Spaces:
Sleeping
Sleeping
Upload 7 files
Browse files- .gitattributes +1 -0
- CHEMBL2039_bioactives.csv +0 -0
- GPT_ZN305_50epochs.weights.h5 +3 -0
- ZN305K_smiles.csv +3 -0
- gen_smiles_CHEMBL2039.csv +25 -0
- layer_store_GPT_ZN305_50epochs.txt +5 -0
- vocab.txt +591 -0
- vocab_305K.txt +100 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* 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
|
|
|
|
|
|
| 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
|
| 36 |
+
ZN305K_smiles.csv filter=lfs diff=lfs merge=lfs -text
|
CHEMBL2039_bioactives.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
GPT_ZN305_50epochs.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96aa16efbb751603eab96a48740db7747c42f14c4659610e1cf88c3df029b36e
|
| 3 |
+
size 29668344
|
ZN305K_smiles.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b761a00a284586ce7727e669fa1c8bab969fc524f5b990cd45cf0d5da73fa0
|
| 3 |
+
size 15686068
|
gen_smiles_CHEMBL2039.csv
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
SMILES
|
| 2 |
+
NC1CCC(N[C@@H]2C[C@@H]2c2ccc(-c3ccc(C(F)(F)F)cc3)nc2)CC1
|
| 3 |
+
C#CCN(C)[C@H](C)Cc1ccccc1
|
| 4 |
+
O=C1CCc2ccc(OCc3cccc(C(F)(F)F)c3)cc2N1
|
| 5 |
+
O=C1/C(=C/c2ccc(Cl)cc2)Cc2cc(O)ccc21
|
| 6 |
+
C#CCN(C)[C@@H](C)Cc1ccc(Cl)cc1
|
| 7 |
+
C#CCN(C)[C@H](C)Cc1cc(O)ccc1OC
|
| 8 |
+
C#CCN(C)c1cc2ccc(OCc3cccc(Cl)c3)cc2[nH]1
|
| 9 |
+
C#CCN(C)CCCOc1ccnc(Cl)c1Cl
|
| 10 |
+
C#CCN(C)CCCOc1ccc(Cl)cc1Cl
|
| 11 |
+
C#CCN(C)C1CCN(Cc2ccc(-c3ccc(C)cc3)cc2)CC1
|
| 12 |
+
C#CCNC1CCc2c(OCc3cn(Cc4ccc(OC)cc4)nn3)cccc21
|
| 13 |
+
NC1CCC(N[C@H]2C[C@@H]2c2ccc3ccccc3c2)CC1
|
| 14 |
+
C#CCN(C)[C@H](C)Cc1ccc(OCCCCCCCN[C@H]2C[C@@H]2c2ccccc2)cc1
|
| 15 |
+
C#CCN(CCCCCOC(=O)Cc1cc2ccccc2oc1=O)Cc1ccccc1OC
|
| 16 |
+
O=C1CCc2ccc(OCCCCN3COCC3)cc2C1
|
| 17 |
+
Fc1ccc(-c2cc([C@H]3CC[C@@H]3NC3CCC(N)CC3)cs2)cc1
|
| 18 |
+
O=C1/C(=C/c2ccc(O)cc2)Cc2c(O)cccc21
|
| 19 |
+
C#CCN(C)Cc1nc2ccc(OCCCc3cn[nH]c3)cCCc2n1C
|
| 20 |
+
O=C(Nc1ccccc1)c1coc2ccc(O)cc2c1=O
|
| 21 |
+
C#CCN(C)[C@H](C)Cc1ccc3ccc(=O)oc3c1
|
| 22 |
+
C#CCN(C)CCCOc1cccc(Cl)c1Cl
|
| 23 |
+
C#CCN(C)[C@H](C)Cc1ccc(NCc2ccccc2)cc1
|
| 24 |
+
C#CCN(C)CCCOc1ccncc1
|
| 25 |
+
C#CCN1CCC(/C=C/c2cc(OC)cc(OC)c2)CC1
|
layer_store_GPT_ZN305_50epochs.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
input_layer_original
|
| 2 |
+
token_and_position_embedding_original
|
| 3 |
+
transformer_block_original
|
| 4 |
+
transformer_block_1_original
|
| 5 |
+
dense_4_original
|
vocab.txt
ADDED
|
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[PAD]
|
| 2 |
+
[unused1]
|
| 3 |
+
[unused2]
|
| 4 |
+
[unused3]
|
| 5 |
+
[unused4]
|
| 6 |
+
[unused5]
|
| 7 |
+
[unused6]
|
| 8 |
+
[unused7]
|
| 9 |
+
[unused8]
|
| 10 |
+
[unused9]
|
| 11 |
+
[unused10]
|
| 12 |
+
[UNK]
|
| 13 |
+
[CLS]
|
| 14 |
+
[SEP]
|
| 15 |
+
[MASK]
|
| 16 |
+
c
|
| 17 |
+
C
|
| 18 |
+
(
|
| 19 |
+
)
|
| 20 |
+
O
|
| 21 |
+
1
|
| 22 |
+
2
|
| 23 |
+
=
|
| 24 |
+
N
|
| 25 |
+
.
|
| 26 |
+
n
|
| 27 |
+
3
|
| 28 |
+
F
|
| 29 |
+
Cl
|
| 30 |
+
>>
|
| 31 |
+
~
|
| 32 |
+
-
|
| 33 |
+
4
|
| 34 |
+
[C@H]
|
| 35 |
+
S
|
| 36 |
+
[C@@H]
|
| 37 |
+
[O-]
|
| 38 |
+
Br
|
| 39 |
+
#
|
| 40 |
+
/
|
| 41 |
+
[nH]
|
| 42 |
+
[N+]
|
| 43 |
+
s
|
| 44 |
+
5
|
| 45 |
+
o
|
| 46 |
+
P
|
| 47 |
+
[Na+]
|
| 48 |
+
[Si]
|
| 49 |
+
I
|
| 50 |
+
[Na]
|
| 51 |
+
[Pd]
|
| 52 |
+
[K+]
|
| 53 |
+
[K]
|
| 54 |
+
[P]
|
| 55 |
+
B
|
| 56 |
+
[C@]
|
| 57 |
+
[C@@]
|
| 58 |
+
[Cl-]
|
| 59 |
+
6
|
| 60 |
+
[OH-]
|
| 61 |
+
\
|
| 62 |
+
[N-]
|
| 63 |
+
[Li]
|
| 64 |
+
[H]
|
| 65 |
+
[2H]
|
| 66 |
+
[NH4+]
|
| 67 |
+
[c-]
|
| 68 |
+
[P-]
|
| 69 |
+
[Cs+]
|
| 70 |
+
[Li+]
|
| 71 |
+
[Cs]
|
| 72 |
+
[NaH]
|
| 73 |
+
[H-]
|
| 74 |
+
[O+]
|
| 75 |
+
[BH4-]
|
| 76 |
+
[Cu]
|
| 77 |
+
7
|
| 78 |
+
[Mg]
|
| 79 |
+
[Fe+2]
|
| 80 |
+
[n+]
|
| 81 |
+
[Sn]
|
| 82 |
+
[BH-]
|
| 83 |
+
[Pd+2]
|
| 84 |
+
[CH]
|
| 85 |
+
[I-]
|
| 86 |
+
[Br-]
|
| 87 |
+
[C-]
|
| 88 |
+
[Zn]
|
| 89 |
+
[B-]
|
| 90 |
+
[F-]
|
| 91 |
+
[Al]
|
| 92 |
+
[P+]
|
| 93 |
+
[BH3-]
|
| 94 |
+
[Fe]
|
| 95 |
+
[C]
|
| 96 |
+
[AlH4]
|
| 97 |
+
[Ni]
|
| 98 |
+
[SiH]
|
| 99 |
+
8
|
| 100 |
+
[Cu+2]
|
| 101 |
+
[Mn]
|
| 102 |
+
[AlH]
|
| 103 |
+
[nH+]
|
| 104 |
+
[AlH4-]
|
| 105 |
+
[O-2]
|
| 106 |
+
[Cr]
|
| 107 |
+
[Mg+2]
|
| 108 |
+
[NH3+]
|
| 109 |
+
[S@]
|
| 110 |
+
[Pt]
|
| 111 |
+
[Al+3]
|
| 112 |
+
[S@@]
|
| 113 |
+
[S-]
|
| 114 |
+
[Ti]
|
| 115 |
+
[Zn+2]
|
| 116 |
+
[PH]
|
| 117 |
+
[NH2+]
|
| 118 |
+
[Ru]
|
| 119 |
+
[Ag+]
|
| 120 |
+
[S+]
|
| 121 |
+
[I+3]
|
| 122 |
+
[NH+]
|
| 123 |
+
[Ca+2]
|
| 124 |
+
[Ag]
|
| 125 |
+
9
|
| 126 |
+
[Os]
|
| 127 |
+
[Se]
|
| 128 |
+
[SiH2]
|
| 129 |
+
[Ca]
|
| 130 |
+
[Ti+4]
|
| 131 |
+
[Ac]
|
| 132 |
+
[Cu+]
|
| 133 |
+
[S]
|
| 134 |
+
[Rh]
|
| 135 |
+
[Cl+3]
|
| 136 |
+
[cH-]
|
| 137 |
+
[Zn+]
|
| 138 |
+
[O]
|
| 139 |
+
[Cl+]
|
| 140 |
+
[SH]
|
| 141 |
+
[H+]
|
| 142 |
+
[Pd+]
|
| 143 |
+
[se]
|
| 144 |
+
[PH+]
|
| 145 |
+
[I]
|
| 146 |
+
[Pt+2]
|
| 147 |
+
[C+]
|
| 148 |
+
[Mg+]
|
| 149 |
+
[Hg]
|
| 150 |
+
[W]
|
| 151 |
+
[SnH]
|
| 152 |
+
[SiH3]
|
| 153 |
+
[Fe+3]
|
| 154 |
+
[NH]
|
| 155 |
+
[Mo]
|
| 156 |
+
[CH2+]
|
| 157 |
+
%10
|
| 158 |
+
[CH2-]
|
| 159 |
+
[CH2]
|
| 160 |
+
[n-]
|
| 161 |
+
[Ce+4]
|
| 162 |
+
[NH-]
|
| 163 |
+
[Co]
|
| 164 |
+
[I+]
|
| 165 |
+
[PH2]
|
| 166 |
+
[Pt+4]
|
| 167 |
+
[Ce]
|
| 168 |
+
[B]
|
| 169 |
+
[Sn+2]
|
| 170 |
+
[Ba+2]
|
| 171 |
+
%11
|
| 172 |
+
[Fe-3]
|
| 173 |
+
[18F]
|
| 174 |
+
[SH-]
|
| 175 |
+
[Pb+2]
|
| 176 |
+
[Os-2]
|
| 177 |
+
[Zr+4]
|
| 178 |
+
[N]
|
| 179 |
+
[Ir]
|
| 180 |
+
[Bi]
|
| 181 |
+
[Ni+2]
|
| 182 |
+
[P@]
|
| 183 |
+
[Co+2]
|
| 184 |
+
[s+]
|
| 185 |
+
[As]
|
| 186 |
+
[P+3]
|
| 187 |
+
[Hg+2]
|
| 188 |
+
[Yb+3]
|
| 189 |
+
[CH-]
|
| 190 |
+
[Zr+2]
|
| 191 |
+
[Mn+2]
|
| 192 |
+
[CH+]
|
| 193 |
+
[In]
|
| 194 |
+
[KH]
|
| 195 |
+
[Ce+3]
|
| 196 |
+
[Zr]
|
| 197 |
+
[AlH2-]
|
| 198 |
+
[OH2+]
|
| 199 |
+
[Ti+3]
|
| 200 |
+
[Rh+2]
|
| 201 |
+
[Sb]
|
| 202 |
+
[S-2]
|
| 203 |
+
%12
|
| 204 |
+
[P@@]
|
| 205 |
+
[Si@H]
|
| 206 |
+
[Mn+4]
|
| 207 |
+
p
|
| 208 |
+
[Ba]
|
| 209 |
+
[NH2-]
|
| 210 |
+
[Ge]
|
| 211 |
+
[Pb+4]
|
| 212 |
+
[Cr+3]
|
| 213 |
+
[Au]
|
| 214 |
+
[LiH]
|
| 215 |
+
[Sc+3]
|
| 216 |
+
[o+]
|
| 217 |
+
[Rh-3]
|
| 218 |
+
%13
|
| 219 |
+
[Br]
|
| 220 |
+
[Sb-]
|
| 221 |
+
[S@+]
|
| 222 |
+
[I+2]
|
| 223 |
+
[Ar]
|
| 224 |
+
[V]
|
| 225 |
+
[Cu-]
|
| 226 |
+
[Al-]
|
| 227 |
+
[Te]
|
| 228 |
+
[13c]
|
| 229 |
+
[13C]
|
| 230 |
+
[Cl]
|
| 231 |
+
[PH4+]
|
| 232 |
+
[SiH4]
|
| 233 |
+
[te]
|
| 234 |
+
[CH3-]
|
| 235 |
+
[S@@+]
|
| 236 |
+
[Rh+3]
|
| 237 |
+
[SH+]
|
| 238 |
+
[Bi+3]
|
| 239 |
+
[Br+2]
|
| 240 |
+
[La]
|
| 241 |
+
[La+3]
|
| 242 |
+
[Pt-2]
|
| 243 |
+
[N@@]
|
| 244 |
+
[PH3+]
|
| 245 |
+
[N@]
|
| 246 |
+
[Si+4]
|
| 247 |
+
[Sr+2]
|
| 248 |
+
[Al+]
|
| 249 |
+
[Pb]
|
| 250 |
+
[SeH]
|
| 251 |
+
[Si-]
|
| 252 |
+
[V+5]
|
| 253 |
+
[Y+3]
|
| 254 |
+
[Re]
|
| 255 |
+
[Ru+]
|
| 256 |
+
[Sm]
|
| 257 |
+
*
|
| 258 |
+
[3H]
|
| 259 |
+
[NH2]
|
| 260 |
+
[Ag-]
|
| 261 |
+
[13CH3]
|
| 262 |
+
[OH+]
|
| 263 |
+
[Ru+3]
|
| 264 |
+
[OH]
|
| 265 |
+
[Gd+3]
|
| 266 |
+
[13CH2]
|
| 267 |
+
[In+3]
|
| 268 |
+
[Si@@]
|
| 269 |
+
[Si@]
|
| 270 |
+
[Ti+2]
|
| 271 |
+
[Sn+]
|
| 272 |
+
[Cl+2]
|
| 273 |
+
[AlH-]
|
| 274 |
+
[Pd-2]
|
| 275 |
+
[SnH3]
|
| 276 |
+
[B+3]
|
| 277 |
+
[Cu-2]
|
| 278 |
+
[Nd+3]
|
| 279 |
+
[Pb+3]
|
| 280 |
+
[13cH]
|
| 281 |
+
[Fe-4]
|
| 282 |
+
[Ga]
|
| 283 |
+
[Sn+4]
|
| 284 |
+
[Hg+]
|
| 285 |
+
[11CH3]
|
| 286 |
+
[Hf]
|
| 287 |
+
[Pr]
|
| 288 |
+
[Y]
|
| 289 |
+
[S+2]
|
| 290 |
+
[Cd]
|
| 291 |
+
[Cr+6]
|
| 292 |
+
[Zr+3]
|
| 293 |
+
[Rh+]
|
| 294 |
+
[CH3]
|
| 295 |
+
[N-3]
|
| 296 |
+
[Hf+2]
|
| 297 |
+
[Th]
|
| 298 |
+
[Sb+3]
|
| 299 |
+
%14
|
| 300 |
+
[Cr+2]
|
| 301 |
+
[Ru+2]
|
| 302 |
+
[Hf+4]
|
| 303 |
+
[14C]
|
| 304 |
+
[Ta]
|
| 305 |
+
[Tl+]
|
| 306 |
+
[B+]
|
| 307 |
+
[Os+4]
|
| 308 |
+
[PdH2]
|
| 309 |
+
[Pd-]
|
| 310 |
+
[Cd+2]
|
| 311 |
+
[Co+3]
|
| 312 |
+
[S+4]
|
| 313 |
+
[Nb+5]
|
| 314 |
+
[123I]
|
| 315 |
+
[c+]
|
| 316 |
+
[Rb+]
|
| 317 |
+
[V+2]
|
| 318 |
+
[CH3+]
|
| 319 |
+
[Ag+2]
|
| 320 |
+
[cH+]
|
| 321 |
+
[Mn+3]
|
| 322 |
+
[Se-]
|
| 323 |
+
[As-]
|
| 324 |
+
[Eu+3]
|
| 325 |
+
[SH2]
|
| 326 |
+
[Sm+3]
|
| 327 |
+
[IH+]
|
| 328 |
+
%15
|
| 329 |
+
[OH3+]
|
| 330 |
+
[PH3]
|
| 331 |
+
[IH2+]
|
| 332 |
+
[SH2+]
|
| 333 |
+
[Ir+3]
|
| 334 |
+
[AlH3]
|
| 335 |
+
[Sc]
|
| 336 |
+
[Yb]
|
| 337 |
+
[15NH2]
|
| 338 |
+
[Lu]
|
| 339 |
+
[sH+]
|
| 340 |
+
[Gd]
|
| 341 |
+
[18F-]
|
| 342 |
+
[SH3+]
|
| 343 |
+
[SnH4]
|
| 344 |
+
[TeH]
|
| 345 |
+
[Si@@H]
|
| 346 |
+
[Ga+3]
|
| 347 |
+
[CaH2]
|
| 348 |
+
[Tl]
|
| 349 |
+
[Ta+5]
|
| 350 |
+
[GeH]
|
| 351 |
+
[Br+]
|
| 352 |
+
[Sr]
|
| 353 |
+
[Tl+3]
|
| 354 |
+
[Sm+2]
|
| 355 |
+
[PH5]
|
| 356 |
+
%16
|
| 357 |
+
[N@@+]
|
| 358 |
+
[Au+3]
|
| 359 |
+
[C-4]
|
| 360 |
+
[Nd]
|
| 361 |
+
[Ti+]
|
| 362 |
+
[IH]
|
| 363 |
+
[N@+]
|
| 364 |
+
[125I]
|
| 365 |
+
[Eu]
|
| 366 |
+
[Sn+3]
|
| 367 |
+
[Nb]
|
| 368 |
+
[Er+3]
|
| 369 |
+
[123I-]
|
| 370 |
+
[14c]
|
| 371 |
+
%17
|
| 372 |
+
[SnH2]
|
| 373 |
+
[YH]
|
| 374 |
+
[Sb+5]
|
| 375 |
+
[Pr+3]
|
| 376 |
+
[Ir+]
|
| 377 |
+
[N+3]
|
| 378 |
+
[AlH2]
|
| 379 |
+
[19F]
|
| 380 |
+
%18
|
| 381 |
+
[Tb]
|
| 382 |
+
[14CH]
|
| 383 |
+
[Mo+4]
|
| 384 |
+
[Si+]
|
| 385 |
+
[BH]
|
| 386 |
+
[Be]
|
| 387 |
+
[Rb]
|
| 388 |
+
[pH]
|
| 389 |
+
%19
|
| 390 |
+
%20
|
| 391 |
+
[Xe]
|
| 392 |
+
[Ir-]
|
| 393 |
+
[Be+2]
|
| 394 |
+
[C+4]
|
| 395 |
+
[RuH2]
|
| 396 |
+
[15NH]
|
| 397 |
+
[U+2]
|
| 398 |
+
[Au-]
|
| 399 |
+
%21
|
| 400 |
+
%22
|
| 401 |
+
[Au+]
|
| 402 |
+
[15n]
|
| 403 |
+
[Al+2]
|
| 404 |
+
[Tb+3]
|
| 405 |
+
[15N]
|
| 406 |
+
[V+3]
|
| 407 |
+
[W+6]
|
| 408 |
+
[14CH3]
|
| 409 |
+
[Cr+4]
|
| 410 |
+
[ClH+]
|
| 411 |
+
b
|
| 412 |
+
[Ti+6]
|
| 413 |
+
[Nd+]
|
| 414 |
+
[Zr+]
|
| 415 |
+
[PH2+]
|
| 416 |
+
[Fm]
|
| 417 |
+
[N@H+]
|
| 418 |
+
[RuH]
|
| 419 |
+
[Dy+3]
|
| 420 |
+
%23
|
| 421 |
+
[Hf+3]
|
| 422 |
+
[W+4]
|
| 423 |
+
[11C]
|
| 424 |
+
[13CH]
|
| 425 |
+
[Er]
|
| 426 |
+
[124I]
|
| 427 |
+
[LaH]
|
| 428 |
+
[F]
|
| 429 |
+
[siH]
|
| 430 |
+
[Ga+]
|
| 431 |
+
[Cm]
|
| 432 |
+
[GeH3]
|
| 433 |
+
[IH-]
|
| 434 |
+
[U+6]
|
| 435 |
+
[SeH+]
|
| 436 |
+
[32P]
|
| 437 |
+
[SeH-]
|
| 438 |
+
[Pt-]
|
| 439 |
+
[Ir+2]
|
| 440 |
+
[se+]
|
| 441 |
+
[U]
|
| 442 |
+
[F+]
|
| 443 |
+
[BH2]
|
| 444 |
+
[As+]
|
| 445 |
+
[Cf]
|
| 446 |
+
[ClH2+]
|
| 447 |
+
[Ni+]
|
| 448 |
+
[TeH3]
|
| 449 |
+
[SbH2]
|
| 450 |
+
[Ag+3]
|
| 451 |
+
%24
|
| 452 |
+
[18O]
|
| 453 |
+
[PH4]
|
| 454 |
+
[Os+2]
|
| 455 |
+
[Na-]
|
| 456 |
+
[Sb+2]
|
| 457 |
+
[V+4]
|
| 458 |
+
[Ho+3]
|
| 459 |
+
[68Ga]
|
| 460 |
+
[PH-]
|
| 461 |
+
[Bi+2]
|
| 462 |
+
[Ce+2]
|
| 463 |
+
[Pd+3]
|
| 464 |
+
[99Tc]
|
| 465 |
+
[13C@@H]
|
| 466 |
+
[Fe+6]
|
| 467 |
+
[c]
|
| 468 |
+
[GeH2]
|
| 469 |
+
[10B]
|
| 470 |
+
[Cu+3]
|
| 471 |
+
[Mo+2]
|
| 472 |
+
[Cr+]
|
| 473 |
+
[Pd+4]
|
| 474 |
+
[Dy]
|
| 475 |
+
[AsH]
|
| 476 |
+
[Ba+]
|
| 477 |
+
[SeH2]
|
| 478 |
+
[In+]
|
| 479 |
+
[TeH2]
|
| 480 |
+
[BrH+]
|
| 481 |
+
[14cH]
|
| 482 |
+
[W+]
|
| 483 |
+
[13C@H]
|
| 484 |
+
[AsH2]
|
| 485 |
+
[In+2]
|
| 486 |
+
[N+2]
|
| 487 |
+
[N@@H+]
|
| 488 |
+
[SbH]
|
| 489 |
+
[60Co]
|
| 490 |
+
[AsH4+]
|
| 491 |
+
[AsH3]
|
| 492 |
+
[18OH]
|
| 493 |
+
[Ru-2]
|
| 494 |
+
[Na-2]
|
| 495 |
+
[CuH2]
|
| 496 |
+
[31P]
|
| 497 |
+
[Ti+5]
|
| 498 |
+
[35S]
|
| 499 |
+
[P@@H]
|
| 500 |
+
[ArH]
|
| 501 |
+
[Co+]
|
| 502 |
+
[Zr-2]
|
| 503 |
+
[BH2-]
|
| 504 |
+
[131I]
|
| 505 |
+
[SH5]
|
| 506 |
+
[VH]
|
| 507 |
+
[B+2]
|
| 508 |
+
[Yb+2]
|
| 509 |
+
[14C@H]
|
| 510 |
+
[211At]
|
| 511 |
+
[NH3+2]
|
| 512 |
+
[IrH]
|
| 513 |
+
[IrH2]
|
| 514 |
+
[Rh-]
|
| 515 |
+
[Cr-]
|
| 516 |
+
[Sb+]
|
| 517 |
+
[Ni+3]
|
| 518 |
+
[TaH3]
|
| 519 |
+
[Tl+2]
|
| 520 |
+
[64Cu]
|
| 521 |
+
[Tc]
|
| 522 |
+
[Cd+]
|
| 523 |
+
[1H]
|
| 524 |
+
[15nH]
|
| 525 |
+
[AlH2+]
|
| 526 |
+
[FH+2]
|
| 527 |
+
[BiH3]
|
| 528 |
+
[Ru-]
|
| 529 |
+
[Mo+6]
|
| 530 |
+
[AsH+]
|
| 531 |
+
[BaH2]
|
| 532 |
+
[BaH]
|
| 533 |
+
[Fe+4]
|
| 534 |
+
[229Th]
|
| 535 |
+
[Th+4]
|
| 536 |
+
[As+3]
|
| 537 |
+
[NH+3]
|
| 538 |
+
[P@H]
|
| 539 |
+
[Li-]
|
| 540 |
+
[7NaH]
|
| 541 |
+
[Bi+]
|
| 542 |
+
[PtH+2]
|
| 543 |
+
[p-]
|
| 544 |
+
[Re+5]
|
| 545 |
+
[NiH]
|
| 546 |
+
[Ni-]
|
| 547 |
+
[Xe+]
|
| 548 |
+
[Ca+]
|
| 549 |
+
[11c]
|
| 550 |
+
[Rh+4]
|
| 551 |
+
[AcH]
|
| 552 |
+
[HeH]
|
| 553 |
+
[Sc+2]
|
| 554 |
+
[Mn+]
|
| 555 |
+
[UH]
|
| 556 |
+
[14CH2]
|
| 557 |
+
[SiH4+]
|
| 558 |
+
[18OH2]
|
| 559 |
+
[Ac-]
|
| 560 |
+
[Re+4]
|
| 561 |
+
[118Sn]
|
| 562 |
+
[153Sm]
|
| 563 |
+
[P+2]
|
| 564 |
+
[9CH]
|
| 565 |
+
[9CH3]
|
| 566 |
+
[Y-]
|
| 567 |
+
[NiH2]
|
| 568 |
+
[Si+2]
|
| 569 |
+
[Mn+6]
|
| 570 |
+
[ZrH2]
|
| 571 |
+
[C-2]
|
| 572 |
+
[Bi+5]
|
| 573 |
+
[24NaH]
|
| 574 |
+
[Fr]
|
| 575 |
+
[15CH]
|
| 576 |
+
[Se+]
|
| 577 |
+
[At]
|
| 578 |
+
[P-3]
|
| 579 |
+
[124I-]
|
| 580 |
+
[CuH2-]
|
| 581 |
+
[Nb+4]
|
| 582 |
+
[Nb+3]
|
| 583 |
+
[MgH]
|
| 584 |
+
[Ir+4]
|
| 585 |
+
[67Ga+3]
|
| 586 |
+
[67Ga]
|
| 587 |
+
[13N]
|
| 588 |
+
[15OH2]
|
| 589 |
+
[2NH]
|
| 590 |
+
[Ho]
|
| 591 |
+
[Cn]
|
vocab_305K.txt
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[PAD]
|
| 2 |
+
[unused]
|
| 3 |
+
[CLS]
|
| 4 |
+
[SEP]
|
| 5 |
+
c
|
| 6 |
+
C
|
| 7 |
+
(
|
| 8 |
+
)
|
| 9 |
+
O
|
| 10 |
+
1
|
| 11 |
+
2
|
| 12 |
+
=
|
| 13 |
+
N
|
| 14 |
+
n
|
| 15 |
+
3
|
| 16 |
+
F
|
| 17 |
+
Cl
|
| 18 |
+
-
|
| 19 |
+
4
|
| 20 |
+
[C@H]
|
| 21 |
+
S
|
| 22 |
+
[C@@H]
|
| 23 |
+
[O-]
|
| 24 |
+
Br
|
| 25 |
+
#
|
| 26 |
+
/
|
| 27 |
+
[nH]
|
| 28 |
+
[N+]
|
| 29 |
+
s
|
| 30 |
+
5
|
| 31 |
+
o
|
| 32 |
+
P
|
| 33 |
+
[Si]
|
| 34 |
+
I
|
| 35 |
+
B
|
| 36 |
+
[C@]
|
| 37 |
+
[C@@]
|
| 38 |
+
6
|
| 39 |
+
\
|
| 40 |
+
[N-]
|
| 41 |
+
[c-]
|
| 42 |
+
[O+]
|
| 43 |
+
7
|
| 44 |
+
[n+]
|
| 45 |
+
[Sn]
|
| 46 |
+
[CH]
|
| 47 |
+
[C-]
|
| 48 |
+
[B-]
|
| 49 |
+
[P+]
|
| 50 |
+
[C]
|
| 51 |
+
8
|
| 52 |
+
[nH+]
|
| 53 |
+
[NH3+]
|
| 54 |
+
[S@]
|
| 55 |
+
[S@@]
|
| 56 |
+
[S-]
|
| 57 |
+
[PH]
|
| 58 |
+
[NH2+]
|
| 59 |
+
[S+]
|
| 60 |
+
[NH+]
|
| 61 |
+
9
|
| 62 |
+
[cH-]
|
| 63 |
+
[O]
|
| 64 |
+
[SH]
|
| 65 |
+
[PH+]
|
| 66 |
+
[C+]
|
| 67 |
+
[SnH]
|
| 68 |
+
%10
|
| 69 |
+
[CH2-]
|
| 70 |
+
[n-]
|
| 71 |
+
[NH-]
|
| 72 |
+
[PH2]
|
| 73 |
+
%11
|
| 74 |
+
[N]
|
| 75 |
+
[P@]
|
| 76 |
+
[s+]
|
| 77 |
+
[CH-]
|
| 78 |
+
[CH+]
|
| 79 |
+
%12
|
| 80 |
+
[P@@]
|
| 81 |
+
[o+]
|
| 82 |
+
%13
|
| 83 |
+
[S@+]
|
| 84 |
+
[S@@+]
|
| 85 |
+
[SH+]
|
| 86 |
+
[OH+]
|
| 87 |
+
%14
|
| 88 |
+
%15
|
| 89 |
+
%16
|
| 90 |
+
[N@@+]
|
| 91 |
+
[N@+]
|
| 92 |
+
[125I]
|
| 93 |
+
%17
|
| 94 |
+
%18
|
| 95 |
+
%19
|
| 96 |
+
%20
|
| 97 |
+
%21
|
| 98 |
+
[P@@H]
|
| 99 |
+
[131I]
|
| 100 |
+
[P@H]
|