nHETATM 21 H8 UNL 1 -3.567 -1.482 1.010 1.00 0.00 H \\nHETATM 22 H9 UNL 1 -3.499 0.198 0.408 1.00 0.00 H \\nHETATM 23 H10 UNL 1 -1.599 -2.662 1.576 1.00 0.00 H \\nCONECT 1 2 14 15 16\\nCONECT 2 3 3 4\\nCONECT 4 5\\nCONECT 5 6 6 10\\nCONECT 6 7 17\\nCONECT 7 8 8 18\\nCONECT 8 9 19\\nCONECT 9 10 10 20\\nCONECT 10 11\\nCONECT 11 12 12 13\\nCONECT 12 21 22\\nCONECT 13 23\\nEND\\n\",\"pdb\");\n",
196
+ "\tviewer_1753264053659028.setStyle({\"stick\": {}});\n",
197
+ "\tviewer_1753264053659028.zoomTo();\n",
198
+ "viewer_1753264053659028.render();\n",
199
+ "});\n",
200
+ "</script>"
201
+ ]
202
+ },
203
+ "metadata": {},
204
+ "output_type": "display_data"
205
+ },
206
+ {
207
+ "data": {
208
+ "text/plain": [
209
+ "<py3Dmol.view at 0x2afbaf020>"
210
+ ]
211
+ },
212
+ "execution_count": 12,
213
+ "metadata": {},
214
+ "output_type": "execute_result"
215
+ }
216
+ ],
217
+ "source": [
218
+ "s = sf.encoder(smiles)\n",
219
+ "s = s + \"[SEP]\"\n",
220
+ "print(s)\n",
221
+ "input_ids = tokenizer.encode(s, return_tensors=\"pt\")\n",
222
+ "n = input_ids.size(1)\n",
223
+ "# Generate output sequence\n",
224
+ "output_ids = model.generate(input_ids, max_length=128, num_beams=5, num_return_sequences=5,\n",
225
+ " early_stopping=True)\n",
226
+ "output = tokenizer.decode(output_ids[1][n:], skip_special_tokens=True)\n",
227
+ "print(output)\n",
228
+ "smiles = sf.decoder(output)\n",
229
+ "print(smiles)\n",
230
+ "smiles_to_3d([smiles])"
231
+ ]
232
+ },
233
+ {
234
+ "cell_type": "code",
235
+ "execution_count": 13,
236
+ "id": "dbe6cebd-c7d5-4da9-aac0-114f232cf147",
237
+ "metadata": {},
238
+ "outputs": [
239
+ {
240
+ "name": "stderr",
241
+ "output_type": "stream",
242
+ "text": [
243
+ "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
244
+ "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
245
+ ]
246
+ },
247
+ {
248
+ "name": "stdout",
249
+ "output_type": "stream",
250
+ "text": [
251
+ "[C][C][=Branch1][C][=O][N][C][=C][C][=N][C][=C][Ring1][=Branch1][C][=Branch1][C][=S][O-1]\n",
252
+ "CC(=O)NC1=CC=NC=C1C(=S)[O-1]\n"
253
+ ]
254
+ },
255
+ {
256
+ "data": {
257
+ "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_17532640697518232\" style=\"position: relative; width: 400px; height: 300px;\">\n <p id=\"3dmolwarning_17532640697518232\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason. Please check your browser console for error messages.<br></p>\n </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n return new Promise((resolve, reject) => {\n //this is to ignore the existence of requirejs amd\n var savedexports, savedmodule;\n if (typeof exports !== 'undefined') savedexports = exports;\n else exports = {}\n if (typeof module !== 'undefined') savedmodule = module;\n else module = {}\n\n var tag = document.createElement('script');\n tag.src = uri;\n tag.async = true;\n tag.onload = () => {\n exports = savedexports;\n module = savedmodule;\n resolve();\n };\n var firstScriptTag = document.getElementsByTagName('script')[0];\n firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n}\n\nvar viewer_17532640697518232 = null;\nvar warn = document.getElementById(\"3dmolwarning_17532640697518232\");\nif(warn) {\n warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_17532640697518232 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_17532640697518232\"),{backgroundColor:\"white\"});\nviewer_17532640697518232.zoomTo();\n\tviewer_17532640697518232.addModel(\"HETATM 1 C1 UNL 1 3.341 0.506 -0.349 1.00 0.00 C \\nHETATM 2 C2 UNL 1 1.994 -0.109 -0.554 1.00 0.00 C \\nHETATM 3 O1 UNL 1 1.839 -0.974 -1.458 1.00 0.00 O \\nHETATM 4 N1 UNL 1 0.876 0.346 0.221 1.00 0.00 N \\nHETATM 5 C3 UNL 1 -0.424 -0.266 0.167 1.00 0.00 C \\nHETATM 6 C4 UNL 1 -0.537 -1.665 0.219 1.00 0.00 C \\nHETATM 7 C5 UNL 1 -1.798 -2.258 0.278 1.00 0.00 C \\nHETATM 8 N2 UNL 1 -2.913 -1.485 0.302 1.00 0.00 N \\nHETATM 9 C6 UNL 1 -2.844 -0.130 0.260 1.00 0.00 C \\nHETATM 10 C7 UNL 1 -1.602 0.521 0.177 1.00 0.00 C \\nHETATM 11 C8 UNL 1 -1.585 1.998 0.085 1.00 0.00 C \\nHETATM 12 S1 UNL 1 -0.600 2.783 -0.963 1.00 0.00 S \\nHETATM 13 O2 UNL 1 -2.485 2.742 0.838 1.00 0.00 O1-\\nHETATM 14 H1 UNL 1 3.531 0.642 0.736 1.00 0.00 H \\nHETATM 15 H2 UNL 1 4.133 -0.148 -0.770 1.00 0.00 H \\nHETATM 16 H3 UNL 1 3.376 1.493 -0.854 1.00 0.00 H \\nHETATM 17 H4 UNL 1 1.005 1.188 0.826 1.00 0.00 H \\nHETATM 18 H5 UNL 1 0.344 -2.292 0.249 1.00 0.00 H \\nHETATM 19 H6 UNL 1 -1.889 -3.335 0.323 1.00 0.00 H \\nHETATM 20 H7 UNL 1 -3.764 0.442 0.270 1.00 0.00 H \\nCONECT 1 2 14 15 16\\nCONECT 2 3 3 4\\nCONECT 4 5 17\\nCONECT 5 6 6 10\\nCONECT 6 7 18\\nCONECT 7 8 8 19\\nCONECT 8 9\\nCONECT 9 10 10 20\\nCONECT 10 11\\nCONECT 11 12 12 13\\nEND\\n\",\"pdb\");\n\tviewer_17532640697518232.setStyle({\"stick\": {}});\n\tviewer_17532640697518232.zoomTo();\nviewer_17532640697518232.render();\n});\n</script>",
258
+ "text/html": [
259
+ "<div id=\"3dmolviewer_17532640697518232\" style=\"position: relative; width: 400px; height: 300px;\">\n",
260
+ " <p id=\"3dmolwarning_17532640697518232\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason. Please check your browser console for error messages.<br></p>\n",
261
+ " </div>\n",
262
+ "<script>\n",
263
+ "\n",
264
+ "var loadScriptAsync = function(uri){\n",
265
+ " return new Promise((resolve, reject) => {\n",
266
+ " //this is to ignore the existence of requirejs amd\n",
267
+ " var savedexports, savedmodule;\n",
268
+ " if (typeof exports !== 'undefined') savedexports = exports;\n",
269
+ " else exports = {}\n",
270
+ " if (typeof module !== 'undefined') savedmodule = module;\n",
271
+ " else module = {}\n",
272
+ "\n",
273
+ " var tag = document.createElement('script');\n",
274
+ " tag.src = uri;\n",
275
+ " tag.async = true;\n",
276
+ " tag.onload = () => {\n",
277
+ " exports = savedexports;\n",
278
+ " module = savedmodule;\n",
279
+ " resolve();\n",
280
+ " };\n",
281
+ " var firstScriptTag = document.getElementsByTagName('script')[0];\n",
282
+ " firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n",
283
+ "});\n",
284
+ "};\n",
285
+ "\n",
286
+ "if(typeof $3Dmolpromise === 'undefined') {\n",
287
+ "$3Dmolpromise = null;\n",
288
+ " $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n",
289
+ "}\n",
290
+ "\n",
291
+ "var viewer_17532640697518232 = null;\n",
292
+ "var warn = document.getElementById(\"3dmolwarning_17532640697518232\");\n",
293
+ "if(warn) {\n",
294
+ " warn.parentNode.removeChild(warn);\n",
295
+ "}\n",
296
+ "$3Dmolpromise.then(function() {\n",
297
+ "viewer_17532640697518232 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_17532640697518232\"),{backgroundColor:\"white\"});\n",
298
+ "viewer_17532640697518232.zoomTo();\n",
299
+ "\tviewer_17532640697518232.addModel(\"HETATM 1 C1 UNL 1 3.341 0.506 -0.349 1.00 0.00 C \\nHETATM 2 C2 UNL 1 1.994 -0.109 -0.554 1.00 0.00 C \\nHETATM 3 O1 UNL 1 1.839 -0.974 -1.458 1.00 0.00 O \\nHETATM 4 N1 UNL 1 0.876 0.346 0.221 1.00 0.00 N \\nHETATM 5 C3 UNL 1 -0.424 -0.266 0.167 1.00 0.00 C \\nHETATM 6 C4 UNL 1 -0.537 -1.665 0.219 1.00 0.00 C \\nHETATM 7 C5 UNL 1 -1.798 -2.258 0.278 1.00 0.00 C \\nHETATM 8 N2 UNL 1 -2.913 -1.485 0.302 1.00 0.00 N \\nHETATM 9 C6 UNL 1 -2.844 -0.130 0.260 1.00 0.00 C \\nHETATM 10 C7 UNL 1 -1.602 0.521 0.177 1.00 0.00 C \\nHETATM 11 C8 UNL 1 -1.585 1.998 0.085 1.00 0.00 C \\nHETATM 12 S1 UNL 1 -0.600 2.783 -0.963 1.00 0.00 S \\nHETATM 13 O2 UNL 1 -2.485 2.742 0.838 1.00 0.00 O1-\\nHETATM 14 H1 UNL 1 3.531 0.642 0.736 1.00 0.00 H \\nHETATM 15 H2 UNL 1 4.133 -0.148 -0.770 1.00 0.00 H \\nHETATM 16 H3 UNL 1 3.376 1.493 -0.854 1.00 0.00 H \\nHETATM 17 H4 UNL 1 1.005 1.188 0.826 1.00 0.00 H \\nHETATM 18 H5 UNL 1 0.344 -2.292 0.249 1.00 0.00 H \\nHETATM 19 H6 UNL 1 -1.889 -3.335 0.323 1.00 0.00 H \\nHETATM 20 H7 UNL 1 -3.764 0.442 0.270 1.00 0.00 H \\nCONECT 1 2 14 15 16\\nCONECT 2 3 3 4\\nCONECT 4 5 17\\nCONECT 5 6 6 10\\nCONECT 6 7 18\\nCONECT 7 8 8 19\\nCONECT 8 9\\nCONECT 9 10 10 20\\nCONECT 10 11\\nCONECT 11 12 12 13\\nEND\\n\",\"pdb\");\n",
300
+ "\tviewer_17532640697518232.setStyle({\"stick\": {}});\n",
301
+ "\tviewer_17532640697518232.zoomTo();\n",
302
+ "viewer_17532640697518232.render();\n",
303
+ "});\n",
304
+ "</script>"
305
+ ]
306
+ },
307
+ "metadata": {},
308
+ "output_type": "display_data"
309
+ },
310
+ {
311
+ "data": {
312
+ "text/plain": [
313
+ "<py3Dmol.view at 0x11fd5a780>"
314
+ ]
315
+ },
316
+ "execution_count": 13,
317
+ "metadata": {},
318
+ "output_type": "execute_result"
319
+ }
320
+ ],
321
+ "source": [
322
+ "input_ids[0][5] = tokenizer.mask_token_id\n",
323
+ "input_ids[0][9] = tokenizer.mask_token_id\n",
324
+ "input_ids[0][18] = tokenizer.mask_token_id\n",
325
+ "input_ids[0][11] = tokenizer.mask_token_id\n",
326
+ "# Generate output sequence\n",
327
+ "output_ids = model.generate(input_ids, max_length=128, num_beams=5, num_return_sequences=5,\n",
328
+ " early_stopping=True)\n",
329
+ "output = tokenizer.decode(output_ids[1][n:], skip_special_tokens=True)\n",
330
+ "print(output)\n",
331
+ "smiles = sf.decoder(output)\n",
332
+ "print(smiles)\n",
333
+ "smiles_to_3d([smiles])"
334
+ ]
335
+ },
336
+ {
337
+ "cell_type": "code",
338
+ "execution_count": null,
339
+ "id": "f696bb9c-2870-4b0b-9b62-1623411e5df6",
340
+ "metadata": {},
341
+ "outputs": [],
342
+ "source": []
343
+ }
344
+ ],
345
+ "metadata": {
346
+ "kernelspec": {
347
+ "display_name": "Python 3 (ipykernel)",
348
+ "language": "python",
349
+ "name": "python3"
350
+ },
351
+ "language_info": {
352
+ "codemirror_mode": {
353
+ "name": "ipython",
354
+ "version": 3
355
+ },
356
+ "file_extension": ".py",
357
+ "mimetype": "text/x-python",
358
+ "name": "python",
359
+ "nbconvert_exporter": "python",
360
+ "pygments_lexer": "ipython3",
361
+ "version": "3.12.10"
362
+ }
363
+ },
364
+ "nbformat": 4,
365
+ "nbformat_minor": 5
366
+ }
added_tokens.json ADDED
@@ -0,0 +1,472 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[#11C-1]": 50724,
3
+ "[#14C]": 50531,
4
+ "[#Al]": 50558,
5
+ "[#B]": 50433,
6
+ "[#Branch1]": 50363,
7
+ "[#Branch2]": 50310,
8
+ "[#Branch3]": 50524,
9
+ "[#C-1]": 50471,
10
+ "[#C]": 50385,
11
+ "[#N+1]": 50527,
12
+ "[#N]": 50379,
13
+ "[#O+1]": 50351,
14
+ "[#Ring1]": 50659,
15
+ "[#Ring2]": 50590,
16
+ "[#S]": 50375,
17
+ "[-/Ring1]": 50311,
18
+ "[-/Ring2]": 50367,
19
+ "[-\\Ring1]": 50421,
20
+ "[-\\Ring2]": 50638,
21
+ "[/-Ring1]": 50274,
22
+ "[/-Ring2]": 50459,
23
+ "[/11CH3]": 50687,
24
+ "[/123I]": 50580,
25
+ "[/125I]": 50671,
26
+ "[/131I]": 50561,
27
+ "[/13CH1]": 50625,
28
+ "[/13C]": 50632,
29
+ "[/14CH1]": 50635,
30
+ "[/14C]": 50706,
31
+ "[/As]": 50409,
32
+ "[/B]": 50655,
33
+ "[/Br]": 50272,
34
+ "[/C-1]": 50700,
35
+ "[/C@@H1]": 50323,
36
+ "[/C@@]": 50497,
37
+ "[/C@H1]": 50516,
38
+ "[/C@]": 50358,
39
+ "[/CH1-1]": 50716,
40
+ "[/C]": 50449,
41
+ "[/Cl]": 50492,
42
+ "[/F]": 50693,
43
+ "[/I]": 50404,
44
+ "[/N+1]": 50283,
45
+ "[/N-1]": 50615,
46
+ "[/NH1+1]": 50415,
47
+ "[/NH1]": 50521,
48
+ "[/N]": 50350,
49
+ "[/O-1]": 50650,
50
+ "[/O]": 50457,
51
+ "[/P@]": 50653,
52
+ "[/P]": 50667,
53
+ "[/S+1]": 50682,
54
+ "[/S-1]": 50621,
55
+ "[/S]": 50406,
56
+ "[/Se]": 50704,
57
+ "[/Si]": 50664,
58
+ "[/Te]": 50628,
59
+ "[10B]": 50540,
60
+ "[11C@H1]": 50622,
61
+ "[11CH1]": 50606,
62
+ "[11CH2]": 50648,
63
+ "[11CH3]": 50608,
64
+ "[11C]": 50617,
65
+ "[123I-1]": 50641,
66
+ "[123IH1]": 50566,
67
+ "[123I]": 50697,
68
+ "[123Te]": 50550,
69
+ "[124I-1]": 50677,
70
+ "[124I]": 50663,
71
+ "[125I-1]": 50544,
72
+ "[125IH1]": 50703,
73
+ "[125I]": 50681,
74
+ "[127I]": 50552,
75
+ "[127Xe]": 50535,
76
+ "[129Xe]": 50548,
77
+ "[131Cs]": 50688,
78
+ "[131I-1]": 50684,
79
+ "[131I]": 50689,
80
+ "[133Xe]": 50589,
81
+ "[135I]": 50626,
82
+ "[13CH1]": 50579,
83
+ "[13CH2]": 50698,
84
+ "[13CH3]": 50619,
85
+ "[13C]": 50633,
86
+ "[13NH3]": 50631,
87
+ "[14C@@H1]": 50627,
88
+ "[14C@H1]": 50594,
89
+ "[14C@]": 50721,
90
+ "[14CH1]": 50598,
91
+ "[14CH2]": 50585,
92
+ "[14CH3]": 50675,
93
+ "[14C]": 50712,
94
+ "[15NH1]": 50553,
95
+ "[15N]": 50595,
96
+ "[15OH2]": 50578,
97
+ "[17F]": 50611,
98
+ "[18F-1]": 50690,
99
+ "[18FH1]": 50582,
100
+ "[18F]": 50549,
101
+ "[18OH1]": 50604,
102
+ "[19F]": 50529,
103
+ "[223Ra+2]": 50715,
104
+ "[223Ra]": 50577,
105
+ "[22Na+1]": 50647,
106
+ "[2H]": 50282,
107
+ "[32PH1]": 50643,
108
+ "[32P]": 50670,
109
+ "[35S]": 50656,
110
+ "[3H]": 50612,
111
+ "[42K+1]": 50616,
112
+ "[45Ca+2]": 50645,
113
+ "[47Ca+2]": 50592,
114
+ "[4H]": 50673,
115
+ "[73Se]": 50574,
116
+ "[75Se]": 50705,
117
+ "[76BrH1]": 50649,
118
+ "[76Br]": 50713,
119
+ "[81Kr]": 50559,
120
+ "[82Rb+1]": 50547,
121
+ "[82Rb]": 50538,
122
+ "[85Sr+2]": 50672,
123
+ "[85SrH2]": 50668,
124
+ "[89Sr+2]": 50723,
125
+ "[=11C]": 50542,
126
+ "[=13CH1]": 50568,
127
+ "[=13C]": 50654,
128
+ "[=14CH1]": 50714,
129
+ "[=14C]": 50701,
130
+ "[=18O]": 50678,
131
+ "[=Al]": 50545,
132
+ "[=As]": 50448,
133
+ "[=B-1]": 50607,
134
+ "[=B]": 50388,
135
+ "[=Be]": 50474,
136
+ "[=Branch1]": 50335,
137
+ "[=Branch2]": 50395,
138
+ "[=Branch3]": 50525,
139
+ "[=C-1]": 50488,
140
+ "[=CH0]": 50502,
141
+ "[=CH1]": 50692,
142
+ "[=C]": 50500,
143
+ "[=Ca]": 50347,
144
+ "[=Cd]": 50441,
145
+ "[=Ce]": 50392,
146
+ "[=Co]": 50496,
147
+ "[=Cr]": 50315,
148
+ "[=Cu]": 50509,
149
+ "[=Fe]": 50290,
150
+ "[=Ge]": 50261,
151
+ "[=Mg]": 50634,
152
+ "[=Mn]": 50383,
153
+ "[=Mo]": 50267,
154
+ "[=N+1]": 50451,
155
+ "[=N-1]": 50316,
156
+ "[=NH1+1]": 50426,
157
+ "[=NH2+1]": 50605,
158
+ "[=N]": 50287,
159
+ "[=Nb]": 50484,
160
+ "[=Ni]": 50298,
161
+ "[=O+1]": 50394,
162
+ "[=O]": 50269,
163
+ "[=P+1]": 50349,
164
+ "[=P@@]": 50587,
165
+ "[=P@]": 50593,
166
+ "[=PH0]": 50304,
167
+ "[=PH1]": 50381,
168
+ "[=PH2]": 50572,
169
+ "[=P]": 50308,
170
+ "[=Pb]": 50397,
171
+ "[=Ring1]": 50400,
172
+ "[=Ring2]": 50330,
173
+ "[=Ring3]": 50528,
174
+ "[=S+1]": 50473,
175
+ "[=S@@]": 50661,
176
+ "[=S@]": 50707,
177
+ "[=SH0]": 50275,
178
+ "[=SH1]": 50584,
179
+ "[=S]": 50348,
180
+ "[=Se+1]": 50546,
181
+ "[=Se]": 50403,
182
+ "[=Si]": 50277,
183
+ "[=SnH2]": 50317,
184
+ "[=Sn]": 50390,
185
+ "[=Sr]": 50472,
186
+ "[=Te+1]": 50658,
187
+ "[=Te]": 50435,
188
+ "[=Ti]": 50327,
189
+ "[=V+2]": 50285,
190
+ "[=V]": 50372,
191
+ "[=W]": 50469,
192
+ "[=Y]": 50503,
193
+ "[=Zn]": 50513,
194
+ "[=Zr]": 50331,
195
+ "[Ag+1]": 50340,
196
+ "[Ag-4]": 50573,
197
+ "[Ag]": 50487,
198
+ "[Al+3]": 50293,
199
+ "[Al-3]": 50597,
200
+ "[Al]": 50399,
201
+ "[As+1]": 50717,
202
+ "[As+3]": 50295,
203
+ "[As-1]": 50530,
204
+ "[AsH1]": 50591,
205
+ "[AsH3]": 50534,
206
+ "[As]": 50520,
207
+ "[Au+1]": 50324,
208
+ "[Au+3]": 50444,
209
+ "[Au]": 50414,
210
+ "[B+3]": 50393,
211
+ "[B-1]": 50281,
212
+ "[B@-1]": 50583,
213
+ "[B@@-1]": 50599,
214
+ "[BH0]": 50337,
215
+ "[BH1-1]": 50629,
216
+ "[BH2-1]": 50620,
217
+ "[BH3-1]": 50702,
218
+ "[B]": 50467,
219
+ "[Ba+2]": 50265,
220
+ "[Ba]": 50571,
221
+ "[Be+2]": 50624,
222
+ "[Be]": 50402,
223
+ "[Bi+3]": 50423,
224
+ "[Bi]": 50514,
225
+ "[Br+2]": 50560,
226
+ "[Br-1]": 50307,
227
+ "[Br]": 50515,
228
+ "[Branch1]": 50482,
229
+ "[Branch2]": 50386,
230
+ "[Branch3]": 50355,
231
+ "[C+1]": 50439,
232
+ "[C-1]": 50490,
233
+ "[C@@H1]": 50405,
234
+ "[C@@]": 50491,
235
+ "[C@H1]": 50475,
236
+ "[C@]": 50510,
237
+ "[CH0]": 50288,
238
+ "[CH1-1]": 50417,
239
+ "[CH1]": 50486,
240
+ "[CH2]": 50328,
241
+ "[C]": 50410,
242
+ "[Ca+2]": 50429,
243
+ "[CaH2]": 50495,
244
+ "[Ca]": 50477,
245
+ "[Cd+2]": 50359,
246
+ "[Cd]": 50494,
247
+ "[Ce+3]": 50360,
248
+ "[Ce]": 50325,
249
+ "[Cl+1]": 50541,
250
+ "[Cl+2]": 50569,
251
+ "[Cl+3]": 50342,
252
+ "[Cl-1]": 50284,
253
+ "[ClH0]": 50264,
254
+ "[Cl]": 50292,
255
+ "[Co+2]": 50299,
256
+ "[Co+3]": 50440,
257
+ "[Co]": 50401,
258
+ "[Cr+3]": 50481,
259
+ "[Cr]": 50306,
260
+ "[Cs+1]": 50376,
261
+ "[Cs]": 50470,
262
+ "[Cu+1]": 50380,
263
+ "[Cu+2]": 50493,
264
+ "[Cu]": 50343,
265
+ "[Dy+3]": 50460,
266
+ "[Dy]": 50326,
267
+ "[F-1]": 50412,
268
+ "[FH0]": 50280,
269
+ "[F]": 50454,
270
+ "[Fe+2]": 50279,
271
+ "[Fe+3]": 50511,
272
+ "[Fe]": 50424,
273
+ "[Gd+3]": 50356,
274
+ "[Gd]": 50321,
275
+ "[Ge]": 50434,
276
+ "[H+1]": 50352,
277
+ "[H-1]": 50391,
278
+ "[HH1]": 50662,
279
+ "[H]": 50378,
280
+ "[He]": 50614,
281
+ "[Hf+4]": 50483,
282
+ "[Hf]": 50425,
283
+ "[Hg+1]": 50450,
284
+ "[Hg+2]": 50432,
285
+ "[Hg]": 50329,
286
+ "[I+1]": 50642,
287
+ "[I+2]": 50669,
288
+ "[I+3]": 50537,
289
+ "[I-1]": 50370,
290
+ "[I]": 50333,
291
+ "[In+3]": 50341,
292
+ "[Ir]": 50430,
293
+ "[K+1]": 50396,
294
+ "[KH1]": 50533,
295
+ "[K]": 50336,
296
+ "[Kr]": 50630,
297
+ "[La+3]": 50507,
298
+ "[La]": 50468,
299
+ "[Li+1]": 50260,
300
+ "[LiH1]": 50652,
301
+ "[Li]": 50498,
302
+ "[Lu+3]": 50364,
303
+ "[Mg+1]": 50562,
304
+ "[Mg+2]": 50263,
305
+ "[MgH2]": 50365,
306
+ "[Mg]": 50466,
307
+ "[Mn+2]": 50465,
308
+ "[Mn+3]": 50384,
309
+ "[Mn]": 50517,
310
+ "[Mo+2]": 50273,
311
+ "[Mo]": 50302,
312
+ "[N+1]": 50346,
313
+ "[N-1]": 50278,
314
+ "[N@+1]": 50680,
315
+ "[N@@+1]": 50636,
316
+ "[N@@]": 50640,
317
+ "[N@]": 50258,
318
+ "[NH0]": 50320,
319
+ "[NH1+1]": 50368,
320
+ "[NH1+2]": 50300,
321
+ "[NH1-1]": 50556,
322
+ "[NH1]": 50438,
323
+ "[NH2+1]": 50313,
324
+ "[NH3+1]": 50354,
325
+ "[NH4+1]": 50455,
326
+ "[N]": 50266,
327
+ "[Na+1]": 50362,
328
+ "[NaH1]": 50711,
329
+ "[Na]": 50322,
330
+ "[Nb+5]": 50353,
331
+ "[Nb]": 50480,
332
+ "[Nd+3]": 50339,
333
+ "[Nd]": 50436,
334
+ "[Ni+2]": 50408,
335
+ "[Ni]": 50377,
336
+ "[Nop]": 50522,
337
+ "[O+1]": 50447,
338
+ "[O-1]": 50453,
339
+ "[O-2]": 50344,
340
+ "[OH0]": 50445,
341
+ "[OH1+1]": 50551,
342
+ "[OH1-1]": 50437,
343
+ "[OH1]": 50575,
344
+ "[O]": 50371,
345
+ "[P+1]": 50501,
346
+ "[P@+1]": 50685,
347
+ "[P@@+1]": 50563,
348
+ "[P@@]": 50289,
349
+ "[P@]": 50398,
350
+ "[PH0]": 50319,
351
+ "[PH1]": 50479,
352
+ "[PH2+1]": 50694,
353
+ "[PH2]": 50564,
354
+ "[P]": 50485,
355
+ "[Pb+2]": 50361,
356
+ "[Pb]": 50427,
357
+ "[Pd+2]": 50446,
358
+ "[Pr+3]": 50338,
359
+ "[Pt+2]": 50431,
360
+ "[Pt+4]": 50519,
361
+ "[Ra+2]": 50710,
362
+ "[Ra]": 50696,
363
+ "[Rb+1]": 50699,
364
+ "[Rb]": 50660,
365
+ "[Re]": 50456,
366
+ "[Rh+3]": 50418,
367
+ "[Rh]": 50374,
368
+ "[Ring1]": 50296,
369
+ "[Ring2]": 50407,
370
+ "[Ring3]": 50523,
371
+ "[Ru+3]": 50508,
372
+ "[S+1]": 50461,
373
+ "[S-1]": 50369,
374
+ "[S-2]": 50303,
375
+ "[S@+1]": 50536,
376
+ "[S@@+1]": 50609,
377
+ "[S@@]": 50665,
378
+ "[S@]": 50613,
379
+ "[SEP]": 50726,
380
+ "[SH0]": 50518,
381
+ "[SH1+1]": 50683,
382
+ "[SH1-1]": 50382,
383
+ "[SH1-2]": 50268,
384
+ "[SH1]": 50676,
385
+ "[SH2]": 50588,
386
+ "[S]": 50309,
387
+ "[Sb+3]": 50387,
388
+ "[Sb]": 50413,
389
+ "[Se+1]": 50666,
390
+ "[Se-1]": 50603,
391
+ "[Se-2]": 50586,
392
+ "[SeH1]": 50637,
393
+ "[SeH2]": 50644,
394
+ "[Se]": 50259,
395
+ "[Si+4]": 50478,
396
+ "[Si-1]": 50601,
397
+ "[Si@]": 50419,
398
+ "[SiH1-1]": 50543,
399
+ "[SiH1]": 50505,
400
+ "[SiH2]": 50709,
401
+ "[SiH3-1]": 50639,
402
+ "[SiH4]": 50570,
403
+ "[Si]": 50334,
404
+ "[Sm+3]": 50297,
405
+ "[Sn+2]": 50452,
406
+ "[Sn+4]": 50462,
407
+ "[SnH2]": 50422,
408
+ "[Sn]": 50276,
409
+ "[Sr+2]": 50458,
410
+ "[SrH2]": 50576,
411
+ "[Sr]": 50314,
412
+ "[Ta]": 50411,
413
+ "[Te+1]": 50596,
414
+ "[Te-1]": 50600,
415
+ "[TeH1]": 50695,
416
+ "[TeH2]": 50719,
417
+ "[Te]": 50512,
418
+ "[Ti+2]": 50443,
419
+ "[Ti+4]": 50464,
420
+ "[Ti]": 50499,
421
+ "[V+2]": 50504,
422
+ "[V]": 50506,
423
+ "[W]": 50345,
424
+ "[Xe]": 50657,
425
+ "[Y+3]": 50442,
426
+ "[Y]": 50373,
427
+ "[Zn+1]": 50679,
428
+ "[Zn+2]": 50357,
429
+ "[Zn-2]": 50554,
430
+ "[Zn]": 50305,
431
+ "[Zr+2]": 50332,
432
+ "[Zr+4]": 50270,
433
+ "[Zr]": 50416,
434
+ "[\\-Ring1]": 50489,
435
+ "[\\-Ring2]": 50294,
436
+ "[\\123I]": 50623,
437
+ "[\\125I]": 50718,
438
+ "[\\131I]": 50557,
439
+ "[\\3H]": 50610,
440
+ "[\\As]": 50389,
441
+ "[\\B]": 50567,
442
+ "[\\Br]": 50366,
443
+ "[\\C-1]": 50565,
444
+ "[\\C@@H1]": 50312,
445
+ "[\\C@@]": 50581,
446
+ "[\\C@H1]": 50301,
447
+ "[\\C@]": 50526,
448
+ "[\\CH1-1]": 50686,
449
+ "[\\C]": 50476,
450
+ "[\\Cl]": 50428,
451
+ "[\\F]": 50720,
452
+ "[\\I]": 50463,
453
+ "[\\N+1]": 50271,
454
+ "[\\NH1+1]": 50286,
455
+ "[\\NH1-1]": 50618,
456
+ "[\\NH1]": 50318,
457
+ "[\\N]": 50262,
458
+ "[\\O-1]": 50532,
459
+ "[\\O]": 50420,
460
+ "[\\P+1]": 50651,
461
+ "[\\PH1]": 50708,
462
+ "[\\P]": 50646,
463
+ "[\\S+1]": 50539,
464
+ "[\\S-1]": 50602,
465
+ "[\\S]": 50291,
466
+ "[\\SeH1]": 50674,
467
+ "[\\Se]": 50691,
468
+ "[\\Si]": 50555,
469
+ "[\\Te]": 50722,
470
+ "[mask]": 50725,
471
+ "[nop]": 50257
472
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.48.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50727
39
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step140000
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bac4c2f49b99725ee39be55476579193e474801c27e01ecf760df051daaa3b1
3
+ size 327533344
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc01645a35abddf4ac67ef22b48b90990d316f59d39d69db007ae67afe2e3fec
3
+ size 14512
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "mask_token": {
5
+ "content": "[mask]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "pad_token": "<|endoftext|>",
12
+ "sep_token": {
13
+ "content": "[SEP]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "unk_token": "<|endoftext|>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,3783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "[nop]",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": "[N@]",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": "[Se]",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": "[Li+1]",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": "[=Ge]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": "[\\N]",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": "[Mg+2]",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": "[ClH0]",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": "[Ba+2]",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": "[N]",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": "[=Mo]",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": "[SH1-2]",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": "[=O]",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": "[Zr+4]",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": "[\\N+1]",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": "[/Br]",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": "[Mo+2]",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": "[/-Ring1]",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": "[=SH0]",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": "[Sn]",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": "[=Si]",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": "[N-1]",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": "[Fe+2]",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": "[FH0]",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": "[B-1]",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": "[2H]",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": "[/N+1]",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": "[Cl-1]",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": "[=V+2]",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": "[\\NH1+1]",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "[=N]",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "[CH0]",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "[P@@]",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "[=Fe]",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "[\\S]",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "[Cl]",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "[Al+3]",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "[\\-Ring2]",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "50295": {
317
+ "content": "[As+3]",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "50296": {
325
+ "content": "[Ring1]",
326
+ "lstrip": false,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "50297": {
333
+ "content": "[Sm+3]",
334
+ "lstrip": false,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "50298": {
341
+ "content": "[=Ni]",
342
+ "lstrip": false,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "50299": {
349
+ "content": "[Co+2]",
350
+ "lstrip": false,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "50300": {
357
+ "content": "[NH1+2]",
358
+ "lstrip": false,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "50301": {
365
+ "content": "[\\C@H1]",
366
+ "lstrip": false,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "50302": {
373
+ "content": "[Mo]",
374
+ "lstrip": false,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "50303": {
381
+ "content": "[S-2]",
382
+ "lstrip": false,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "50304": {
389
+ "content": "[=PH0]",
390
+ "lstrip": false,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "50305": {
397
+ "content": "[Zn]",
398
+ "lstrip": false,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "50306": {
405
+ "content": "[Cr]",
406
+ "lstrip": false,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "50307": {
413
+ "content": "[Br-1]",
414
+ "lstrip": false,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "50308": {
421
+ "content": "[=P]",
422
+ "lstrip": false,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "50309": {
429
+ "content": "[S]",
430
+ "lstrip": false,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "50310": {
437
+ "content": "[#Branch2]",
438
+ "lstrip": false,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "50311": {
445
+ "content": "[-/Ring1]",
446
+ "lstrip": false,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "50312": {
453
+ "content": "[\\C@@H1]",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "50313": {
461
+ "content": "[NH2+1]",
462
+ "lstrip": false,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "50314": {
469
+ "content": "[Sr]",
470
+ "lstrip": false,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "50315": {
477
+ "content": "[=Cr]",
478
+ "lstrip": false,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "50316": {
485
+ "content": "[=N-1]",
486
+ "lstrip": false,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "50317": {
493
+ "content": "[=SnH2]",
494
+ "lstrip": false,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "50318": {
501
+ "content": "[\\NH1]",
502
+ "lstrip": false,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "50319": {
509
+ "content": "[PH0]",
510
+ "lstrip": false,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "50320": {
517
+ "content": "[NH0]",
518
+ "lstrip": false,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "50321": {
525
+ "content": "[Gd]",
526
+ "lstrip": false,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "50322": {
533
+ "content": "[Na]",
534
+ "lstrip": false,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "50323": {
541
+ "content": "[/C@@H1]",
542
+ "lstrip": false,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "50324": {
549
+ "content": "[Au+1]",
550
+ "lstrip": false,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "50325": {
557
+ "content": "[Ce]",
558
+ "lstrip": false,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "50326": {
565
+ "content": "[Dy]",
566
+ "lstrip": false,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "50327": {
573
+ "content": "[=Ti]",
574
+ "lstrip": false,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "50328": {
581
+ "content": "[CH2]",
582
+ "lstrip": false,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "50329": {
589
+ "content": "[Hg]",
590
+ "lstrip": false,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "50330": {
597
+ "content": "[=Ring2]",
598
+ "lstrip": false,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "50331": {
605
+ "content": "[=Zr]",
606
+ "lstrip": false,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "50332": {
613
+ "content": "[Zr+2]",
614
+ "lstrip": false,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "50333": {
621
+ "content": "[I]",
622
+ "lstrip": false,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "50334": {
629
+ "content": "[Si]",
630
+ "lstrip": false,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "50335": {
637
+ "content": "[=Branch1]",
638
+ "lstrip": false,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "50336": {
645
+ "content": "[K]",
646
+ "lstrip": false,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "50337": {
653
+ "content": "[BH0]",
654
+ "lstrip": false,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "50338": {
661
+ "content": "[Pr+3]",
662
+ "lstrip": false,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "50339": {
669
+ "content": "[Nd+3]",
670
+ "lstrip": false,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "50340": {
677
+ "content": "[Ag+1]",
678
+ "lstrip": false,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "50341": {
685
+ "content": "[In+3]",
686
+ "lstrip": false,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "50342": {
693
+ "content": "[Cl+3]",
694
+ "lstrip": false,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "50343": {
701
+ "content": "[Cu]",
702
+ "lstrip": false,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "50344": {
709
+ "content": "[O-2]",
710
+ "lstrip": false,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "50345": {
717
+ "content": "[W]",
718
+ "lstrip": false,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "50346": {
725
+ "content": "[N+1]",
726
+ "lstrip": false,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "50347": {
733
+ "content": "[=Ca]",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "50348": {
741
+ "content": "[=S]",
742
+ "lstrip": false,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "50349": {
749
+ "content": "[=P+1]",
750
+ "lstrip": false,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "50350": {
757
+ "content": "[/N]",
758
+ "lstrip": false,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "50351": {
765
+ "content": "[#O+1]",
766
+ "lstrip": false,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "50352": {
773
+ "content": "[H+1]",
774
+ "lstrip": false,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "50353": {
781
+ "content": "[Nb+5]",
782
+ "lstrip": false,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "50354": {
789
+ "content": "[NH3+1]",
790
+ "lstrip": false,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "50355": {
797
+ "content": "[Branch3]",
798
+ "lstrip": false,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "50356": {
805
+ "content": "[Gd+3]",
806
+ "lstrip": false,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "50357": {
813
+ "content": "[Zn+2]",
814
+ "lstrip": false,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "50358": {
821
+ "content": "[/C@]",
822
+ "lstrip": false,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ },
828
+ "50359": {
829
+ "content": "[Cd+2]",
830
+ "lstrip": false,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "50360": {
837
+ "content": "[Ce+3]",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "50361": {
845
+ "content": "[Pb+2]",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ },
852
+ "50362": {
853
+ "content": "[Na+1]",
854
+ "lstrip": false,
855
+ "normalized": true,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": false
859
+ },
860
+ "50363": {
861
+ "content": "[#Branch1]",
862
+ "lstrip": false,
863
+ "normalized": true,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": false
867
+ },
868
+ "50364": {
869
+ "content": "[Lu+3]",
870
+ "lstrip": false,
871
+ "normalized": true,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": false
875
+ },
876
+ "50365": {
877
+ "content": "[MgH2]",
878
+ "lstrip": false,
879
+ "normalized": true,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": false
883
+ },
884
+ "50366": {
885
+ "content": "[\\Br]",
886
+ "lstrip": false,
887
+ "normalized": true,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": false
891
+ },
892
+ "50367": {
893
+ "content": "[-/Ring2]",
894
+ "lstrip": false,
895
+ "normalized": true,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": false
899
+ },
900
+ "50368": {
901
+ "content": "[NH1+1]",
902
+ "lstrip": false,
903
+ "normalized": true,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": false
907
+ },
908
+ "50369": {
909
+ "content": "[S-1]",
910
+ "lstrip": false,
911
+ "normalized": true,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": false
915
+ },
916
+ "50370": {
917
+ "content": "[I-1]",
918
+ "lstrip": false,
919
+ "normalized": true,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": false
923
+ },
924
+ "50371": {
925
+ "content": "[O]",
926
+ "lstrip": false,
927
+ "normalized": true,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": false
931
+ },
932
+ "50372": {
933
+ "content": "[=V]",
934
+ "lstrip": false,
935
+ "normalized": true,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": false
939
+ },
940
+ "50373": {
941
+ "content": "[Y]",
942
+ "lstrip": false,
943
+ "normalized": true,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": false
947
+ },
948
+ "50374": {
949
+ "content": "[Rh]",
950
+ "lstrip": false,
951
+ "normalized": true,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": false
955
+ },
956
+ "50375": {
957
+ "content": "[#S]",
958
+ "lstrip": false,
959
+ "normalized": true,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": false
963
+ },
964
+ "50376": {
965
+ "content": "[Cs+1]",
966
+ "lstrip": false,
967
+ "normalized": true,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": false
971
+ },
972
+ "50377": {
973
+ "content": "[Ni]",
974
+ "lstrip": false,
975
+ "normalized": true,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": false
979
+ },
980
+ "50378": {
981
+ "content": "[H]",
982
+ "lstrip": false,
983
+ "normalized": true,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": false
987
+ },
988
+ "50379": {
989
+ "content": "[#N]",
990
+ "lstrip": false,
991
+ "normalized": true,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": false
995
+ },
996
+ "50380": {
997
+ "content": "[Cu+1]",
998
+ "lstrip": false,
999
+ "normalized": true,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": false
1003
+ },
1004
+ "50381": {
1005
+ "content": "[=PH1]",
1006
+ "lstrip": false,
1007
+ "normalized": true,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": false
1011
+ },
1012
+ "50382": {
1013
+ "content": "[SH1-1]",
1014
+ "lstrip": false,
1015
+ "normalized": true,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": false
1019
+ },
1020
+ "50383": {
1021
+ "content": "[=Mn]",
1022
+ "lstrip": false,
1023
+ "normalized": true,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": false
1027
+ },
1028
+ "50384": {
1029
+ "content": "[Mn+3]",
1030
+ "lstrip": false,
1031
+ "normalized": true,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": false
1035
+ },
1036
+ "50385": {
1037
+ "content": "[#C]",
1038
+ "lstrip": false,
1039
+ "normalized": true,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": false
1043
+ },
1044
+ "50386": {
1045
+ "content": "[Branch2]",
1046
+ "lstrip": false,
1047
+ "normalized": true,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": false
1051
+ },
1052
+ "50387": {
1053
+ "content": "[Sb+3]",
1054
+ "lstrip": false,
1055
+ "normalized": true,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": false
1059
+ },
1060
+ "50388": {
1061
+ "content": "[=B]",
1062
+ "lstrip": false,
1063
+ "normalized": true,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": false
1067
+ },
1068
+ "50389": {
1069
+ "content": "[\\As]",
1070
+ "lstrip": false,
1071
+ "normalized": true,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": false
1075
+ },
1076
+ "50390": {
1077
+ "content": "[=Sn]",
1078
+ "lstrip": false,
1079
+ "normalized": true,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": false
1083
+ },
1084
+ "50391": {
1085
+ "content": "[H-1]",
1086
+ "lstrip": false,
1087
+ "normalized": true,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": false
1091
+ },
1092
+ "50392": {
1093
+ "content": "[=Ce]",
1094
+ "lstrip": false,
1095
+ "normalized": true,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": false
1099
+ },
1100
+ "50393": {
1101
+ "content": "[B+3]",
1102
+ "lstrip": false,
1103
+ "normalized": true,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": false
1107
+ },
1108
+ "50394": {
1109
+ "content": "[=O+1]",
1110
+ "lstrip": false,
1111
+ "normalized": true,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": false
1115
+ },
1116
+ "50395": {
1117
+ "content": "[=Branch2]",
1118
+ "lstrip": false,
1119
+ "normalized": true,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": false
1123
+ },
1124
+ "50396": {
1125
+ "content": "[K+1]",
1126
+ "lstrip": false,
1127
+ "normalized": true,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": false
1131
+ },
1132
+ "50397": {
1133
+ "content": "[=Pb]",
1134
+ "lstrip": false,
1135
+ "normalized": true,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": false
1139
+ },
1140
+ "50398": {
1141
+ "content": "[P@]",
1142
+ "lstrip": false,
1143
+ "normalized": true,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": false
1147
+ },
1148
+ "50399": {
1149
+ "content": "[Al]",
1150
+ "lstrip": false,
1151
+ "normalized": true,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": false
1155
+ },
1156
+ "50400": {
1157
+ "content": "[=Ring1]",
1158
+ "lstrip": false,
1159
+ "normalized": true,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": false
1163
+ },
1164
+ "50401": {
1165
+ "content": "[Co]",
1166
+ "lstrip": false,
1167
+ "normalized": true,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": false
1171
+ },
1172
+ "50402": {
1173
+ "content": "[Be]",
1174
+ "lstrip": false,
1175
+ "normalized": true,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": false
1179
+ },
1180
+ "50403": {
1181
+ "content": "[=Se]",
1182
+ "lstrip": false,
1183
+ "normalized": true,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": false
1187
+ },
1188
+ "50404": {
1189
+ "content": "[/I]",
1190
+ "lstrip": false,
1191
+ "normalized": true,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": false
1195
+ },
1196
+ "50405": {
1197
+ "content": "[C@@H1]",
1198
+ "lstrip": false,
1199
+ "normalized": true,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": false
1203
+ },
1204
+ "50406": {
1205
+ "content": "[/S]",
1206
+ "lstrip": false,
1207
+ "normalized": true,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": false
1211
+ },
1212
+ "50407": {
1213
+ "content": "[Ring2]",
1214
+ "lstrip": false,
1215
+ "normalized": true,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": false
1219
+ },
1220
+ "50408": {
1221
+ "content": "[Ni+2]",
1222
+ "lstrip": false,
1223
+ "normalized": true,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": false
1227
+ },
1228
+ "50409": {
1229
+ "content": "[/As]",
1230
+ "lstrip": false,
1231
+ "normalized": true,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": false
1235
+ },
1236
+ "50410": {
1237
+ "content": "[C]",
1238
+ "lstrip": false,
1239
+ "normalized": true,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": false
1243
+ },
1244
+ "50411": {
1245
+ "content": "[Ta]",
1246
+ "lstrip": false,
1247
+ "normalized": true,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": false
1251
+ },
1252
+ "50412": {
1253
+ "content": "[F-1]",
1254
+ "lstrip": false,
1255
+ "normalized": true,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": false
1259
+ },
1260
+ "50413": {
1261
+ "content": "[Sb]",
1262
+ "lstrip": false,
1263
+ "normalized": true,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": false
1267
+ },
1268
+ "50414": {
1269
+ "content": "[Au]",
1270
+ "lstrip": false,
1271
+ "normalized": true,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": false
1275
+ },
1276
+ "50415": {
1277
+ "content": "[/NH1+1]",
1278
+ "lstrip": false,
1279
+ "normalized": true,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": false
1283
+ },
1284
+ "50416": {
1285
+ "content": "[Zr]",
1286
+ "lstrip": false,
1287
+ "normalized": true,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": false
1291
+ },
1292
+ "50417": {
1293
+ "content": "[CH1-1]",
1294
+ "lstrip": false,
1295
+ "normalized": true,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": false
1299
+ },
1300
+ "50418": {
1301
+ "content": "[Rh+3]",
1302
+ "lstrip": false,
1303
+ "normalized": true,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": false
1307
+ },
1308
+ "50419": {
1309
+ "content": "[Si@]",
1310
+ "lstrip": false,
1311
+ "normalized": true,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": false
1315
+ },
1316
+ "50420": {
1317
+ "content": "[\\O]",
1318
+ "lstrip": false,
1319
+ "normalized": true,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": false
1323
+ },
1324
+ "50421": {
1325
+ "content": "[-\\Ring1]",
1326
+ "lstrip": false,
1327
+ "normalized": true,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": false
1331
+ },
1332
+ "50422": {
1333
+ "content": "[SnH2]",
1334
+ "lstrip": false,
1335
+ "normalized": true,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": false
1339
+ },
1340
+ "50423": {
1341
+ "content": "[Bi+3]",
1342
+ "lstrip": false,
1343
+ "normalized": true,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": false
1347
+ },
1348
+ "50424": {
1349
+ "content": "[Fe]",
1350
+ "lstrip": false,
1351
+ "normalized": true,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": false
1355
+ },
1356
+ "50425": {
1357
+ "content": "[Hf]",
1358
+ "lstrip": false,
1359
+ "normalized": true,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": false
1363
+ },
1364
+ "50426": {
1365
+ "content": "[=NH1+1]",
1366
+ "lstrip": false,
1367
+ "normalized": true,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": false
1371
+ },
1372
+ "50427": {
1373
+ "content": "[Pb]",
1374
+ "lstrip": false,
1375
+ "normalized": true,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": false
1379
+ },
1380
+ "50428": {
1381
+ "content": "[\\Cl]",
1382
+ "lstrip": false,
1383
+ "normalized": true,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": false
1387
+ },
1388
+ "50429": {
1389
+ "content": "[Ca+2]",
1390
+ "lstrip": false,
1391
+ "normalized": true,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": false
1395
+ },
1396
+ "50430": {
1397
+ "content": "[Ir]",
1398
+ "lstrip": false,
1399
+ "normalized": true,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": false
1403
+ },
1404
+ "50431": {
1405
+ "content": "[Pt+2]",
1406
+ "lstrip": false,
1407
+ "normalized": true,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": false
1411
+ },
1412
+ "50432": {
1413
+ "content": "[Hg+2]",
1414
+ "lstrip": false,
1415
+ "normalized": true,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": false
1419
+ },
1420
+ "50433": {
1421
+ "content": "[#B]",
1422
+ "lstrip": false,
1423
+ "normalized": true,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": false
1427
+ },
1428
+ "50434": {
1429
+ "content": "[Ge]",
1430
+ "lstrip": false,
1431
+ "normalized": true,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": false
1435
+ },
1436
+ "50435": {
1437
+ "content": "[=Te]",
1438
+ "lstrip": false,
1439
+ "normalized": true,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": false
1443
+ },
1444
+ "50436": {
1445
+ "content": "[Nd]",
1446
+ "lstrip": false,
1447
+ "normalized": true,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": false
1451
+ },
1452
+ "50437": {
1453
+ "content": "[OH1-1]",
1454
+ "lstrip": false,
1455
+ "normalized": true,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": false
1459
+ },
1460
+ "50438": {
1461
+ "content": "[NH1]",
1462
+ "lstrip": false,
1463
+ "normalized": true,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": false
1467
+ },
1468
+ "50439": {
1469
+ "content": "[C+1]",
1470
+ "lstrip": false,
1471
+ "normalized": true,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": false
1475
+ },
1476
+ "50440": {
1477
+ "content": "[Co+3]",
1478
+ "lstrip": false,
1479
+ "normalized": true,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": false
1483
+ },
1484
+ "50441": {
1485
+ "content": "[=Cd]",
1486
+ "lstrip": false,
1487
+ "normalized": true,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": false
1491
+ },
1492
+ "50442": {
1493
+ "content": "[Y+3]",
1494
+ "lstrip": false,
1495
+ "normalized": true,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": false
1499
+ },
1500
+ "50443": {
1501
+ "content": "[Ti+2]",
1502
+ "lstrip": false,
1503
+ "normalized": true,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": false
1507
+ },
1508
+ "50444": {
1509
+ "content": "[Au+3]",
1510
+ "lstrip": false,
1511
+ "normalized": true,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": false
1515
+ },
1516
+ "50445": {
1517
+ "content": "[OH0]",
1518
+ "lstrip": false,
1519
+ "normalized": true,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": false
1523
+ },
1524
+ "50446": {
1525
+ "content": "[Pd+2]",
1526
+ "lstrip": false,
1527
+ "normalized": true,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": false
1531
+ },
1532
+ "50447": {
1533
+ "content": "[O+1]",
1534
+ "lstrip": false,
1535
+ "normalized": true,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": false
1539
+ },
1540
+ "50448": {
1541
+ "content": "[=As]",
1542
+ "lstrip": false,
1543
+ "normalized": true,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": false
1547
+ },
1548
+ "50449": {
1549
+ "content": "[/C]",
1550
+ "lstrip": false,
1551
+ "normalized": true,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": false
1555
+ },
1556
+ "50450": {
1557
+ "content": "[Hg+1]",
1558
+ "lstrip": false,
1559
+ "normalized": true,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": false
1563
+ },
1564
+ "50451": {
1565
+ "content": "[=N+1]",
1566
+ "lstrip": false,
1567
+ "normalized": true,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": false
1571
+ },
1572
+ "50452": {
1573
+ "content": "[Sn+2]",
1574
+ "lstrip": false,
1575
+ "normalized": true,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": false
1579
+ },
1580
+ "50453": {
1581
+ "content": "[O-1]",
1582
+ "lstrip": false,
1583
+ "normalized": true,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": false
1587
+ },
1588
+ "50454": {
1589
+ "content": "[F]",
1590
+ "lstrip": false,
1591
+ "normalized": true,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": false
1595
+ },
1596
+ "50455": {
1597
+ "content": "[NH4+1]",
1598
+ "lstrip": false,
1599
+ "normalized": true,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": false
1603
+ },
1604
+ "50456": {
1605
+ "content": "[Re]",
1606
+ "lstrip": false,
1607
+ "normalized": true,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": false
1611
+ },
1612
+ "50457": {
1613
+ "content": "[/O]",
1614
+ "lstrip": false,
1615
+ "normalized": true,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": false
1619
+ },
1620
+ "50458": {
1621
+ "content": "[Sr+2]",
1622
+ "lstrip": false,
1623
+ "normalized": true,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": false
1627
+ },
1628
+ "50459": {
1629
+ "content": "[/-Ring2]",
1630
+ "lstrip": false,
1631
+ "normalized": true,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": false
1635
+ },
1636
+ "50460": {
1637
+ "content": "[Dy+3]",
1638
+ "lstrip": false,
1639
+ "normalized": true,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": false
1643
+ },
1644
+ "50461": {
1645
+ "content": "[S+1]",
1646
+ "lstrip": false,
1647
+ "normalized": true,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": false
1651
+ },
1652
+ "50462": {
1653
+ "content": "[Sn+4]",
1654
+ "lstrip": false,
1655
+ "normalized": true,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": false
1659
+ },
1660
+ "50463": {
1661
+ "content": "[\\I]",
1662
+ "lstrip": false,
1663
+ "normalized": true,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": false
1667
+ },
1668
+ "50464": {
1669
+ "content": "[Ti+4]",
1670
+ "lstrip": false,
1671
+ "normalized": true,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": false
1675
+ },
1676
+ "50465": {
1677
+ "content": "[Mn+2]",
1678
+ "lstrip": false,
1679
+ "normalized": true,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": false
1683
+ },
1684
+ "50466": {
1685
+ "content": "[Mg]",
1686
+ "lstrip": false,
1687
+ "normalized": true,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": false
1691
+ },
1692
+ "50467": {
1693
+ "content": "[B]",
1694
+ "lstrip": false,
1695
+ "normalized": true,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": false
1699
+ },
1700
+ "50468": {
1701
+ "content": "[La]",
1702
+ "lstrip": false,
1703
+ "normalized": true,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": false
1707
+ },
1708
+ "50469": {
1709
+ "content": "[=W]",
1710
+ "lstrip": false,
1711
+ "normalized": true,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": false
1715
+ },
1716
+ "50470": {
1717
+ "content": "[Cs]",
1718
+ "lstrip": false,
1719
+ "normalized": true,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": false
1723
+ },
1724
+ "50471": {
1725
+ "content": "[#C-1]",
1726
+ "lstrip": false,
1727
+ "normalized": true,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": false
1731
+ },
1732
+ "50472": {
1733
+ "content": "[=Sr]",
1734
+ "lstrip": false,
1735
+ "normalized": true,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": false
1739
+ },
1740
+ "50473": {
1741
+ "content": "[=S+1]",
1742
+ "lstrip": false,
1743
+ "normalized": true,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": false
1747
+ },
1748
+ "50474": {
1749
+ "content": "[=Be]",
1750
+ "lstrip": false,
1751
+ "normalized": true,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": false
1755
+ },
1756
+ "50475": {
1757
+ "content": "[C@H1]",
1758
+ "lstrip": false,
1759
+ "normalized": true,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": false
1763
+ },
1764
+ "50476": {
1765
+ "content": "[\\C]",
1766
+ "lstrip": false,
1767
+ "normalized": true,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": false
1771
+ },
1772
+ "50477": {
1773
+ "content": "[Ca]",
1774
+ "lstrip": false,
1775
+ "normalized": true,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": false
1779
+ },
1780
+ "50478": {
1781
+ "content": "[Si+4]",
1782
+ "lstrip": false,
1783
+ "normalized": true,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": false
1787
+ },
1788
+ "50479": {
1789
+ "content": "[PH1]",
1790
+ "lstrip": false,
1791
+ "normalized": true,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": false
1795
+ },
1796
+ "50480": {
1797
+ "content": "[Nb]",
1798
+ "lstrip": false,
1799
+ "normalized": true,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": false
1803
+ },
1804
+ "50481": {
1805
+ "content": "[Cr+3]",
1806
+ "lstrip": false,
1807
+ "normalized": true,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": false
1811
+ },
1812
+ "50482": {
1813
+ "content": "[Branch1]",
1814
+ "lstrip": false,
1815
+ "normalized": true,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": false
1819
+ },
1820
+ "50483": {
1821
+ "content": "[Hf+4]",
1822
+ "lstrip": false,
1823
+ "normalized": true,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": false
1827
+ },
1828
+ "50484": {
1829
+ "content": "[=Nb]",
1830
+ "lstrip": false,
1831
+ "normalized": true,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": false
1835
+ },
1836
+ "50485": {
1837
+ "content": "[P]",
1838
+ "lstrip": false,
1839
+ "normalized": true,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": false
1843
+ },
1844
+ "50486": {
1845
+ "content": "[CH1]",
1846
+ "lstrip": false,
1847
+ "normalized": true,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": false
1851
+ },
1852
+ "50487": {
1853
+ "content": "[Ag]",
1854
+ "lstrip": false,
1855
+ "normalized": true,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": false
1859
+ },
1860
+ "50488": {
1861
+ "content": "[=C-1]",
1862
+ "lstrip": false,
1863
+ "normalized": true,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": false
1867
+ },
1868
+ "50489": {
1869
+ "content": "[\\-Ring1]",
1870
+ "lstrip": false,
1871
+ "normalized": true,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": false
1875
+ },
1876
+ "50490": {
1877
+ "content": "[C-1]",
1878
+ "lstrip": false,
1879
+ "normalized": true,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": false
1883
+ },
1884
+ "50491": {
1885
+ "content": "[C@@]",
1886
+ "lstrip": false,
1887
+ "normalized": true,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": false
1891
+ },
1892
+ "50492": {
1893
+ "content": "[/Cl]",
1894
+ "lstrip": false,
1895
+ "normalized": true,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": false
1899
+ },
1900
+ "50493": {
1901
+ "content": "[Cu+2]",
1902
+ "lstrip": false,
1903
+ "normalized": true,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": false
1907
+ },
1908
+ "50494": {
1909
+ "content": "[Cd]",
1910
+ "lstrip": false,
1911
+ "normalized": true,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": false
1915
+ },
1916
+ "50495": {
1917
+ "content": "[CaH2]",
1918
+ "lstrip": false,
1919
+ "normalized": true,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": false
1923
+ },
1924
+ "50496": {
1925
+ "content": "[=Co]",
1926
+ "lstrip": false,
1927
+ "normalized": true,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": false
1931
+ },
1932
+ "50497": {
1933
+ "content": "[/C@@]",
1934
+ "lstrip": false,
1935
+ "normalized": true,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": false
1939
+ },
1940
+ "50498": {
1941
+ "content": "[Li]",
1942
+ "lstrip": false,
1943
+ "normalized": true,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": false
1947
+ },
1948
+ "50499": {
1949
+ "content": "[Ti]",
1950
+ "lstrip": false,
1951
+ "normalized": true,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": false
1955
+ },
1956
+ "50500": {
1957
+ "content": "[=C]",
1958
+ "lstrip": false,
1959
+ "normalized": true,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": false
1963
+ },
1964
+ "50501": {
1965
+ "content": "[P+1]",
1966
+ "lstrip": false,
1967
+ "normalized": true,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": false
1971
+ },
1972
+ "50502": {
1973
+ "content": "[=CH0]",
1974
+ "lstrip": false,
1975
+ "normalized": true,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": false
1979
+ },
1980
+ "50503": {
1981
+ "content": "[=Y]",
1982
+ "lstrip": false,
1983
+ "normalized": true,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": false
1987
+ },
1988
+ "50504": {
1989
+ "content": "[V+2]",
1990
+ "lstrip": false,
1991
+ "normalized": true,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": false
1995
+ },
1996
+ "50505": {
1997
+ "content": "[SiH1]",
1998
+ "lstrip": false,
1999
+ "normalized": true,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": false
2003
+ },
2004
+ "50506": {
2005
+ "content": "[V]",
2006
+ "lstrip": false,
2007
+ "normalized": true,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": false
2011
+ },
2012
+ "50507": {
2013
+ "content": "[La+3]",
2014
+ "lstrip": false,
2015
+ "normalized": true,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": false
2019
+ },
2020
+ "50508": {
2021
+ "content": "[Ru+3]",
2022
+ "lstrip": false,
2023
+ "normalized": true,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": false
2027
+ },
2028
+ "50509": {
2029
+ "content": "[=Cu]",
2030
+ "lstrip": false,
2031
+ "normalized": true,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": false
2035
+ },
2036
+ "50510": {
2037
+ "content": "[C@]",
2038
+ "lstrip": false,
2039
+ "normalized": true,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": false
2043
+ },
2044
+ "50511": {
2045
+ "content": "[Fe+3]",
2046
+ "lstrip": false,
2047
+ "normalized": true,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": false
2051
+ },
2052
+ "50512": {
2053
+ "content": "[Te]",
2054
+ "lstrip": false,
2055
+ "normalized": true,
2056
+ "rstrip": false,
2057
+ "single_word": false,
2058
+ "special": false
2059
+ },
2060
+ "50513": {
2061
+ "content": "[=Zn]",
2062
+ "lstrip": false,
2063
+ "normalized": true,
2064
+ "rstrip": false,
2065
+ "single_word": false,
2066
+ "special": false
2067
+ },
2068
+ "50514": {
2069
+ "content": "[Bi]",
2070
+ "lstrip": false,
2071
+ "normalized": true,
2072
+ "rstrip": false,
2073
+ "single_word": false,
2074
+ "special": false
2075
+ },
2076
+ "50515": {
2077
+ "content": "[Br]",
2078
+ "lstrip": false,
2079
+ "normalized": true,
2080
+ "rstrip": false,
2081
+ "single_word": false,
2082
+ "special": false
2083
+ },
2084
+ "50516": {
2085
+ "content": "[/C@H1]",
2086
+ "lstrip": false,
2087
+ "normalized": true,
2088
+ "rstrip": false,
2089
+ "single_word": false,
2090
+ "special": false
2091
+ },
2092
+ "50517": {
2093
+ "content": "[Mn]",
2094
+ "lstrip": false,
2095
+ "normalized": true,
2096
+ "rstrip": false,
2097
+ "single_word": false,
2098
+ "special": false
2099
+ },
2100
+ "50518": {
2101
+ "content": "[SH0]",
2102
+ "lstrip": false,
2103
+ "normalized": true,
2104
+ "rstrip": false,
2105
+ "single_word": false,
2106
+ "special": false
2107
+ },
2108
+ "50519": {
2109
+ "content": "[Pt+4]",
2110
+ "lstrip": false,
2111
+ "normalized": true,
2112
+ "rstrip": false,
2113
+ "single_word": false,
2114
+ "special": false
2115
+ },
2116
+ "50520": {
2117
+ "content": "[As]",
2118
+ "lstrip": false,
2119
+ "normalized": true,
2120
+ "rstrip": false,
2121
+ "single_word": false,
2122
+ "special": false
2123
+ },
2124
+ "50521": {
2125
+ "content": "[/NH1]",
2126
+ "lstrip": false,
2127
+ "normalized": true,
2128
+ "rstrip": false,
2129
+ "single_word": false,
2130
+ "special": false
2131
+ },
2132
+ "50522": {
2133
+ "content": "[Nop]",
2134
+ "lstrip": false,
2135
+ "normalized": true,
2136
+ "rstrip": false,
2137
+ "single_word": false,
2138
+ "special": false
2139
+ },
2140
+ "50523": {
2141
+ "content": "[Ring3]",
2142
+ "lstrip": false,
2143
+ "normalized": true,
2144
+ "rstrip": false,
2145
+ "single_word": false,
2146
+ "special": false
2147
+ },
2148
+ "50524": {
2149
+ "content": "[#Branch3]",
2150
+ "lstrip": false,
2151
+ "normalized": true,
2152
+ "rstrip": false,
2153
+ "single_word": false,
2154
+ "special": false
2155
+ },
2156
+ "50525": {
2157
+ "content": "[=Branch3]",
2158
+ "lstrip": false,
2159
+ "normalized": true,
2160
+ "rstrip": false,
2161
+ "single_word": false,
2162
+ "special": false
2163
+ },
2164
+ "50526": {
2165
+ "content": "[\\C@]",
2166
+ "lstrip": false,
2167
+ "normalized": true,
2168
+ "rstrip": false,
2169
+ "single_word": false,
2170
+ "special": false
2171
+ },
2172
+ "50527": {
2173
+ "content": "[#N+1]",
2174
+ "lstrip": false,
2175
+ "normalized": true,
2176
+ "rstrip": false,
2177
+ "single_word": false,
2178
+ "special": false
2179
+ },
2180
+ "50528": {
2181
+ "content": "[=Ring3]",
2182
+ "lstrip": false,
2183
+ "normalized": true,
2184
+ "rstrip": false,
2185
+ "single_word": false,
2186
+ "special": false
2187
+ },
2188
+ "50529": {
2189
+ "content": "[19F]",
2190
+ "lstrip": false,
2191
+ "normalized": true,
2192
+ "rstrip": false,
2193
+ "single_word": false,
2194
+ "special": false
2195
+ },
2196
+ "50530": {
2197
+ "content": "[As-1]",
2198
+ "lstrip": false,
2199
+ "normalized": true,
2200
+ "rstrip": false,
2201
+ "single_word": false,
2202
+ "special": false
2203
+ },
2204
+ "50531": {
2205
+ "content": "[#14C]",
2206
+ "lstrip": false,
2207
+ "normalized": true,
2208
+ "rstrip": false,
2209
+ "single_word": false,
2210
+ "special": false
2211
+ },
2212
+ "50532": {
2213
+ "content": "[\\O-1]",
2214
+ "lstrip": false,
2215
+ "normalized": true,
2216
+ "rstrip": false,
2217
+ "single_word": false,
2218
+ "special": false
2219
+ },
2220
+ "50533": {
2221
+ "content": "[KH1]",
2222
+ "lstrip": false,
2223
+ "normalized": true,
2224
+ "rstrip": false,
2225
+ "single_word": false,
2226
+ "special": false
2227
+ },
2228
+ "50534": {
2229
+ "content": "[AsH3]",
2230
+ "lstrip": false,
2231
+ "normalized": true,
2232
+ "rstrip": false,
2233
+ "single_word": false,
2234
+ "special": false
2235
+ },
2236
+ "50535": {
2237
+ "content": "[127Xe]",
2238
+ "lstrip": false,
2239
+ "normalized": true,
2240
+ "rstrip": false,
2241
+ "single_word": false,
2242
+ "special": false
2243
+ },
2244
+ "50536": {
2245
+ "content": "[S@+1]",
2246
+ "lstrip": false,
2247
+ "normalized": true,
2248
+ "rstrip": false,
2249
+ "single_word": false,
2250
+ "special": false
2251
+ },
2252
+ "50537": {
2253
+ "content": "[I+3]",
2254
+ "lstrip": false,
2255
+ "normalized": true,
2256
+ "rstrip": false,
2257
+ "single_word": false,
2258
+ "special": false
2259
+ },
2260
+ "50538": {
2261
+ "content": "[82Rb]",
2262
+ "lstrip": false,
2263
+ "normalized": true,
2264
+ "rstrip": false,
2265
+ "single_word": false,
2266
+ "special": false
2267
+ },
2268
+ "50539": {
2269
+ "content": "[\\S+1]",
2270
+ "lstrip": false,
2271
+ "normalized": true,
2272
+ "rstrip": false,
2273
+ "single_word": false,
2274
+ "special": false
2275
+ },
2276
+ "50540": {
2277
+ "content": "[10B]",
2278
+ "lstrip": false,
2279
+ "normalized": true,
2280
+ "rstrip": false,
2281
+ "single_word": false,
2282
+ "special": false
2283
+ },
2284
+ "50541": {
2285
+ "content": "[Cl+1]",
2286
+ "lstrip": false,
2287
+ "normalized": true,
2288
+ "rstrip": false,
2289
+ "single_word": false,
2290
+ "special": false
2291
+ },
2292
+ "50542": {
2293
+ "content": "[=11C]",
2294
+ "lstrip": false,
2295
+ "normalized": true,
2296
+ "rstrip": false,
2297
+ "single_word": false,
2298
+ "special": false
2299
+ },
2300
+ "50543": {
2301
+ "content": "[SiH1-1]",
2302
+ "lstrip": false,
2303
+ "normalized": true,
2304
+ "rstrip": false,
2305
+ "single_word": false,
2306
+ "special": false
2307
+ },
2308
+ "50544": {
2309
+ "content": "[125I-1]",
2310
+ "lstrip": false,
2311
+ "normalized": true,
2312
+ "rstrip": false,
2313
+ "single_word": false,
2314
+ "special": false
2315
+ },
2316
+ "50545": {
2317
+ "content": "[=Al]",
2318
+ "lstrip": false,
2319
+ "normalized": true,
2320
+ "rstrip": false,
2321
+ "single_word": false,
2322
+ "special": false
2323
+ },
2324
+ "50546": {
2325
+ "content": "[=Se+1]",
2326
+ "lstrip": false,
2327
+ "normalized": true,
2328
+ "rstrip": false,
2329
+ "single_word": false,
2330
+ "special": false
2331
+ },
2332
+ "50547": {
2333
+ "content": "[82Rb+1]",
2334
+ "lstrip": false,
2335
+ "normalized": true,
2336
+ "rstrip": false,
2337
+ "single_word": false,
2338
+ "special": false
2339
+ },
2340
+ "50548": {
2341
+ "content": "[129Xe]",
2342
+ "lstrip": false,
2343
+ "normalized": true,
2344
+ "rstrip": false,
2345
+ "single_word": false,
2346
+ "special": false
2347
+ },
2348
+ "50549": {
2349
+ "content": "[18F]",
2350
+ "lstrip": false,
2351
+ "normalized": true,
2352
+ "rstrip": false,
2353
+ "single_word": false,
2354
+ "special": false
2355
+ },
2356
+ "50550": {
2357
+ "content": "[123Te]",
2358
+ "lstrip": false,
2359
+ "normalized": true,
2360
+ "rstrip": false,
2361
+ "single_word": false,
2362
+ "special": false
2363
+ },
2364
+ "50551": {
2365
+ "content": "[OH1+1]",
2366
+ "lstrip": false,
2367
+ "normalized": true,
2368
+ "rstrip": false,
2369
+ "single_word": false,
2370
+ "special": false
2371
+ },
2372
+ "50552": {
2373
+ "content": "[127I]",
2374
+ "lstrip": false,
2375
+ "normalized": true,
2376
+ "rstrip": false,
2377
+ "single_word": false,
2378
+ "special": false
2379
+ },
2380
+ "50553": {
2381
+ "content": "[15NH1]",
2382
+ "lstrip": false,
2383
+ "normalized": true,
2384
+ "rstrip": false,
2385
+ "single_word": false,
2386
+ "special": false
2387
+ },
2388
+ "50554": {
2389
+ "content": "[Zn-2]",
2390
+ "lstrip": false,
2391
+ "normalized": true,
2392
+ "rstrip": false,
2393
+ "single_word": false,
2394
+ "special": false
2395
+ },
2396
+ "50555": {
2397
+ "content": "[\\Si]",
2398
+ "lstrip": false,
2399
+ "normalized": true,
2400
+ "rstrip": false,
2401
+ "single_word": false,
2402
+ "special": false
2403
+ },
2404
+ "50556": {
2405
+ "content": "[NH1-1]",
2406
+ "lstrip": false,
2407
+ "normalized": true,
2408
+ "rstrip": false,
2409
+ "single_word": false,
2410
+ "special": false
2411
+ },
2412
+ "50557": {
2413
+ "content": "[\\131I]",
2414
+ "lstrip": false,
2415
+ "normalized": true,
2416
+ "rstrip": false,
2417
+ "single_word": false,
2418
+ "special": false
2419
+ },
2420
+ "50558": {
2421
+ "content": "[#Al]",
2422
+ "lstrip": false,
2423
+ "normalized": true,
2424
+ "rstrip": false,
2425
+ "single_word": false,
2426
+ "special": false
2427
+ },
2428
+ "50559": {
2429
+ "content": "[81Kr]",
2430
+ "lstrip": false,
2431
+ "normalized": true,
2432
+ "rstrip": false,
2433
+ "single_word": false,
2434
+ "special": false
2435
+ },
2436
+ "50560": {
2437
+ "content": "[Br+2]",
2438
+ "lstrip": false,
2439
+ "normalized": true,
2440
+ "rstrip": false,
2441
+ "single_word": false,
2442
+ "special": false
2443
+ },
2444
+ "50561": {
2445
+ "content": "[/131I]",
2446
+ "lstrip": false,
2447
+ "normalized": true,
2448
+ "rstrip": false,
2449
+ "single_word": false,
2450
+ "special": false
2451
+ },
2452
+ "50562": {
2453
+ "content": "[Mg+1]",
2454
+ "lstrip": false,
2455
+ "normalized": true,
2456
+ "rstrip": false,
2457
+ "single_word": false,
2458
+ "special": false
2459
+ },
2460
+ "50563": {
2461
+ "content": "[P@@+1]",
2462
+ "lstrip": false,
2463
+ "normalized": true,
2464
+ "rstrip": false,
2465
+ "single_word": false,
2466
+ "special": false
2467
+ },
2468
+ "50564": {
2469
+ "content": "[PH2]",
2470
+ "lstrip": false,
2471
+ "normalized": true,
2472
+ "rstrip": false,
2473
+ "single_word": false,
2474
+ "special": false
2475
+ },
2476
+ "50565": {
2477
+ "content": "[\\C-1]",
2478
+ "lstrip": false,
2479
+ "normalized": true,
2480
+ "rstrip": false,
2481
+ "single_word": false,
2482
+ "special": false
2483
+ },
2484
+ "50566": {
2485
+ "content": "[123IH1]",
2486
+ "lstrip": false,
2487
+ "normalized": true,
2488
+ "rstrip": false,
2489
+ "single_word": false,
2490
+ "special": false
2491
+ },
2492
+ "50567": {
2493
+ "content": "[\\B]",
2494
+ "lstrip": false,
2495
+ "normalized": true,
2496
+ "rstrip": false,
2497
+ "single_word": false,
2498
+ "special": false
2499
+ },
2500
+ "50568": {
2501
+ "content": "[=13CH1]",
2502
+ "lstrip": false,
2503
+ "normalized": true,
2504
+ "rstrip": false,
2505
+ "single_word": false,
2506
+ "special": false
2507
+ },
2508
+ "50569": {
2509
+ "content": "[Cl+2]",
2510
+ "lstrip": false,
2511
+ "normalized": true,
2512
+ "rstrip": false,
2513
+ "single_word": false,
2514
+ "special": false
2515
+ },
2516
+ "50570": {
2517
+ "content": "[SiH4]",
2518
+ "lstrip": false,
2519
+ "normalized": true,
2520
+ "rstrip": false,
2521
+ "single_word": false,
2522
+ "special": false
2523
+ },
2524
+ "50571": {
2525
+ "content": "[Ba]",
2526
+ "lstrip": false,
2527
+ "normalized": true,
2528
+ "rstrip": false,
2529
+ "single_word": false,
2530
+ "special": false
2531
+ },
2532
+ "50572": {
2533
+ "content": "[=PH2]",
2534
+ "lstrip": false,
2535
+ "normalized": true,
2536
+ "rstrip": false,
2537
+ "single_word": false,
2538
+ "special": false
2539
+ },
2540
+ "50573": {
2541
+ "content": "[Ag-4]",
2542
+ "lstrip": false,
2543
+ "normalized": true,
2544
+ "rstrip": false,
2545
+ "single_word": false,
2546
+ "special": false
2547
+ },
2548
+ "50574": {
2549
+ "content": "[73Se]",
2550
+ "lstrip": false,
2551
+ "normalized": true,
2552
+ "rstrip": false,
2553
+ "single_word": false,
2554
+ "special": false
2555
+ },
2556
+ "50575": {
2557
+ "content": "[OH1]",
2558
+ "lstrip": false,
2559
+ "normalized": true,
2560
+ "rstrip": false,
2561
+ "single_word": false,
2562
+ "special": false
2563
+ },
2564
+ "50576": {
2565
+ "content": "[SrH2]",
2566
+ "lstrip": false,
2567
+ "normalized": true,
2568
+ "rstrip": false,
2569
+ "single_word": false,
2570
+ "special": false
2571
+ },
2572
+ "50577": {
2573
+ "content": "[223Ra]",
2574
+ "lstrip": false,
2575
+ "normalized": true,
2576
+ "rstrip": false,
2577
+ "single_word": false,
2578
+ "special": false
2579
+ },
2580
+ "50578": {
2581
+ "content": "[15OH2]",
2582
+ "lstrip": false,
2583
+ "normalized": true,
2584
+ "rstrip": false,
2585
+ "single_word": false,
2586
+ "special": false
2587
+ },
2588
+ "50579": {
2589
+ "content": "[13CH1]",
2590
+ "lstrip": false,
2591
+ "normalized": true,
2592
+ "rstrip": false,
2593
+ "single_word": false,
2594
+ "special": false
2595
+ },
2596
+ "50580": {
2597
+ "content": "[/123I]",
2598
+ "lstrip": false,
2599
+ "normalized": true,
2600
+ "rstrip": false,
2601
+ "single_word": false,
2602
+ "special": false
2603
+ },
2604
+ "50581": {
2605
+ "content": "[\\C@@]",
2606
+ "lstrip": false,
2607
+ "normalized": true,
2608
+ "rstrip": false,
2609
+ "single_word": false,
2610
+ "special": false
2611
+ },
2612
+ "50582": {
2613
+ "content": "[18FH1]",
2614
+ "lstrip": false,
2615
+ "normalized": true,
2616
+ "rstrip": false,
2617
+ "single_word": false,
2618
+ "special": false
2619
+ },
2620
+ "50583": {
2621
+ "content": "[B@-1]",
2622
+ "lstrip": false,
2623
+ "normalized": true,
2624
+ "rstrip": false,
2625
+ "single_word": false,
2626
+ "special": false
2627
+ },
2628
+ "50584": {
2629
+ "content": "[=SH1]",
2630
+ "lstrip": false,
2631
+ "normalized": true,
2632
+ "rstrip": false,
2633
+ "single_word": false,
2634
+ "special": false
2635
+ },
2636
+ "50585": {
2637
+ "content": "[14CH2]",
2638
+ "lstrip": false,
2639
+ "normalized": true,
2640
+ "rstrip": false,
2641
+ "single_word": false,
2642
+ "special": false
2643
+ },
2644
+ "50586": {
2645
+ "content": "[Se-2]",
2646
+ "lstrip": false,
2647
+ "normalized": true,
2648
+ "rstrip": false,
2649
+ "single_word": false,
2650
+ "special": false
2651
+ },
2652
+ "50587": {
2653
+ "content": "[=P@@]",
2654
+ "lstrip": false,
2655
+ "normalized": true,
2656
+ "rstrip": false,
2657
+ "single_word": false,
2658
+ "special": false
2659
+ },
2660
+ "50588": {
2661
+ "content": "[SH2]",
2662
+ "lstrip": false,
2663
+ "normalized": true,
2664
+ "rstrip": false,
2665
+ "single_word": false,
2666
+ "special": false
2667
+ },
2668
+ "50589": {
2669
+ "content": "[133Xe]",
2670
+ "lstrip": false,
2671
+ "normalized": true,
2672
+ "rstrip": false,
2673
+ "single_word": false,
2674
+ "special": false
2675
+ },
2676
+ "50590": {
2677
+ "content": "[#Ring2]",
2678
+ "lstrip": false,
2679
+ "normalized": true,
2680
+ "rstrip": false,
2681
+ "single_word": false,
2682
+ "special": false
2683
+ },
2684
+ "50591": {
2685
+ "content": "[AsH1]",
2686
+ "lstrip": false,
2687
+ "normalized": true,
2688
+ "rstrip": false,
2689
+ "single_word": false,
2690
+ "special": false
2691
+ },
2692
+ "50592": {
2693
+ "content": "[47Ca+2]",
2694
+ "lstrip": false,
2695
+ "normalized": true,
2696
+ "rstrip": false,
2697
+ "single_word": false,
2698
+ "special": false
2699
+ },
2700
+ "50593": {
2701
+ "content": "[=P@]",
2702
+ "lstrip": false,
2703
+ "normalized": true,
2704
+ "rstrip": false,
2705
+ "single_word": false,
2706
+ "special": false
2707
+ },
2708
+ "50594": {
2709
+ "content": "[14C@H1]",
2710
+ "lstrip": false,
2711
+ "normalized": true,
2712
+ "rstrip": false,
2713
+ "single_word": false,
2714
+ "special": false
2715
+ },
2716
+ "50595": {
2717
+ "content": "[15N]",
2718
+ "lstrip": false,
2719
+ "normalized": true,
2720
+ "rstrip": false,
2721
+ "single_word": false,
2722
+ "special": false
2723
+ },
2724
+ "50596": {
2725
+ "content": "[Te+1]",
2726
+ "lstrip": false,
2727
+ "normalized": true,
2728
+ "rstrip": false,
2729
+ "single_word": false,
2730
+ "special": false
2731
+ },
2732
+ "50597": {
2733
+ "content": "[Al-3]",
2734
+ "lstrip": false,
2735
+ "normalized": true,
2736
+ "rstrip": false,
2737
+ "single_word": false,
2738
+ "special": false
2739
+ },
2740
+ "50598": {
2741
+ "content": "[14CH1]",
2742
+ "lstrip": false,
2743
+ "normalized": true,
2744
+ "rstrip": false,
2745
+ "single_word": false,
2746
+ "special": false
2747
+ },
2748
+ "50599": {
2749
+ "content": "[B@@-1]",
2750
+ "lstrip": false,
2751
+ "normalized": true,
2752
+ "rstrip": false,
2753
+ "single_word": false,
2754
+ "special": false
2755
+ },
2756
+ "50600": {
2757
+ "content": "[Te-1]",
2758
+ "lstrip": false,
2759
+ "normalized": true,
2760
+ "rstrip": false,
2761
+ "single_word": false,
2762
+ "special": false
2763
+ },
2764
+ "50601": {
2765
+ "content": "[Si-1]",
2766
+ "lstrip": false,
2767
+ "normalized": true,
2768
+ "rstrip": false,
2769
+ "single_word": false,
2770
+ "special": false
2771
+ },
2772
+ "50602": {
2773
+ "content": "[\\S-1]",
2774
+ "lstrip": false,
2775
+ "normalized": true,
2776
+ "rstrip": false,
2777
+ "single_word": false,
2778
+ "special": false
2779
+ },
2780
+ "50603": {
2781
+ "content": "[Se-1]",
2782
+ "lstrip": false,
2783
+ "normalized": true,
2784
+ "rstrip": false,
2785
+ "single_word": false,
2786
+ "special": false
2787
+ },
2788
+ "50604": {
2789
+ "content": "[18OH1]",
2790
+ "lstrip": false,
2791
+ "normalized": true,
2792
+ "rstrip": false,
2793
+ "single_word": false,
2794
+ "special": false
2795
+ },
2796
+ "50605": {
2797
+ "content": "[=NH2+1]",
2798
+ "lstrip": false,
2799
+ "normalized": true,
2800
+ "rstrip": false,
2801
+ "single_word": false,
2802
+ "special": false
2803
+ },
2804
+ "50606": {
2805
+ "content": "[11CH1]",
2806
+ "lstrip": false,
2807
+ "normalized": true,
2808
+ "rstrip": false,
2809
+ "single_word": false,
2810
+ "special": false
2811
+ },
2812
+ "50607": {
2813
+ "content": "[=B-1]",
2814
+ "lstrip": false,
2815
+ "normalized": true,
2816
+ "rstrip": false,
2817
+ "single_word": false,
2818
+ "special": false
2819
+ },
2820
+ "50608": {
2821
+ "content": "[11CH3]",
2822
+ "lstrip": false,
2823
+ "normalized": true,
2824
+ "rstrip": false,
2825
+ "single_word": false,
2826
+ "special": false
2827
+ },
2828
+ "50609": {
2829
+ "content": "[S@@+1]",
2830
+ "lstrip": false,
2831
+ "normalized": true,
2832
+ "rstrip": false,
2833
+ "single_word": false,
2834
+ "special": false
2835
+ },
2836
+ "50610": {
2837
+ "content": "[\\3H]",
2838
+ "lstrip": false,
2839
+ "normalized": true,
2840
+ "rstrip": false,
2841
+ "single_word": false,
2842
+ "special": false
2843
+ },
2844
+ "50611": {
2845
+ "content": "[17F]",
2846
+ "lstrip": false,
2847
+ "normalized": true,
2848
+ "rstrip": false,
2849
+ "single_word": false,
2850
+ "special": false
2851
+ },
2852
+ "50612": {
2853
+ "content": "[3H]",
2854
+ "lstrip": false,
2855
+ "normalized": true,
2856
+ "rstrip": false,
2857
+ "single_word": false,
2858
+ "special": false
2859
+ },
2860
+ "50613": {
2861
+ "content": "[S@]",
2862
+ "lstrip": false,
2863
+ "normalized": true,
2864
+ "rstrip": false,
2865
+ "single_word": false,
2866
+ "special": false
2867
+ },
2868
+ "50614": {
2869
+ "content": "[He]",
2870
+ "lstrip": false,
2871
+ "normalized": true,
2872
+ "rstrip": false,
2873
+ "single_word": false,
2874
+ "special": false
2875
+ },
2876
+ "50615": {
2877
+ "content": "[/N-1]",
2878
+ "lstrip": false,
2879
+ "normalized": true,
2880
+ "rstrip": false,
2881
+ "single_word": false,
2882
+ "special": false
2883
+ },
2884
+ "50616": {
2885
+ "content": "[42K+1]",
2886
+ "lstrip": false,
2887
+ "normalized": true,
2888
+ "rstrip": false,
2889
+ "single_word": false,
2890
+ "special": false
2891
+ },
2892
+ "50617": {
2893
+ "content": "[11C]",
2894
+ "lstrip": false,
2895
+ "normalized": true,
2896
+ "rstrip": false,
2897
+ "single_word": false,
2898
+ "special": false
2899
+ },
2900
+ "50618": {
2901
+ "content": "[\\NH1-1]",
2902
+ "lstrip": false,
2903
+ "normalized": true,
2904
+ "rstrip": false,
2905
+ "single_word": false,
2906
+ "special": false
2907
+ },
2908
+ "50619": {
2909
+ "content": "[13CH3]",
2910
+ "lstrip": false,
2911
+ "normalized": true,
2912
+ "rstrip": false,
2913
+ "single_word": false,
2914
+ "special": false
2915
+ },
2916
+ "50620": {
2917
+ "content": "[BH2-1]",
2918
+ "lstrip": false,
2919
+ "normalized": true,
2920
+ "rstrip": false,
2921
+ "single_word": false,
2922
+ "special": false
2923
+ },
2924
+ "50621": {
2925
+ "content": "[/S-1]",
2926
+ "lstrip": false,
2927
+ "normalized": true,
2928
+ "rstrip": false,
2929
+ "single_word": false,
2930
+ "special": false
2931
+ },
2932
+ "50622": {
2933
+ "content": "[11C@H1]",
2934
+ "lstrip": false,
2935
+ "normalized": true,
2936
+ "rstrip": false,
2937
+ "single_word": false,
2938
+ "special": false
2939
+ },
2940
+ "50623": {
2941
+ "content": "[\\123I]",
2942
+ "lstrip": false,
2943
+ "normalized": true,
2944
+ "rstrip": false,
2945
+ "single_word": false,
2946
+ "special": false
2947
+ },
2948
+ "50624": {
2949
+ "content": "[Be+2]",
2950
+ "lstrip": false,
2951
+ "normalized": true,
2952
+ "rstrip": false,
2953
+ "single_word": false,
2954
+ "special": false
2955
+ },
2956
+ "50625": {
2957
+ "content": "[/13CH1]",
2958
+ "lstrip": false,
2959
+ "normalized": true,
2960
+ "rstrip": false,
2961
+ "single_word": false,
2962
+ "special": false
2963
+ },
2964
+ "50626": {
2965
+ "content": "[135I]",
2966
+ "lstrip": false,
2967
+ "normalized": true,
2968
+ "rstrip": false,
2969
+ "single_word": false,
2970
+ "special": false
2971
+ },
2972
+ "50627": {
2973
+ "content": "[14C@@H1]",
2974
+ "lstrip": false,
2975
+ "normalized": true,
2976
+ "rstrip": false,
2977
+ "single_word": false,
2978
+ "special": false
2979
+ },
2980
+ "50628": {
2981
+ "content": "[/Te]",
2982
+ "lstrip": false,
2983
+ "normalized": true,
2984
+ "rstrip": false,
2985
+ "single_word": false,
2986
+ "special": false
2987
+ },
2988
+ "50629": {
2989
+ "content": "[BH1-1]",
2990
+ "lstrip": false,
2991
+ "normalized": true,
2992
+ "rstrip": false,
2993
+ "single_word": false,
2994
+ "special": false
2995
+ },
2996
+ "50630": {
2997
+ "content": "[Kr]",
2998
+ "lstrip": false,
2999
+ "normalized": true,
3000
+ "rstrip": false,
3001
+ "single_word": false,
3002
+ "special": false
3003
+ },
3004
+ "50631": {
3005
+ "content": "[13NH3]",
3006
+ "lstrip": false,
3007
+ "normalized": true,
3008
+ "rstrip": false,
3009
+ "single_word": false,
3010
+ "special": false
3011
+ },
3012
+ "50632": {
3013
+ "content": "[/13C]",
3014
+ "lstrip": false,
3015
+ "normalized": true,
3016
+ "rstrip": false,
3017
+ "single_word": false,
3018
+ "special": false
3019
+ },
3020
+ "50633": {
3021
+ "content": "[13C]",
3022
+ "lstrip": false,
3023
+ "normalized": true,
3024
+ "rstrip": false,
3025
+ "single_word": false,
3026
+ "special": false
3027
+ },
3028
+ "50634": {
3029
+ "content": "[=Mg]",
3030
+ "lstrip": false,
3031
+ "normalized": true,
3032
+ "rstrip": false,
3033
+ "single_word": false,
3034
+ "special": false
3035
+ },
3036
+ "50635": {
3037
+ "content": "[/14CH1]",
3038
+ "lstrip": false,
3039
+ "normalized": true,
3040
+ "rstrip": false,
3041
+ "single_word": false,
3042
+ "special": false
3043
+ },
3044
+ "50636": {
3045
+ "content": "[N@@+1]",
3046
+ "lstrip": false,
3047
+ "normalized": true,
3048
+ "rstrip": false,
3049
+ "single_word": false,
3050
+ "special": false
3051
+ },
3052
+ "50637": {
3053
+ "content": "[SeH1]",
3054
+ "lstrip": false,
3055
+ "normalized": true,
3056
+ "rstrip": false,
3057
+ "single_word": false,
3058
+ "special": false
3059
+ },
3060
+ "50638": {
3061
+ "content": "[-\\Ring2]",
3062
+ "lstrip": false,
3063
+ "normalized": true,
3064
+ "rstrip": false,
3065
+ "single_word": false,
3066
+ "special": false
3067
+ },
3068
+ "50639": {
3069
+ "content": "[SiH3-1]",
3070
+ "lstrip": false,
3071
+ "normalized": true,
3072
+ "rstrip": false,
3073
+ "single_word": false,
3074
+ "special": false
3075
+ },
3076
+ "50640": {
3077
+ "content": "[N@@]",
3078
+ "lstrip": false,
3079
+ "normalized": true,
3080
+ "rstrip": false,
3081
+ "single_word": false,
3082
+ "special": false
3083
+ },
3084
+ "50641": {
3085
+ "content": "[123I-1]",
3086
+ "lstrip": false,
3087
+ "normalized": true,
3088
+ "rstrip": false,
3089
+ "single_word": false,
3090
+ "special": false
3091
+ },
3092
+ "50642": {
3093
+ "content": "[I+1]",
3094
+ "lstrip": false,
3095
+ "normalized": true,
3096
+ "rstrip": false,
3097
+ "single_word": false,
3098
+ "special": false
3099
+ },
3100
+ "50643": {
3101
+ "content": "[32PH1]",
3102
+ "lstrip": false,
3103
+ "normalized": true,
3104
+ "rstrip": false,
3105
+ "single_word": false,
3106
+ "special": false
3107
+ },
3108
+ "50644": {
3109
+ "content": "[SeH2]",
3110
+ "lstrip": false,
3111
+ "normalized": true,
3112
+ "rstrip": false,
3113
+ "single_word": false,
3114
+ "special": false
3115
+ },
3116
+ "50645": {
3117
+ "content": "[45Ca+2]",
3118
+ "lstrip": false,
3119
+ "normalized": true,
3120
+ "rstrip": false,
3121
+ "single_word": false,
3122
+ "special": false
3123
+ },
3124
+ "50646": {
3125
+ "content": "[\\P]",
3126
+ "lstrip": false,
3127
+ "normalized": true,
3128
+ "rstrip": false,
3129
+ "single_word": false,
3130
+ "special": false
3131
+ },
3132
+ "50647": {
3133
+ "content": "[22Na+1]",
3134
+ "lstrip": false,
3135
+ "normalized": true,
3136
+ "rstrip": false,
3137
+ "single_word": false,
3138
+ "special": false
3139
+ },
3140
+ "50648": {
3141
+ "content": "[11CH2]",
3142
+ "lstrip": false,
3143
+ "normalized": true,
3144
+ "rstrip": false,
3145
+ "single_word": false,
3146
+ "special": false
3147
+ },
3148
+ "50649": {
3149
+ "content": "[76BrH1]",
3150
+ "lstrip": false,
3151
+ "normalized": true,
3152
+ "rstrip": false,
3153
+ "single_word": false,
3154
+ "special": false
3155
+ },
3156
+ "50650": {
3157
+ "content": "[/O-1]",
3158
+ "lstrip": false,
3159
+ "normalized": true,
3160
+ "rstrip": false,
3161
+ "single_word": false,
3162
+ "special": false
3163
+ },
3164
+ "50651": {
3165
+ "content": "[\\P+1]",
3166
+ "lstrip": false,
3167
+ "normalized": true,
3168
+ "rstrip": false,
3169
+ "single_word": false,
3170
+ "special": false
3171
+ },
3172
+ "50652": {
3173
+ "content": "[LiH1]",
3174
+ "lstrip": false,
3175
+ "normalized": true,
3176
+ "rstrip": false,
3177
+ "single_word": false,
3178
+ "special": false
3179
+ },
3180
+ "50653": {
3181
+ "content": "[/P@]",
3182
+ "lstrip": false,
3183
+ "normalized": true,
3184
+ "rstrip": false,
3185
+ "single_word": false,
3186
+ "special": false
3187
+ },
3188
+ "50654": {
3189
+ "content": "[=13C]",
3190
+ "lstrip": false,
3191
+ "normalized": true,
3192
+ "rstrip": false,
3193
+ "single_word": false,
3194
+ "special": false
3195
+ },
3196
+ "50655": {
3197
+ "content": "[/B]",
3198
+ "lstrip": false,
3199
+ "normalized": true,
3200
+ "rstrip": false,
3201
+ "single_word": false,
3202
+ "special": false
3203
+ },
3204
+ "50656": {
3205
+ "content": "[35S]",
3206
+ "lstrip": false,
3207
+ "normalized": true,
3208
+ "rstrip": false,
3209
+ "single_word": false,
3210
+ "special": false
3211
+ },
3212
+ "50657": {
3213
+ "content": "[Xe]",
3214
+ "lstrip": false,
3215
+ "normalized": true,
3216
+ "rstrip": false,
3217
+ "single_word": false,
3218
+ "special": false
3219
+ },
3220
+ "50658": {
3221
+ "content": "[=Te+1]",
3222
+ "lstrip": false,
3223
+ "normalized": true,
3224
+ "rstrip": false,
3225
+ "single_word": false,
3226
+ "special": false
3227
+ },
3228
+ "50659": {
3229
+ "content": "[#Ring1]",
3230
+ "lstrip": false,
3231
+ "normalized": true,
3232
+ "rstrip": false,
3233
+ "single_word": false,
3234
+ "special": false
3235
+ },
3236
+ "50660": {
3237
+ "content": "[Rb]",
3238
+ "lstrip": false,
3239
+ "normalized": true,
3240
+ "rstrip": false,
3241
+ "single_word": false,
3242
+ "special": false
3243
+ },
3244
+ "50661": {
3245
+ "content": "[=S@@]",
3246
+ "lstrip": false,
3247
+ "normalized": true,
3248
+ "rstrip": false,
3249
+ "single_word": false,
3250
+ "special": false
3251
+ },
3252
+ "50662": {
3253
+ "content": "[HH1]",
3254
+ "lstrip": false,
3255
+ "normalized": true,
3256
+ "rstrip": false,
3257
+ "single_word": false,
3258
+ "special": false
3259
+ },
3260
+ "50663": {
3261
+ "content": "[124I]",
3262
+ "lstrip": false,
3263
+ "normalized": true,
3264
+ "rstrip": false,
3265
+ "single_word": false,
3266
+ "special": false
3267
+ },
3268
+ "50664": {
3269
+ "content": "[/Si]",
3270
+ "lstrip": false,
3271
+ "normalized": true,
3272
+ "rstrip": false,
3273
+ "single_word": false,
3274
+ "special": false
3275
+ },
3276
+ "50665": {
3277
+ "content": "[S@@]",
3278
+ "lstrip": false,
3279
+ "normalized": true,
3280
+ "rstrip": false,
3281
+ "single_word": false,
3282
+ "special": false
3283
+ },
3284
+ "50666": {
3285
+ "content": "[Se+1]",
3286
+ "lstrip": false,
3287
+ "normalized": true,
3288
+ "rstrip": false,
3289
+ "single_word": false,
3290
+ "special": false
3291
+ },
3292
+ "50667": {
3293
+ "content": "[/P]",
3294
+ "lstrip": false,
3295
+ "normalized": true,
3296
+ "rstrip": false,
3297
+ "single_word": false,
3298
+ "special": false
3299
+ },
3300
+ "50668": {
3301
+ "content": "[85SrH2]",
3302
+ "lstrip": false,
3303
+ "normalized": true,
3304
+ "rstrip": false,
3305
+ "single_word": false,
3306
+ "special": false
3307
+ },
3308
+ "50669": {
3309
+ "content": "[I+2]",
3310
+ "lstrip": false,
3311
+ "normalized": true,
3312
+ "rstrip": false,
3313
+ "single_word": false,
3314
+ "special": false
3315
+ },
3316
+ "50670": {
3317
+ "content": "[32P]",
3318
+ "lstrip": false,
3319
+ "normalized": true,
3320
+ "rstrip": false,
3321
+ "single_word": false,
3322
+ "special": false
3323
+ },
3324
+ "50671": {
3325
+ "content": "[/125I]",
3326
+ "lstrip": false,
3327
+ "normalized": true,
3328
+ "rstrip": false,
3329
+ "single_word": false,
3330
+ "special": false
3331
+ },
3332
+ "50672": {
3333
+ "content": "[85Sr+2]",
3334
+ "lstrip": false,
3335
+ "normalized": true,
3336
+ "rstrip": false,
3337
+ "single_word": false,
3338
+ "special": false
3339
+ },
3340
+ "50673": {
3341
+ "content": "[4H]",
3342
+ "lstrip": false,
3343
+ "normalized": true,
3344
+ "rstrip": false,
3345
+ "single_word": false,
3346
+ "special": false
3347
+ },
3348
+ "50674": {
3349
+ "content": "[\\SeH1]",
3350
+ "lstrip": false,
3351
+ "normalized": true,
3352
+ "rstrip": false,
3353
+ "single_word": false,
3354
+ "special": false
3355
+ },
3356
+ "50675": {
3357
+ "content": "[14CH3]",
3358
+ "lstrip": false,
3359
+ "normalized": true,
3360
+ "rstrip": false,
3361
+ "single_word": false,
3362
+ "special": false
3363
+ },
3364
+ "50676": {
3365
+ "content": "[SH1]",
3366
+ "lstrip": false,
3367
+ "normalized": true,
3368
+ "rstrip": false,
3369
+ "single_word": false,
3370
+ "special": false
3371
+ },
3372
+ "50677": {
3373
+ "content": "[124I-1]",
3374
+ "lstrip": false,
3375
+ "normalized": true,
3376
+ "rstrip": false,
3377
+ "single_word": false,
3378
+ "special": false
3379
+ },
3380
+ "50678": {
3381
+ "content": "[=18O]",
3382
+ "lstrip": false,
3383
+ "normalized": true,
3384
+ "rstrip": false,
3385
+ "single_word": false,
3386
+ "special": false
3387
+ },
3388
+ "50679": {
3389
+ "content": "[Zn+1]",
3390
+ "lstrip": false,
3391
+ "normalized": true,
3392
+ "rstrip": false,
3393
+ "single_word": false,
3394
+ "special": false
3395
+ },
3396
+ "50680": {
3397
+ "content": "[N@+1]",
3398
+ "lstrip": false,
3399
+ "normalized": true,
3400
+ "rstrip": false,
3401
+ "single_word": false,
3402
+ "special": false
3403
+ },
3404
+ "50681": {
3405
+ "content": "[125I]",
3406
+ "lstrip": false,
3407
+ "normalized": true,
3408
+ "rstrip": false,
3409
+ "single_word": false,
3410
+ "special": false
3411
+ },
3412
+ "50682": {
3413
+ "content": "[/S+1]",
3414
+ "lstrip": false,
3415
+ "normalized": true,
3416
+ "rstrip": false,
3417
+ "single_word": false,
3418
+ "special": false
3419
+ },
3420
+ "50683": {
3421
+ "content": "[SH1+1]",
3422
+ "lstrip": false,
3423
+ "normalized": true,
3424
+ "rstrip": false,
3425
+ "single_word": false,
3426
+ "special": false
3427
+ },
3428
+ "50684": {
3429
+ "content": "[131I-1]",
3430
+ "lstrip": false,
3431
+ "normalized": true,
3432
+ "rstrip": false,
3433
+ "single_word": false,
3434
+ "special": false
3435
+ },
3436
+ "50685": {
3437
+ "content": "[P@+1]",
3438
+ "lstrip": false,
3439
+ "normalized": true,
3440
+ "rstrip": false,
3441
+ "single_word": false,
3442
+ "special": false
3443
+ },
3444
+ "50686": {
3445
+ "content": "[\\CH1-1]",
3446
+ "lstrip": false,
3447
+ "normalized": true,
3448
+ "rstrip": false,
3449
+ "single_word": false,
3450
+ "special": false
3451
+ },
3452
+ "50687": {
3453
+ "content": "[/11CH3]",
3454
+ "lstrip": false,
3455
+ "normalized": true,
3456
+ "rstrip": false,
3457
+ "single_word": false,
3458
+ "special": false
3459
+ },
3460
+ "50688": {
3461
+ "content": "[131Cs]",
3462
+ "lstrip": false,
3463
+ "normalized": true,
3464
+ "rstrip": false,
3465
+ "single_word": false,
3466
+ "special": false
3467
+ },
3468
+ "50689": {
3469
+ "content": "[131I]",
3470
+ "lstrip": false,
3471
+ "normalized": true,
3472
+ "rstrip": false,
3473
+ "single_word": false,
3474
+ "special": false
3475
+ },
3476
+ "50690": {
3477
+ "content": "[18F-1]",
3478
+ "lstrip": false,
3479
+ "normalized": true,
3480
+ "rstrip": false,
3481
+ "single_word": false,
3482
+ "special": false
3483
+ },
3484
+ "50691": {
3485
+ "content": "[\\Se]",
3486
+ "lstrip": false,
3487
+ "normalized": true,
3488
+ "rstrip": false,
3489
+ "single_word": false,
3490
+ "special": false
3491
+ },
3492
+ "50692": {
3493
+ "content": "[=CH1]",
3494
+ "lstrip": false,
3495
+ "normalized": true,
3496
+ "rstrip": false,
3497
+ "single_word": false,
3498
+ "special": false
3499
+ },
3500
+ "50693": {
3501
+ "content": "[/F]",
3502
+ "lstrip": false,
3503
+ "normalized": true,
3504
+ "rstrip": false,
3505
+ "single_word": false,
3506
+ "special": false
3507
+ },
3508
+ "50694": {
3509
+ "content": "[PH2+1]",
3510
+ "lstrip": false,
3511
+ "normalized": true,
3512
+ "rstrip": false,
3513
+ "single_word": false,
3514
+ "special": false
3515
+ },
3516
+ "50695": {
3517
+ "content": "[TeH1]",
3518
+ "lstrip": false,
3519
+ "normalized": true,
3520
+ "rstrip": false,
3521
+ "single_word": false,
3522
+ "special": false
3523
+ },
3524
+ "50696": {
3525
+ "content": "[Ra]",
3526
+ "lstrip": false,
3527
+ "normalized": true,
3528
+ "rstrip": false,
3529
+ "single_word": false,
3530
+ "special": false
3531
+ },
3532
+ "50697": {
3533
+ "content": "[123I]",
3534
+ "lstrip": false,
3535
+ "normalized": true,
3536
+ "rstrip": false,
3537
+ "single_word": false,
3538
+ "special": false
3539
+ },
3540
+ "50698": {
3541
+ "content": "[13CH2]",
3542
+ "lstrip": false,
3543
+ "normalized": true,
3544
+ "rstrip": false,
3545
+ "single_word": false,
3546
+ "special": false
3547
+ },
3548
+ "50699": {
3549
+ "content": "[Rb+1]",
3550
+ "lstrip": false,
3551
+ "normalized": true,
3552
+ "rstrip": false,
3553
+ "single_word": false,
3554
+ "special": false
3555
+ },
3556
+ "50700": {
3557
+ "content": "[/C-1]",
3558
+ "lstrip": false,
3559
+ "normalized": true,
3560
+ "rstrip": false,
3561
+ "single_word": false,
3562
+ "special": false
3563
+ },
3564
+ "50701": {
3565
+ "content": "[=14C]",
3566
+ "lstrip": false,
3567
+ "normalized": true,
3568
+ "rstrip": false,
3569
+ "single_word": false,
3570
+ "special": false
3571
+ },
3572
+ "50702": {
3573
+ "content": "[BH3-1]",
3574
+ "lstrip": false,
3575
+ "normalized": true,
3576
+ "rstrip": false,
3577
+ "single_word": false,
3578
+ "special": false
3579
+ },
3580
+ "50703": {
3581
+ "content": "[125IH1]",
3582
+ "lstrip": false,
3583
+ "normalized": true,
3584
+ "rstrip": false,
3585
+ "single_word": false,
3586
+ "special": false
3587
+ },
3588
+ "50704": {
3589
+ "content": "[/Se]",
3590
+ "lstrip": false,
3591
+ "normalized": true,
3592
+ "rstrip": false,
3593
+ "single_word": false,
3594
+ "special": false
3595
+ },
3596
+ "50705": {
3597
+ "content": "[75Se]",
3598
+ "lstrip": false,
3599
+ "normalized": true,
3600
+ "rstrip": false,
3601
+ "single_word": false,
3602
+ "special": false
3603
+ },
3604
+ "50706": {
3605
+ "content": "[/14C]",
3606
+ "lstrip": false,
3607
+ "normalized": true,
3608
+ "rstrip": false,
3609
+ "single_word": false,
3610
+ "special": false
3611
+ },
3612
+ "50707": {
3613
+ "content": "[=S@]",
3614
+ "lstrip": false,
3615
+ "normalized": true,
3616
+ "rstrip": false,
3617
+ "single_word": false,
3618
+ "special": false
3619
+ },
3620
+ "50708": {
3621
+ "content": "[\\PH1]",
3622
+ "lstrip": false,
3623
+ "normalized": true,
3624
+ "rstrip": false,
3625
+ "single_word": false,
3626
+ "special": false
3627
+ },
3628
+ "50709": {
3629
+ "content": "[SiH2]",
3630
+ "lstrip": false,
3631
+ "normalized": true,
3632
+ "rstrip": false,
3633
+ "single_word": false,
3634
+ "special": false
3635
+ },
3636
+ "50710": {
3637
+ "content": "[Ra+2]",
3638
+ "lstrip": false,
3639
+ "normalized": true,
3640
+ "rstrip": false,
3641
+ "single_word": false,
3642
+ "special": false
3643
+ },
3644
+ "50711": {
3645
+ "content": "[NaH1]",
3646
+ "lstrip": false,
3647
+ "normalized": true,
3648
+ "rstrip": false,
3649
+ "single_word": false,
3650
+ "special": false
3651
+ },
3652
+ "50712": {
3653
+ "content": "[14C]",
3654
+ "lstrip": false,
3655
+ "normalized": true,
3656
+ "rstrip": false,
3657
+ "single_word": false,
3658
+ "special": false
3659
+ },
3660
+ "50713": {
3661
+ "content": "[76Br]",
3662
+ "lstrip": false,
3663
+ "normalized": true,
3664
+ "rstrip": false,
3665
+ "single_word": false,
3666
+ "special": false
3667
+ },
3668
+ "50714": {
3669
+ "content": "[=14CH1]",
3670
+ "lstrip": false,
3671
+ "normalized": true,
3672
+ "rstrip": false,
3673
+ "single_word": false,
3674
+ "special": false
3675
+ },
3676
+ "50715": {
3677
+ "content": "[223Ra+2]",
3678
+ "lstrip": false,
3679
+ "normalized": true,
3680
+ "rstrip": false,
3681
+ "single_word": false,
3682
+ "special": false
3683
+ },
3684
+ "50716": {
3685
+ "content": "[/CH1-1]",
3686
+ "lstrip": false,
3687
+ "normalized": true,
3688
+ "rstrip": false,
3689
+ "single_word": false,
3690
+ "special": false
3691
+ },
3692
+ "50717": {
3693
+ "content": "[As+1]",
3694
+ "lstrip": false,
3695
+ "normalized": true,
3696
+ "rstrip": false,
3697
+ "single_word": false,
3698
+ "special": false
3699
+ },
3700
+ "50718": {
3701
+ "content": "[\\125I]",
3702
+ "lstrip": false,
3703
+ "normalized": true,
3704
+ "rstrip": false,
3705
+ "single_word": false,
3706
+ "special": false
3707
+ },
3708
+ "50719": {
3709
+ "content": "[TeH2]",
3710
+ "lstrip": false,
3711
+ "normalized": true,
3712
+ "rstrip": false,
3713
+ "single_word": false,
3714
+ "special": false
3715
+ },
3716
+ "50720": {
3717
+ "content": "[\\F]",
3718
+ "lstrip": false,
3719
+ "normalized": true,
3720
+ "rstrip": false,
3721
+ "single_word": false,
3722
+ "special": false
3723
+ },
3724
+ "50721": {
3725
+ "content": "[14C@]",
3726
+ "lstrip": false,
3727
+ "normalized": true,
3728
+ "rstrip": false,
3729
+ "single_word": false,
3730
+ "special": false
3731
+ },
3732
+ "50722": {
3733
+ "content": "[\\Te]",
3734
+ "lstrip": false,
3735
+ "normalized": true,
3736
+ "rstrip": false,
3737
+ "single_word": false,
3738
+ "special": false
3739
+ },
3740
+ "50723": {
3741
+ "content": "[89Sr+2]",
3742
+ "lstrip": false,
3743
+ "normalized": true,
3744
+ "rstrip": false,
3745
+ "single_word": false,
3746
+ "special": false
3747
+ },
3748
+ "50724": {
3749
+ "content": "[#11C-1]",
3750
+ "lstrip": false,
3751
+ "normalized": true,
3752
+ "rstrip": false,
3753
+ "single_word": false,
3754
+ "special": false
3755
+ },
3756
+ "50725": {
3757
+ "content": "[mask]",
3758
+ "lstrip": false,
3759
+ "normalized": false,
3760
+ "rstrip": false,
3761
+ "single_word": false,
3762
+ "special": true
3763
+ },
3764
+ "50726": {
3765
+ "content": "[SEP]",
3766
+ "lstrip": false,
3767
+ "normalized": false,
3768
+ "rstrip": false,
3769
+ "single_word": false,
3770
+ "special": true
3771
+ }
3772
+ },
3773
+ "bos_token": "<|endoftext|>",
3774
+ "clean_up_tokenization_spaces": false,
3775
+ "eos_token": "<|endoftext|>",
3776
+ "extra_special_tokens": {},
3777
+ "mask_token": "[mask]",
3778
+ "model_max_length": 1024,
3779
+ "pad_token": "<|endoftext|>",
3780
+ "sep_token": "[SEP]",
3781
+ "tokenizer_class": "GPT2Tokenizer",
3782
+ "unk_token": "<|endoftext|>"
3783
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590730e8df4f2ae9bc79071d8aeb9e86f9e55dd5a08030991d65b12c3b2d54bf
3
+ size 6968
vocab.json ADDED
The diff for this file is too large to render. See raw diff