Hugging Face's logo

hicai-zju
/
InstructBioMol-instruct

PyTorch
llama
Model card Files
xet
Community
1
XiangZH commited on
Commit
a28c395
·
verified ·
1 Parent(s): 9ad6c3a

add ckpt

Browse files
Files changed (7) hide show
  1. README.md +71 -3
  2. added_tokens.json +987 -0
  3. config.json +26 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +35 -0
README.md CHANGED
@@ -1,3 +1,71 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+ <div align="center">
6
+
7
+ <h3>InstructBioMol: A Multimodal LLM for Biomolecule Understanding and Design</h3>
8
+
9
+ <p align="center">
10
+ <a href="https://arxiv.org/abs/2410.07919">Paper</a> •
11
+ <a href="https://github.com/HICAI-ZJU/InstructBioMol">Project</a> •
12
+ <a href="#quickstart">Quickstart</a> •
13
+ <a href="#citation">Citation</a>
14
+ </p>
15
+ </div>
16
+
17
+ ### Model Description
18
+
19
+ InstructBioMol is a multimodal large language model that bridges natural language with biomolecules (proteins and small molecules). It achieves any-to-any alignment between natural language, molecules, and proteins through comprehensive instruction tuning.
20
+
21
+ *For detailed information, please refer to our [paper](https://arxiv.org/abs/2410.07919) and [code repository](https://github.com/HICAI-ZJU/InstructBioMol).*
22
+ ### Released Variants
23
+
24
+ | Model Name | Stage | Multimodal| Description |
25
+ |------------|-----------| -------| -------|
26
+ | [InstructBioMol-base](https://huggingface.co/hicai-zju/InstructBioMol-base) | Pretraining | ❎| Continual pretrained model on molecular sequences, protein sequences, and scientific literature. |
27
+ | [InstructBioMol-instruct-stage1](https://huggingface.co/hicai-zju/InstructBioMol-instruct-stage1) | Instruction tuning (stage 1) | ✅ | Stage1 instruction-tuned model with biomolecular multimodal processing capabilities. (e.g., 3D molecules/proteins) |
28
+ | [InstructBioMol-instruct](https://huggingface.co/hicai-zju/InstructBioMol-instruct) (*This Model*) | Instruction tuning (stage 1 and 2) | ✅| Fully instruction-tuned model (stage1 & stage2) with biomolecular multimodal processing capabilities (e.g., 3D molecules/proteins) |
29
+
30
+ ### Training Details
31
+
32
+ **Base Architecture**: InstructBioMol-instruct-stage1
33
+
34
+ **Training Data**:
35
+
36
+ ​1. Molecule - Natural Language Alignment:
37
+ - 52K data from chebi
38
+
39
+ ​2. Protein - Natural Langauge Alignment:
40
+ - 2 million data from UniProt (Swiss-Prot)
41
+
42
+ ​3. Molecule - Protein Alignment:
43
+ - 1 million data from BindingDB and Rhea
44
+
45
+
46
+ **Training Objective**: Instruction tuning
47
+
48
+
49
+ ### Citation
50
+
51
+ ```bibtex
52
+ @article{DBLP:journals/corr/abs-2410-07919,
53
+ author = {Xiang Zhuang and
54
+ Keyan Ding and
55
+ Tianwen Lyu and
56
+ Yinuo Jiang and
57
+ Xiaotong Li and
58
+ Zhuoyi Xiang and
59
+ Zeyuan Wang and
60
+ Ming Qin and
61
+ Kehua Feng and
62
+ Jike Wang and
63
+ Qiang Zhang and
64
+ Huajun Chen},
65
+ title = {InstructBioMol: Advancing Biomolecule Understanding and Design Following
66
+ Human Instructions},
67
+ journal = {CoRR},
68
+ volume = {abs/2410.07919},
69
+ year = {2024}
70
+ }
71
+ ```
added_tokens.json ADDED
@@ -0,0 +1,987 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</FASTA>": 32007,
3
+ "</MOL>": 32001,
4
+ "</PROT>": 32003,
5
+ "</SELFIES>": 32005,
6
+ "<FASTA>": 32006,
7
+ "<MOL>": 32000,
8
+ "<PROT>": 32002,
9
+ "<SELFIES>": 32004,
10
+ "<p>A": 32008,
11
+ "<p>C": 32009,
12
+ "<p>D": 32010,
13
+ "<p>E": 32011,
14
+ "<p>F": 32012,
15
+ "<p>G": 32013,
16
+ "<p>H": 32014,
17
+ "<p>I": 32015,
18
+ "<p>K": 32016,
19
+ "<p>L": 32017,
20
+ "<p>M": 32018,
21
+ "<p>N": 32019,
22
+ "<p>P": 32020,
23
+ "<p>Q": 32021,
24
+ "<p>R": 32022,
25
+ "<p>S": 32023,
26
+ "<p>T": 32024,
27
+ "<p>V": 32025,
28
+ "<p>W": 32026,
29
+ "<p>Y": 32027,
30
+ "[#Al]": 32463,
31
+ "[#As+1]": 32509,
32
+ "[#As]": 32536,
33
+ "[#B-1]": 32337,
34
+ "[#B]": 32044,
35
+ "[#Bi]": 32705,
36
+ "[#Branch1]": 32094,
37
+ "[#Branch2]": 32110,
38
+ "[#C+1]": 32247,
39
+ "[#C-1]": 32922,
40
+ "[#C]": 32380,
41
+ "[#Ce]": 32153,
42
+ "[#Co]": 32551,
43
+ "[#Cr]": 32206,
44
+ "[#Dy]": 32097,
45
+ "[#Er]": 32128,
46
+ "[#Eu]": 32517,
47
+ "[#Fe+1]": 32599,
48
+ "[#Fe]": 32941,
49
+ "[#Ga]": 32114,
50
+ "[#Gd]": 32404,
51
+ "[#GeH1]": 32732,
52
+ "[#Ge]": 32312,
53
+ "[#Hf+1]": 32244,
54
+ "[#Ho]": 32340,
55
+ "[#In]": 32357,
56
+ "[#Ir+1]": 32628,
57
+ "[#La]": 32291,
58
+ "[#Lu]": 32405,
59
+ "[#Mn]": 32583,
60
+ "[#Mo+1]": 32085,
61
+ "[#Mo]": 32811,
62
+ "[#N+1]": 32040,
63
+ "[#NH1+1]": 32806,
64
+ "[#N]": 32302,
65
+ "[#Nb]": 32903,
66
+ "[#Nd]": 32683,
67
+ "[#Ni]": 32578,
68
+ "[#O+1]": 32055,
69
+ "[#Os+2]": 32199,
70
+ "[#Os]": 32892,
71
+ "[#P+1]": 32379,
72
+ "[#PH1+1]": 32919,
73
+ "[#P]": 32557,
74
+ "[#PbH1]": 32211,
75
+ "[#Pb]": 32845,
76
+ "[#Pd]": 32746,
77
+ "[#Re]": 32346,
78
+ "[#Ring1]": 32755,
79
+ "[#Ring2]": 32947,
80
+ "[#Ru]": 32702,
81
+ "[#S+1]": 32975,
82
+ "[#S-1]": 32658,
83
+ "[#SH1]": 32230,
84
+ "[#S]": 32965,
85
+ "[#Sb]": 32592,
86
+ "[#Sc]": 32043,
87
+ "[#SeH1]": 32185,
88
+ "[#Se]": 32593,
89
+ "[#Si+1]": 32799,
90
+ "[#Si-1]": 32832,
91
+ "[#SiH1]": 32812,
92
+ "[#Si]": 32465,
93
+ "[#Sm]": 32666,
94
+ "[#Sn]": 32435,
95
+ "[#Ta+1]": 32283,
96
+ "[#Ta]": 32684,
97
+ "[#Tb]": 32507,
98
+ "[#Tc+1]": 32757,
99
+ "[#Tc]": 32801,
100
+ "[#Te]": 32296,
101
+ "[#Th]": 32563,
102
+ "[#Ti+1]": 32790,
103
+ "[#Ti]": 32464,
104
+ "[#Tl]": 32401,
105
+ "[#Tm]": 32689,
106
+ "[#U]": 32257,
107
+ "[#V+1]": 32896,
108
+ "[#V]": 32663,
109
+ "[#W+1]": 32285,
110
+ "[#WH1]": 32719,
111
+ "[#W]": 32550,
112
+ "[#Y]": 32863,
113
+ "[#Yb]": 32075,
114
+ "[#Zr+1]": 32745,
115
+ "[#Zr]": 32184,
116
+ "[-/Ring1]": 32685,
117
+ "[-/Ring2]": 32647,
118
+ "[-\\Ring1]": 32798,
119
+ "[-\\Ring2]": 32140,
120
+ "[/Br]": 32707,
121
+ "[/C@@H1]": 32679,
122
+ "[/C@@]": 32598,
123
+ "[/C@H1]": 32278,
124
+ "[/C@]": 32622,
125
+ "[/CH1-1]": 32814,
126
+ "[/C]": 32348,
127
+ "[/Cl]": 32893,
128
+ "[/F]": 32381,
129
+ "[/I]": 32982,
130
+ "[/N+1]": 32698,
131
+ "[/N-1]": 32837,
132
+ "[/NH1+1]": 32237,
133
+ "[/NH1]": 32147,
134
+ "[/NH2+1]": 32973,
135
+ "[/N]": 32101,
136
+ "[/O-1]": 32152,
137
+ "[/O]": 32427,
138
+ "[/P+1]": 32430,
139
+ "[/P]": 32731,
140
+ "[/S]": 32098,
141
+ "[10B]": 32554,
142
+ "[111Cd]": 32079,
143
+ "[115Sn]": 32254,
144
+ "[117Sn]": 32793,
145
+ "[119Sn]": 32498,
146
+ "[11B]": 32960,
147
+ "[11CH3]": 32969,
148
+ "[121Sb]": 32395,
149
+ "[123I]": 32107,
150
+ "[123Sb]": 32359,
151
+ "[125I]": 32937,
152
+ "[125Te]": 32699,
153
+ "[127IH1]": 32688,
154
+ "[129Xe]": 32660,
155
+ "[131I]": 32899,
156
+ "[139La]": 32378,
157
+ "[13C@@H1]": 32623,
158
+ "[13C@H1]": 32844,
159
+ "[13CH1]": 32036,
160
+ "[13CH2]": 32615,
161
+ "[13CH3]": 32625,
162
+ "[13C]": 32095,
163
+ "[13NH3]": 32154,
164
+ "[14CH3]": 32362,
165
+ "[14C]": 32785,
166
+ "[151Eu]": 32754,
167
+ "[15NH2]": 32809,
168
+ "[15OH2]": 32220,
169
+ "[16OH2]": 32950,
170
+ "[17OH2]": 32270,
171
+ "[183W]": 32642,
172
+ "[18FH1]": 32933,
173
+ "[18F]": 32039,
174
+ "[18OH2]": 32908,
175
+ "[197Au]": 32571,
176
+ "[197Hg]": 32708,
177
+ "[1H+1]": 32636,
178
+ "[1HH1]": 32332,
179
+ "[203Hg]": 32880,
180
+ "[203Tl]": 32588,
181
+ "[205Tl]": 32966,
182
+ "[210Po]": 32213,
183
+ "[23Na]": 32559,
184
+ "[25Mg]": 32493,
185
+ "[28Si]": 32487,
186
+ "[29Si]": 32740,
187
+ "[2HH1]": 32902,
188
+ "[2H]": 32413,
189
+ "[30Si]": 32423,
190
+ "[31Si]": 32879,
191
+ "[32SH2]": 32365,
192
+ "[32Si]": 32274,
193
+ "[33PH3]": 32587,
194
+ "[33SH2]": 32438,
195
+ "[35SH2]": 32219,
196
+ "[36SH2]": 32064,
197
+ "[39Ar]": 32860,
198
+ "[39K]": 32376,
199
+ "[3HH1]": 32087,
200
+ "[3H]": 32193,
201
+ "[3He]": 32339,
202
+ "[45Sc]": 32066,
203
+ "[4He]": 32276,
204
+ "[51Cr]": 32475,
205
+ "[51V]": 32275,
206
+ "[57Fe]": 32632,
207
+ "[63Cu]": 32897,
208
+ "[65Zn]": 32166,
209
+ "[67Zn]": 32353,
210
+ "[6Li]": 32631,
211
+ "[73Ge]": 32226,
212
+ "[77Se]": 32038,
213
+ "[79BrH1]": 32239,
214
+ "[7Li]": 32229,
215
+ "[87Rb]": 32333,
216
+ "[89Y]": 32322,
217
+ "[93Nb]": 32262,
218
+ "[95Mo]": 32156,
219
+ "[9Be]": 32792,
220
+ "[=13CH1]": 32454,
221
+ "[=13C]": 32834,
222
+ "[=Ag]": 32148,
223
+ "[=Al-1]": 32930,
224
+ "[=AlH1]": 32569,
225
+ "[=Al]": 32601,
226
+ "[=AsH1]": 32855,
227
+ "[=AsH2]": 32843,
228
+ "[=AsH3]": 32138,
229
+ "[=As]": 32948,
230
+ "[=Au]": 32567,
231
+ "[=B-1]": 32730,
232
+ "[=BH1-1]": 32558,
233
+ "[=BH2-1]": 32242,
234
+ "[=B]": 32936,
235
+ "[=Ba]": 32410,
236
+ "[=Bi+1]": 32387,
237
+ "[=BiH1]": 32343,
238
+ "[=Bi]": 32407,
239
+ "[=Branch1]": 32328,
240
+ "[=Branch2]": 32316,
241
+ "[=C+1]": 32594,
242
+ "[=C-1]": 32963,
243
+ "[=CH0]": 32223,
244
+ "[=CH1+1]": 32091,
245
+ "[=CH1-1]": 32214,
246
+ "[=C]": 32176,
247
+ "[=Ca]": 32279,
248
+ "[=Cd]": 32573,
249
+ "[=Ce]": 32531,
250
+ "[=CoH1]": 32859,
251
+ "[=Co]": 32497,
252
+ "[=CrH2]": 32656,
253
+ "[=Cr]": 32856,
254
+ "[=Cu]": 32775,
255
+ "[=Dy]": 32617,
256
+ "[=Eu]": 32388,
257
+ "[=Fe+1]": 32170,
258
+ "[=Fe]": 32773,
259
+ "[=Ga]": 32748,
260
+ "[=Gd]": 32048,
261
+ "[=GeH1]": 32927,
262
+ "[=GeH2]": 32661,
263
+ "[=Ge]": 32547,
264
+ "[=Hf+2]": 32172,
265
+ "[=Hf]": 32390,
266
+ "[=Hg]": 32556,
267
+ "[=Ho]": 32142,
268
+ "[=I]": 32676,
269
+ "[=InH1]": 32668,
270
+ "[=In]": 32155,
271
+ "[=IrH1]": 32252,
272
+ "[=Ir]": 32503,
273
+ "[=La]": 32641,
274
+ "[=Lu]": 32260,
275
+ "[=Mg]": 32253,
276
+ "[=Mn-1]": 32455,
277
+ "[=MnH1]": 32417,
278
+ "[=Mn]": 32957,
279
+ "[=Mo+2]": 32326,
280
+ "[=Mo+4]": 32083,
281
+ "[=MoH1]": 32611,
282
+ "[=MoH2]": 32263,
283
+ "[=MoH3]": 32338,
284
+ "[=Mo]": 32889,
285
+ "[=N+1]": 32467,
286
+ "[=N-1]": 32917,
287
+ "[=NH0]": 32756,
288
+ "[=NH1+1]": 32373,
289
+ "[=NH2+1]": 32619,
290
+ "[=N]": 32366,
291
+ "[=Nb]": 32741,
292
+ "[=Ni]": 32335,
293
+ "[=O+1]": 32425,
294
+ "[=OH1+1]": 32131,
295
+ "[=O]": 32294,
296
+ "[=Os+2]": 32847,
297
+ "[=Os]": 32568,
298
+ "[=P+1]": 32912,
299
+ "[=P-1]": 32687,
300
+ "[=PH1+1]": 32029,
301
+ "[=PH1]": 32319,
302
+ "[=PH2+1]": 32499,
303
+ "[=PH2]": 32259,
304
+ "[=PH3]": 32816,
305
+ "[=P]": 32954,
306
+ "[=PbH2]": 32466,
307
+ "[=Pb]": 32585,
308
+ "[=Pd]": 32839,
309
+ "[=Pr+1]": 32300,
310
+ "[=Pr]": 32579,
311
+ "[=Pt]": 32489,
312
+ "[=ReH1]": 32144,
313
+ "[=Re]": 32956,
314
+ "[=RhH1]": 32310,
315
+ "[=Rh]": 32779,
316
+ "[=Ring1]": 32271,
317
+ "[=Ring2]": 32494,
318
+ "[=Ring3]": 32422,
319
+ "[=Ru+1]": 32073,
320
+ "[=RuH1]": 32907,
321
+ "[=RuH2]": 32609,
322
+ "[=Ru]": 32958,
323
+ "[=S+1]": 32501,
324
+ "[=S-1]": 32750,
325
+ "[=S@@]": 32301,
326
+ "[=SH0]": 32163,
327
+ "[=SH1+1]": 32772,
328
+ "[=SH1-1]": 32979,
329
+ "[=SH1]": 32552,
330
+ "[=SH2]": 32667,
331
+ "[=SH4]": 32864,
332
+ "[=S]": 32768,
333
+ "[=Sb+1]": 32288,
334
+ "[=SbH1]": 32045,
335
+ "[=SbH2]": 32420,
336
+ "[=SbH3]": 32604,
337
+ "[=Sb]": 32444,
338
+ "[=Sc]": 32511,
339
+ "[=Se+1]": 32106,
340
+ "[=SeH1]": 32868,
341
+ "[=SeH2]": 32764,
342
+ "[=Se]": 32726,
343
+ "[=Si+1]": 32549,
344
+ "[=Si+2]": 32174,
345
+ "[=Si-1]": 32284,
346
+ "[=SiH1+1]": 32850,
347
+ "[=SiH1-1]": 32904,
348
+ "[=SiH1]": 32777,
349
+ "[=SiH2]": 32492,
350
+ "[=Si]": 32854,
351
+ "[=SnH1]": 32510,
352
+ "[=SnH2]": 32458,
353
+ "[=Sn]": 32886,
354
+ "[=Sr]": 32090,
355
+ "[=TaH1]": 32303,
356
+ "[=Ta]": 32162,
357
+ "[=Tb]": 32681,
358
+ "[=Tc+1]": 32032,
359
+ "[=Tc+2]": 32612,
360
+ "[=Tc+3]": 32874,
361
+ "[=Tc+4]": 32970,
362
+ "[=Tc+5]": 32697,
363
+ "[=Tc]": 32076,
364
+ "[=TeH2]": 32926,
365
+ "[=Te]": 32158,
366
+ "[=Th+2]": 32086,
367
+ "[=Th]": 32400,
368
+ "[=Ti+1]": 32542,
369
+ "[=Ti+2]": 32881,
370
+ "[=Ti]": 32788,
371
+ "[=Tl]": 32309,
372
+ "[=Tm]": 32540,
373
+ "[=U+2]": 32190,
374
+ "[=UH1]": 32201,
375
+ "[=U]": 32895,
376
+ "[=V+2]": 32796,
377
+ "[=VH1]": 32058,
378
+ "[=VH2]": 32364,
379
+ "[=V]": 32232,
380
+ "[=W-1]": 32050,
381
+ "[=WH1]": 32829,
382
+ "[=WH2]": 32961,
383
+ "[=WH4]": 32727,
384
+ "[=W]": 32069,
385
+ "[=Xe]": 32249,
386
+ "[=YH1]": 32787,
387
+ "[=Y]": 32654,
388
+ "[=Yb]": 32885,
389
+ "[=Zn]": 32134,
390
+ "[=Zr+2]": 32635,
391
+ "[=ZrH2]": 32061,
392
+ "[=Zr]": 32129,
393
+ "[Ac]": 32603,
394
+ "[Ag+1]": 32115,
395
+ "[Ag-1]": 32409,
396
+ "[AgH1]": 32962,
397
+ "[Ag]": 32502,
398
+ "[Al+1]": 32350,
399
+ "[Al+2]": 32496,
400
+ "[Al+3]": 32921,
401
+ "[Al-1]": 32168,
402
+ "[Al-3]": 32945,
403
+ "[AlH1+1]": 32857,
404
+ "[AlH1+2]": 32883,
405
+ "[AlH1-1]": 32369,
406
+ "[AlH1]": 32477,
407
+ "[AlH2+1]": 32597,
408
+ "[AlH2-1]": 32882,
409
+ "[AlH2]": 32072,
410
+ "[AlH3-1]": 32870,
411
+ "[AlH3]": 32637,
412
+ "[AlH4-1]": 32840,
413
+ "[Al]": 32694,
414
+ "[Am]": 32581,
415
+ "[Ar]": 32113,
416
+ "[As+1]": 32393,
417
+ "[As+3]": 32739,
418
+ "[As-1]": 32452,
419
+ "[AsH1+1]": 32068,
420
+ "[AsH1]": 32914,
421
+ "[AsH2+1]": 32909,
422
+ "[AsH2]": 32711,
423
+ "[AsH3+1]": 32305,
424
+ "[AsH3]": 32292,
425
+ "[As]": 32810,
426
+ "[AtH1]": 32445,
427
+ "[At]": 32835,
428
+ "[Au+1]": 32808,
429
+ "[Au+3]": 32749,
430
+ "[Au-1]": 32234,
431
+ "[AuH1]": 32210,
432
+ "[Au]": 32383,
433
+ "[B-1]": 32544,
434
+ "[BH0]": 32728,
435
+ "[BH1-1]": 32876,
436
+ "[BH2-1]": 32071,
437
+ "[BH3-1]": 32938,
438
+ "[BH4-1]": 32830,
439
+ "[B]": 32828,
440
+ "[Ba+2]": 32392,
441
+ "[Be+2]": 32108,
442
+ "[Be]": 32621,
443
+ "[Bh]": 32751,
444
+ "[Bi+1]": 32122,
445
+ "[Bi+2]": 32537,
446
+ "[Bi+3]": 32649,
447
+ "[Bi-1]": 32721,
448
+ "[Bi-2]": 32875,
449
+ "[BiH1]": 32959,
450
+ "[BiH2+2]": 32256,
451
+ "[BiH2]": 32710,
452
+ "[BiH3]": 32672,
453
+ "[Bi]": 32607,
454
+ "[Bk]": 32651,
455
+ "[Br+1]": 32165,
456
+ "[Br+2]": 32299,
457
+ "[Br+3]": 32983,
458
+ "[Br-1]": 32057,
459
+ "[Br]": 32150,
460
+ "[Branch1]": 32136,
461
+ "[Branch2]": 32216,
462
+ "[Branch3]": 32576,
463
+ "[C+1]": 32034,
464
+ "[C-1]": 32709,
465
+ "[C@@H1]": 32640,
466
+ "[C@@]": 32074,
467
+ "[C@H1]": 32179,
468
+ "[C@]": 32560,
469
+ "[CH0]": 32250,
470
+ "[CH1+1]": 32762,
471
+ "[CH1-1]": 32575,
472
+ "[CH1]": 32195,
473
+ "[CH2+1]": 32692,
474
+ "[CH2-1]": 32384,
475
+ "[CH3+1]": 32734,
476
+ "[CH3-1]": 32123,
477
+ "[C]": 32824,
478
+ "[Ca+2]": 32474,
479
+ "[Ca]": 32634,
480
+ "[Cd+2]": 32093,
481
+ "[Cd-1]": 32461,
482
+ "[Cd-2]": 32967,
483
+ "[Cd]": 32738,
484
+ "[Ce+3]": 32505,
485
+ "[Ce+4]": 32231,
486
+ "[CeH1]": 32389,
487
+ "[Ce]": 32255,
488
+ "[Cf]": 32789,
489
+ "[Cl+1]": 32446,
490
+ "[Cl+2]": 32696,
491
+ "[Cl+3]": 32911,
492
+ "[Cl-1]": 32513,
493
+ "[ClH0]": 32853,
494
+ "[ClH1+1]": 32887,
495
+ "[ClH2+1]": 32297,
496
+ "[ClH3+2]": 32591,
497
+ "[Cl]": 32441,
498
+ "[Cm]": 32733,
499
+ "[Co+1]": 32541,
500
+ "[Co+2]": 32356,
501
+ "[Co+3]": 32315,
502
+ "[Co-1]": 32187,
503
+ "[Co-2]": 32724,
504
+ "[Co-3]": 32180,
505
+ "[CoH1+1]": 32841,
506
+ "[CoH1+2]": 32890,
507
+ "[CoH2]": 32602,
508
+ "[Co]": 32495,
509
+ "[Cr+1]": 32512,
510
+ "[Cr+2]": 32361,
511
+ "[Cr+3]": 32949,
512
+ "[Cr+4]": 32119,
513
+ "[Cr+5]": 32215,
514
+ "[Cr+6]": 32508,
515
+ "[Cr-1]": 32295,
516
+ "[Cr-2]": 32173,
517
+ "[Cr-3]": 32873,
518
+ "[CrH1+2]": 32718,
519
+ "[CrH2]": 32382,
520
+ "[Cr]": 32747,
521
+ "[Cs+1]": 32624,
522
+ "[Cu+1]": 32375,
523
+ "[Cu+2]": 32081,
524
+ "[Cu-1]": 32671,
525
+ "[Cu-2]": 32803,
526
+ "[CuH1+1]": 32084,
527
+ "[CuH1]": 32704,
528
+ "[CuH2-1]": 32778,
529
+ "[Cu]": 32111,
530
+ "[Db]": 32935,
531
+ "[Dy+3]": 32221,
532
+ "[Dy]": 32526,
533
+ "[Er+3]": 32327,
534
+ "[Er]": 32208,
535
+ "[Es]": 32833,
536
+ "[Eu+2]": 32955,
537
+ "[Eu+3]": 32062,
538
+ "[Eu]": 32898,
539
+ "[F-1]": 32807,
540
+ "[F]": 32188,
541
+ "[Fe+1]": 32877,
542
+ "[Fe+2]": 32125,
543
+ "[Fe+3]": 32776,
544
+ "[Fe+4]": 32453,
545
+ "[Fe+5]": 32918,
546
+ "[Fe+6]": 32934,
547
+ "[Fe-1]": 32046,
548
+ "[Fe-2]": 32916,
549
+ "[Fe-3]": 32118,
550
+ "[Fe-4]": 32673,
551
+ "[FeH1]": 32659,
552
+ "[FeH2]": 32737,
553
+ "[FeH3]": 32416,
554
+ "[Fe]": 32159,
555
+ "[Fm]": 32530,
556
+ "[Ga+3]": 32049,
557
+ "[Ga-1]": 32334,
558
+ "[GaH1]": 32700,
559
+ "[GaH2]": 32209,
560
+ "[GaH3]": 32402,
561
+ "[Ga]": 32582,
562
+ "[Gd+2]": 32434,
563
+ "[Gd+3]": 32978,
564
+ "[Gd-4]": 32265,
565
+ "[Gd]": 32146,
566
+ "[Ge+4]": 32429,
567
+ "[GeH1]": 32646,
568
+ "[GeH2]": 32228,
569
+ "[GeH3]": 32871,
570
+ "[GeH4]": 32469,
571
+ "[Ge]": 32240,
572
+ "[H+1]": 32054,
573
+ "[H-1]": 32481,
574
+ "[HH1]": 32761,
575
+ "[H]": 32318,
576
+ "[He]": 32135,
577
+ "[Hf+2]": 32606,
578
+ "[Hf+4]": 32342,
579
+ "[Hf]": 32584,
580
+ "[Hg+1]": 32849,
581
+ "[Hg+2]": 32218,
582
+ "[Hg-1]": 32664,
583
+ "[Hg-2]": 32515,
584
+ "[HgH1]": 32984,
585
+ "[Hg]": 32104,
586
+ "[Ho+3]": 32644,
587
+ "[Ho]": 32281,
588
+ "[Hs]": 32564,
589
+ "[I+1]": 32894,
590
+ "[I+2]": 32695,
591
+ "[I+3]": 32742,
592
+ "[I-1]": 32753,
593
+ "[IH0]": 32472,
594
+ "[IH1+1]": 32082,
595
+ "[IH1-1]": 32406,
596
+ "[IH2+1]": 32491,
597
+ "[I]": 32720,
598
+ "[In+1]": 32183,
599
+ "[In+3]": 32268,
600
+ "[In-1]": 32974,
601
+ "[InH1]": 32307,
602
+ "[InH2]": 32451,
603
+ "[InH3]": 32519,
604
+ "[In]": 32572,
605
+ "[Ir+1]": 32331,
606
+ "[Ir+2]": 32202,
607
+ "[Ir+3]": 32565,
608
+ "[Ir-2]": 32433,
609
+ "[Ir-3]": 32415,
610
+ "[IrH1+2]": 32528,
611
+ "[IrH1]": 32650,
612
+ "[IrH2]": 32780,
613
+ "[IrH3]": 32878,
614
+ "[Ir]": 32653,
615
+ "[K+1]": 32396,
616
+ "[K]": 32942,
617
+ "[Kr]": 32706,
618
+ "[La+3]": 32539,
619
+ "[La]": 32600,
620
+ "[Li+1]": 32030,
621
+ "[Li-1]": 32888,
622
+ "[Li]": 32287,
623
+ "[Lr]": 32191,
624
+ "[Lu+3]": 32358,
625
+ "[Lu]": 32205,
626
+ "[Md]": 32320,
627
+ "[Mg+1]": 32665,
628
+ "[Mg+2]": 32447,
629
+ "[Mg]": 32836,
630
+ "[Mn+1]": 32913,
631
+ "[Mn+2]": 32324,
632
+ "[Mn+3]": 32838,
633
+ "[Mn-2]": 32207,
634
+ "[MnH1+1]": 32457,
635
+ "[MnH1]": 32212,
636
+ "[Mn]": 32932,
637
+ "[Mo+1]": 32341,
638
+ "[Mo+2]": 32905,
639
+ "[Mo+3]": 32562,
640
+ "[Mo+4]": 32629,
641
+ "[Mo-2]": 32476,
642
+ "[MoH1]": 32488,
643
+ "[MoH2]": 32412,
644
+ "[Mo]": 32759,
645
+ "[Mt]": 32139,
646
+ "[N+1]": 32171,
647
+ "[N-1]": 32524,
648
+ "[N@+1]": 32520,
649
+ "[N@@+1]": 32805,
650
+ "[N@@H1+1]": 32289,
651
+ "[N@H1+1]": 32852,
652
+ "[N@]": 32298,
653
+ "[NH0]": 32815,
654
+ "[NH1+1]": 32626,
655
+ "[NH1-1]": 32121,
656
+ "[NH1]": 32485,
657
+ "[NH2+1]": 32946,
658
+ "[NH2-1]": 32103,
659
+ "[NH3+1]": 32067,
660
+ "[NH4+1]": 32910,
661
+ "[N]": 32349,
662
+ "[Na+1]": 32831,
663
+ "[Na]": 32827,
664
+ "[Nb+2]": 32323,
665
+ "[Nb+3]": 32428,
666
+ "[Nb+5]": 32105,
667
+ "[Nb-1]": 32371,
668
+ "[Nb-2]": 32813,
669
+ "[NbH3]": 32538,
670
+ "[Nb]": 32825,
671
+ "[Nd+3]": 32545,
672
+ "[Nd]": 32532,
673
+ "[Ne]": 32555,
674
+ "[Ni+1]": 32630,
675
+ "[Ni+2]": 32783,
676
+ "[Ni+3]": 32133,
677
+ "[Ni-1]": 32304,
678
+ "[Ni-2]": 32680,
679
+ "[Ni-3]": 32293,
680
+ "[NiH1]": 32241,
681
+ "[NiH2]": 32204,
682
+ "[Ni]": 32372,
683
+ "[No]": 32804,
684
+ "[Np]": 32355,
685
+ "[O+1]": 32151,
686
+ "[O-1]": 32473,
687
+ "[O-2]": 32483,
688
+ "[OH0]": 32729,
689
+ "[OH1+1]": 32951,
690
+ "[OH1-1]": 32194,
691
+ "[OH2+1]": 32063,
692
+ "[OH3+1]": 32117,
693
+ "[O]": 32767,
694
+ "[Os+1]": 32070,
695
+ "[Os+2]": 32928,
696
+ "[Os+4]": 32370,
697
+ "[Os+5]": 32160,
698
+ "[Os+6]": 32518,
699
+ "[Os+7]": 32088,
700
+ "[Os+8]": 32137,
701
+ "[Os-1]": 32968,
702
+ "[Os-2]": 32306,
703
+ "[Os-3]": 32398,
704
+ "[OsH1-1]": 32648,
705
+ "[OsH1]": 32823,
706
+ "[OsH2]": 32716,
707
+ "[Os]": 32662,
708
+ "[P+1]": 32198,
709
+ "[P-1]": 32657,
710
+ "[P-3]": 32421,
711
+ "[P@@]": 32437,
712
+ "[P@]": 32802,
713
+ "[PH0]": 32460,
714
+ "[PH1+1]": 32399,
715
+ "[PH1-1]": 32586,
716
+ "[PH1]": 32971,
717
+ "[PH2+1]": 32099,
718
+ "[PH2-1]": 32374,
719
+ "[PH2]": 32330,
720
+ "[PH3+1]": 32196,
721
+ "[PH3]": 32655,
722
+ "[PH4+1]": 32675,
723
+ "[PH4]": 32590,
724
+ "[P]": 32456,
725
+ "[Pa]": 32906,
726
+ "[Pb+2]": 32533,
727
+ "[PbH1]": 32077,
728
+ "[PbH2+2]": 32482,
729
+ "[PbH2]": 32553,
730
+ "[PbH3]": 32674,
731
+ "[PbH4]": 32826,
732
+ "[Pb]": 32525,
733
+ "[Pd+1]": 32891,
734
+ "[Pd+2]": 32701,
735
+ "[Pd-1]": 32821,
736
+ "[Pd-2]": 32795,
737
+ "[PdH1+1]": 32053,
738
+ "[PdH1]": 32385,
739
+ "[PdH2]": 32923,
740
+ "[Pd]": 32713,
741
+ "[Pm]": 32431,
742
+ "[PoH1]": 32245,
743
+ "[Po]": 32419,
744
+ "[Pr+3]": 32596,
745
+ "[Pr]": 32432,
746
+ "[Pt+1]": 32360,
747
+ "[Pt+2]": 32763,
748
+ "[Pt+4]": 32089,
749
+ "[Pt-1]": 32872,
750
+ "[Pt-2]": 32858,
751
+ "[PtH1+1]": 32161,
752
+ "[PtH1]": 32822,
753
+ "[PtH2]": 32470,
754
+ "[PtH3]": 32181,
755
+ "[Pt]": 32236,
756
+ "[Pu]": 32426,
757
+ "[Rb+1]": 32217,
758
+ "[Rb]": 32758,
759
+ "[Re-1]": 32782,
760
+ "[Re-2]": 32506,
761
+ "[ReH1]": 32589,
762
+ "[ReH2]": 32286,
763
+ "[ReH3]": 32620,
764
+ "[ReH4]": 32031,
765
+ "[ReH7]": 32329,
766
+ "[Re]": 32126,
767
+ "[Rf]": 32677,
768
+ "[Rh+1]": 32277,
769
+ "[Rh+2]": 32862,
770
+ "[Rh+3]": 32608,
771
+ "[Rh-1]": 32574,
772
+ "[Rh-2]": 32233,
773
+ "[Rh-3]": 32670,
774
+ "[RhH1+2]": 32391,
775
+ "[RhH1]": 32869,
776
+ "[RhH2]": 32272,
777
+ "[RhH3]": 32120,
778
+ "[Rh]": 32516,
779
+ "[Ring1]": 32884,
780
+ "[Ring2]": 32028,
781
+ "[Ring3]": 32786,
782
+ "[Rn]": 32645,
783
+ "[Ru+1]": 32408,
784
+ "[Ru+2]": 32321,
785
+ "[Ru+3]": 32943,
786
+ "[Ru+4]": 32818,
787
+ "[Ru+5]": 32566,
788
+ "[Ru+6]": 32939,
789
+ "[Ru+8]": 32052,
790
+ "[Ru-1]": 32141,
791
+ "[Ru-2]": 32471,
792
+ "[Ru-3]": 32486,
793
+ "[Ru-4]": 32227,
794
+ "[RuH1+1]": 32132,
795
+ "[RuH1+2]": 32325,
796
+ "[RuH1+3]": 32504,
797
+ "[RuH1-1]": 32273,
798
+ "[RuH1]": 32443,
799
+ "[RuH2]": 32693,
800
+ "[RuH3]": 32690,
801
+ "[RuH4]": 32462,
802
+ "[Ru]": 32439,
803
+ "[S+1]": 32638,
804
+ "[S-1]": 32035,
805
+ "[S-2]": 32848,
806
+ "[S@+1]": 32100,
807
+ "[S@@+1]": 32514,
808
+ "[S@@]": 32546,
809
+ "[S@]": 32784,
810
+ "[SH0]": 32940,
811
+ "[SH1+1]": 32817,
812
+ "[SH1-1]": 32127,
813
+ "[SH1]": 32267,
814
+ "[SH2+1]": 32521,
815
+ "[SH2]": 32925,
816
+ "[SH3+1]": 32186,
817
+ "[SH3]": 32929,
818
+ "[SH4]": 32116,
819
+ "[S]": 32610,
820
+ "[Sb+1]": 32317,
821
+ "[Sb+3]": 32377,
822
+ "[Sb+5]": 32820,
823
+ "[Sb-1]": 32715,
824
+ "[SbH1+1]": 32769,
825
+ "[SbH1]": 32042,
826
+ "[SbH2+1]": 32580,
827
+ "[SbH2]": 32459,
828
+ "[SbH3+1]": 32484,
829
+ "[SbH4]": 32867,
830
+ "[Sb]": 32363,
831
+ "[Sc+3]": 32344,
832
+ "[Sc]": 32725,
833
+ "[Se+1]": 32336,
834
+ "[Se+4]": 32222,
835
+ "[Se-1]": 32614,
836
+ "[Se-2]": 32920,
837
+ "[SeH1+1]": 32145,
838
+ "[SeH1-1]": 32414,
839
+ "[SeH1]": 32102,
840
+ "[SeH2+1]": 32313,
841
+ "[SeH2]": 32440,
842
+ "[SeH3+1]": 32842,
843
+ "[SeH5]": 32723,
844
+ "[Se]": 32577,
845
+ "[Sg]": 32595,
846
+ "[Si+1]": 32041,
847
+ "[Si+2]": 32235,
848
+ "[Si+3]": 32866,
849
+ "[Si+4]": 32703,
850
+ "[Si-1]": 32770,
851
+ "[SiH1+1]": 32924,
852
+ "[SiH1-1]": 32976,
853
+ "[SiH1]": 32080,
854
+ "[SiH2+1]": 32771,
855
+ "[SiH2-1]": 32047,
856
+ "[SiH2]": 32964,
857
+ "[SiH3-1]": 32192,
858
+ "[SiH3]": 32130,
859
+ "[SiH4-1]": 32752,
860
+ "[SiH4]": 32682,
861
+ "[Si]": 32714,
862
+ "[Sm+3]": 32953,
863
+ "[Sm]": 32972,
864
+ "[Sn+1]": 32490,
865
+ "[Sn+2]": 32981,
866
+ "[Sn+3]": 32468,
867
+ "[Sn+4]": 32282,
868
+ "[Sn-1]": 32411,
869
+ "[SnH1+1]": 32548,
870
+ "[SnH1+3]": 32261,
871
+ "[SnH1]": 32669,
872
+ "[SnH2+2]": 32143,
873
+ "[SnH2-1]": 32418,
874
+ "[SnH2]": 32743,
875
+ "[SnH3]": 32944,
876
+ "[SnH4]": 32846,
877
+ "[Sn]": 32736,
878
+ "[Sr+2]": 32436,
879
+ "[Sr]": 32269,
880
+ "[Ta+2]": 32643,
881
+ "[Ta+5]": 32224,
882
+ "[Ta-1]": 32149,
883
+ "[TaH1]": 32735,
884
+ "[TaH2]": 32652,
885
+ "[TaH3]": 32442,
886
+ "[Ta]": 32712,
887
+ "[Tb+3]": 32351,
888
+ "[Tb+4]": 32264,
889
+ "[Tb]": 32056,
890
+ "[Tc+1]": 32060,
891
+ "[Tc+4]": 32368,
892
+ "[Tc+5]": 32251,
893
+ "[Tc+6]": 32570,
894
+ "[Tc+7]": 32065,
895
+ "[Tc]": 32394,
896
+ "[Te+1]": 32535,
897
+ "[Te+4]": 32722,
898
+ "[TeH1]": 32225,
899
+ "[TeH2+1]": 32522,
900
+ "[TeH2]": 32177,
901
+ "[Te]": 32033,
902
+ "[Th+2]": 32618,
903
+ "[Th+4]": 32175,
904
+ "[ThH1]": 32243,
905
+ "[ThH2]": 32164,
906
+ "[Th]": 32109,
907
+ "[Ti+1]": 32182,
908
+ "[Ti+2]": 32345,
909
+ "[Ti+3]": 32200,
910
+ "[Ti+4]": 32112,
911
+ "[Ti-1]": 32311,
912
+ "[Ti-2]": 32478,
913
+ "[TiH1+1]": 32167,
914
+ "[TiH1]": 32157,
915
+ "[Ti]": 32633,
916
+ "[Tl+1]": 32397,
917
+ "[Tl+3]": 32800,
918
+ "[TlH1]": 32258,
919
+ "[TlH2]": 32819,
920
+ "[Tl]": 32760,
921
+ "[Tm+3]": 32527,
922
+ "[Tm]": 32561,
923
+ "[U+2]": 32691,
924
+ "[U+3]": 32197,
925
+ "[U+4]": 32354,
926
+ "[UH1]": 32479,
927
+ "[UH2]": 32952,
928
+ "[UH3]": 32169,
929
+ "[U]": 32308,
930
+ "[V+2]": 32096,
931
+ "[V+4]": 32915,
932
+ "[VH1]": 32450,
933
+ "[VH2]": 32280,
934
+ "[V]": 32980,
935
+ "[W+1]": 32248,
936
+ "[W+2]": 32449,
937
+ "[WH1]": 32765,
938
+ "[WH2]": 32900,
939
+ "[WH3]": 32189,
940
+ "[W]": 32448,
941
+ "[XeH1]": 32794,
942
+ "[Xe]": 32616,
943
+ "[Y+3]": 32078,
944
+ "[YH1]": 32347,
945
+ "[YH2]": 32901,
946
+ "[Y]": 32352,
947
+ "[Yb+2]": 32861,
948
+ "[Yb+3]": 32500,
949
+ "[YbH2]": 32851,
950
+ "[Yb]": 32203,
951
+ "[Zn+1]": 32124,
952
+ "[Zn+2]": 32290,
953
+ "[Zn-1]": 32678,
954
+ "[Zn-2]": 32781,
955
+ "[ZnH1+1]": 32480,
956
+ "[ZnH1]": 32534,
957
+ "[ZnH2]": 32367,
958
+ "[Zn]": 32977,
959
+ "[Zr+2]": 32238,
960
+ "[Zr+3]": 32314,
961
+ "[Zr+4]": 32613,
962
+ "[Zr-1]": 32639,
963
+ "[Zr-2]": 32791,
964
+ "[Zr-3]": 32774,
965
+ "[Zr-4]": 32059,
966
+ "[ZrH1]": 32744,
967
+ "[ZrH2]": 32037,
968
+ "[Zr]": 32865,
969
+ "[\\Br]": 32523,
970
+ "[\\C@@H1]": 32686,
971
+ "[\\C@@]": 32266,
972
+ "[\\C@H1]": 32717,
973
+ "[\\C@]": 32246,
974
+ "[\\C]": 32424,
975
+ "[\\Cl]": 32931,
976
+ "[\\F]": 32529,
977
+ "[\\I]": 32386,
978
+ "[\\N+1]": 32403,
979
+ "[\\N-1]": 32092,
980
+ "[\\NH1+1]": 32766,
981
+ "[\\NH1]": 32051,
982
+ "[\\NH2+1]": 32627,
983
+ "[\\N]": 32178,
984
+ "[\\O-1]": 32605,
985
+ "[\\O]": 32797,
986
+ "[\\S]": 32543
987
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32985
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ada0dece6a1aeb4a0c73fa0bcd494d9ae51109ae36693588d3fa7a1052496eb
3
+ size 13737571554
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }