Upload tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer_config.json +609 -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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a8fd5a78121908164e7568cfcbdd66ffb6aeec7d709ac707d6ef088575369a
|
3 |
+
size 17490584
|
tokenizer_config.json
ADDED
@@ -0,0 +1,609 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"7": {
|
38 |
+
"content": "[START_SMILES]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"8": {
|
46 |
+
"content": "[END_SMILES]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"9": {
|
54 |
+
"content": "[FORMULA]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"10": {
|
62 |
+
"content": "[SYNONYM]",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
"11": {
|
70 |
+
"content": "[RELATED]",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": false
|
76 |
+
},
|
77 |
+
"12": {
|
78 |
+
"content": "[SIMILAR]",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": false
|
84 |
+
},
|
85 |
+
"13": {
|
86 |
+
"content": "[PROPERTY]",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": false
|
92 |
+
},
|
93 |
+
"14": {
|
94 |
+
"content": "[SAS]",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
"15": {
|
102 |
+
"content": "[WEIGHT]",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": false
|
108 |
+
},
|
109 |
+
"16": {
|
110 |
+
"content": "[TPSA]",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": false
|
116 |
+
},
|
117 |
+
"17": {
|
118 |
+
"content": "[CLOGP]",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"18": {
|
126 |
+
"content": "[QED]",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"19": {
|
134 |
+
"content": "[NUMHDONORS]",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"20": {
|
142 |
+
"content": "[NUMHACCEPTORS]",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"21": {
|
150 |
+
"content": "[NUMHETEROATOMS]",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"22": {
|
158 |
+
"content": "[NUMROTATABLEBONDS]",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"23": {
|
166 |
+
"content": "[NOCOUNT]",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"24": {
|
174 |
+
"content": "[NHOHCOUNT]",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"25": {
|
182 |
+
"content": "[RINGCOUNT]",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"26": {
|
190 |
+
"content": "[HEAVYATOMCOUNT]",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"27": {
|
198 |
+
"content": "[FRACTIONCSP3]",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"28": {
|
206 |
+
"content": "[NUMAROMATICRINGS]",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
"29": {
|
214 |
+
"content": "[NUMSATURATEDRINGS]",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": false
|
220 |
+
},
|
221 |
+
"30": {
|
222 |
+
"content": "[NUMAROMATICHETEROCYCLES]",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": false
|
228 |
+
},
|
229 |
+
"31": {
|
230 |
+
"content": "[NUMAROMATICCARBOCYCLES]",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": false
|
236 |
+
},
|
237 |
+
"32": {
|
238 |
+
"content": "[NUMSATURATEDHETEROCYCLES]",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
"33": {
|
246 |
+
"content": "[NUMSATURATEDCARBOCYCLES]",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": false
|
252 |
+
},
|
253 |
+
"34": {
|
254 |
+
"content": "[NUMALIPHATICRINGS]",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": false
|
260 |
+
},
|
261 |
+
"35": {
|
262 |
+
"content": "[NUMALIPHATICHETEROCYCLES]",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": false
|
268 |
+
},
|
269 |
+
"36": {
|
270 |
+
"content": "[NUMALIPHATICCARBOCYCLES]",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": false
|
276 |
+
},
|
277 |
+
"37": {
|
278 |
+
"content": "[IUPAC]",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
+
"38": {
|
286 |
+
"content": "[VAR_NAME]",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": false
|
292 |
+
},
|
293 |
+
"39": {
|
294 |
+
"content": "[VAR_DESC]",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": false
|
300 |
+
},
|
301 |
+
"40": {
|
302 |
+
"content": "[VAR_VAL]",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": false
|
308 |
+
},
|
309 |
+
"41": {
|
310 |
+
"content": "[ASSAY_NAME]",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": false
|
316 |
+
},
|
317 |
+
"42": {
|
318 |
+
"content": "[ASSAY_DESC]",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": false
|
324 |
+
},
|
325 |
+
"43": {
|
326 |
+
"content": "[/FORMULA]",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": false
|
332 |
+
},
|
333 |
+
"44": {
|
334 |
+
"content": "[/SYNONYM]",
|
335 |
+
"lstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false,
|
339 |
+
"special": false
|
340 |
+
},
|
341 |
+
"45": {
|
342 |
+
"content": "[/RELATED]",
|
343 |
+
"lstrip": false,
|
344 |
+
"normalized": false,
|
345 |
+
"rstrip": false,
|
346 |
+
"single_word": false,
|
347 |
+
"special": false
|
348 |
+
},
|
349 |
+
"46": {
|
350 |
+
"content": "[/SIMILAR]",
|
351 |
+
"lstrip": false,
|
352 |
+
"normalized": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"single_word": false,
|
355 |
+
"special": false
|
356 |
+
},
|
357 |
+
"47": {
|
358 |
+
"content": "[/PROPERTY]",
|
359 |
+
"lstrip": false,
|
360 |
+
"normalized": false,
|
361 |
+
"rstrip": false,
|
362 |
+
"single_word": false,
|
363 |
+
"special": false
|
364 |
+
},
|
365 |
+
"48": {
|
366 |
+
"content": "[/SAS]",
|
367 |
+
"lstrip": false,
|
368 |
+
"normalized": false,
|
369 |
+
"rstrip": false,
|
370 |
+
"single_word": false,
|
371 |
+
"special": false
|
372 |
+
},
|
373 |
+
"49": {
|
374 |
+
"content": "[/WEIGHT]",
|
375 |
+
"lstrip": false,
|
376 |
+
"normalized": false,
|
377 |
+
"rstrip": false,
|
378 |
+
"single_word": false,
|
379 |
+
"special": false
|
380 |
+
},
|
381 |
+
"50": {
|
382 |
+
"content": "[/TPSA]",
|
383 |
+
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false,
|
387 |
+
"special": false
|
388 |
+
},
|
389 |
+
"51": {
|
390 |
+
"content": "[/CLOGP]",
|
391 |
+
"lstrip": false,
|
392 |
+
"normalized": false,
|
393 |
+
"rstrip": false,
|
394 |
+
"single_word": false,
|
395 |
+
"special": false
|
396 |
+
},
|
397 |
+
"52": {
|
398 |
+
"content": "[/QED]",
|
399 |
+
"lstrip": false,
|
400 |
+
"normalized": false,
|
401 |
+
"rstrip": false,
|
402 |
+
"single_word": false,
|
403 |
+
"special": false
|
404 |
+
},
|
405 |
+
"53": {
|
406 |
+
"content": "[/NUMHDONORS]",
|
407 |
+
"lstrip": false,
|
408 |
+
"normalized": false,
|
409 |
+
"rstrip": false,
|
410 |
+
"single_word": false,
|
411 |
+
"special": false
|
412 |
+
},
|
413 |
+
"54": {
|
414 |
+
"content": "[/NUMHACCEPTORS]",
|
415 |
+
"lstrip": false,
|
416 |
+
"normalized": false,
|
417 |
+
"rstrip": false,
|
418 |
+
"single_word": false,
|
419 |
+
"special": false
|
420 |
+
},
|
421 |
+
"55": {
|
422 |
+
"content": "[/NUMHETEROATOMS]",
|
423 |
+
"lstrip": false,
|
424 |
+
"normalized": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"single_word": false,
|
427 |
+
"special": false
|
428 |
+
},
|
429 |
+
"56": {
|
430 |
+
"content": "[/NUMROTATABLEBONDS]",
|
431 |
+
"lstrip": false,
|
432 |
+
"normalized": false,
|
433 |
+
"rstrip": false,
|
434 |
+
"single_word": false,
|
435 |
+
"special": false
|
436 |
+
},
|
437 |
+
"57": {
|
438 |
+
"content": "[/NOCOUNT]",
|
439 |
+
"lstrip": false,
|
440 |
+
"normalized": false,
|
441 |
+
"rstrip": false,
|
442 |
+
"single_word": false,
|
443 |
+
"special": false
|
444 |
+
},
|
445 |
+
"58": {
|
446 |
+
"content": "[/NHOHCOUNT]",
|
447 |
+
"lstrip": false,
|
448 |
+
"normalized": false,
|
449 |
+
"rstrip": false,
|
450 |
+
"single_word": false,
|
451 |
+
"special": false
|
452 |
+
},
|
453 |
+
"59": {
|
454 |
+
"content": "[/RINGCOUNT]",
|
455 |
+
"lstrip": false,
|
456 |
+
"normalized": false,
|
457 |
+
"rstrip": false,
|
458 |
+
"single_word": false,
|
459 |
+
"special": false
|
460 |
+
},
|
461 |
+
"60": {
|
462 |
+
"content": "[/HEAVYATOMCOUNT]",
|
463 |
+
"lstrip": false,
|
464 |
+
"normalized": false,
|
465 |
+
"rstrip": false,
|
466 |
+
"single_word": false,
|
467 |
+
"special": false
|
468 |
+
},
|
469 |
+
"61": {
|
470 |
+
"content": "[/FRACTIONCSP3]",
|
471 |
+
"lstrip": false,
|
472 |
+
"normalized": false,
|
473 |
+
"rstrip": false,
|
474 |
+
"single_word": false,
|
475 |
+
"special": false
|
476 |
+
},
|
477 |
+
"62": {
|
478 |
+
"content": "[/NUMAROMATICRINGS]",
|
479 |
+
"lstrip": false,
|
480 |
+
"normalized": false,
|
481 |
+
"rstrip": false,
|
482 |
+
"single_word": false,
|
483 |
+
"special": false
|
484 |
+
},
|
485 |
+
"63": {
|
486 |
+
"content": "[/NUMSATURATEDRINGS]",
|
487 |
+
"lstrip": false,
|
488 |
+
"normalized": false,
|
489 |
+
"rstrip": false,
|
490 |
+
"single_word": false,
|
491 |
+
"special": false
|
492 |
+
},
|
493 |
+
"64": {
|
494 |
+
"content": "[/NUMAROMATICHETEROCYCLES]",
|
495 |
+
"lstrip": false,
|
496 |
+
"normalized": false,
|
497 |
+
"rstrip": false,
|
498 |
+
"single_word": false,
|
499 |
+
"special": false
|
500 |
+
},
|
501 |
+
"65": {
|
502 |
+
"content": "[/NUMAROMATICCARBOCYCLES]",
|
503 |
+
"lstrip": false,
|
504 |
+
"normalized": false,
|
505 |
+
"rstrip": false,
|
506 |
+
"single_word": false,
|
507 |
+
"special": false
|
508 |
+
},
|
509 |
+
"66": {
|
510 |
+
"content": "[/NUMSATURATEDHETEROCYCLES]",
|
511 |
+
"lstrip": false,
|
512 |
+
"normalized": false,
|
513 |
+
"rstrip": false,
|
514 |
+
"single_word": false,
|
515 |
+
"special": false
|
516 |
+
},
|
517 |
+
"67": {
|
518 |
+
"content": "[/NUMSATURATEDCARBOCYCLES]",
|
519 |
+
"lstrip": false,
|
520 |
+
"normalized": false,
|
521 |
+
"rstrip": false,
|
522 |
+
"single_word": false,
|
523 |
+
"special": false
|
524 |
+
},
|
525 |
+
"68": {
|
526 |
+
"content": "[/NUMALIPHATICRINGS]",
|
527 |
+
"lstrip": false,
|
528 |
+
"normalized": false,
|
529 |
+
"rstrip": false,
|
530 |
+
"single_word": false,
|
531 |
+
"special": false
|
532 |
+
},
|
533 |
+
"69": {
|
534 |
+
"content": "[/NUMALIPHATICHETEROCYCLES]",
|
535 |
+
"lstrip": false,
|
536 |
+
"normalized": false,
|
537 |
+
"rstrip": false,
|
538 |
+
"single_word": false,
|
539 |
+
"special": false
|
540 |
+
},
|
541 |
+
"70": {
|
542 |
+
"content": "[/NUMALIPHATICCARBOCYCLES]",
|
543 |
+
"lstrip": false,
|
544 |
+
"normalized": false,
|
545 |
+
"rstrip": false,
|
546 |
+
"single_word": false,
|
547 |
+
"special": false
|
548 |
+
},
|
549 |
+
"71": {
|
550 |
+
"content": "[/IUPAC]",
|
551 |
+
"lstrip": false,
|
552 |
+
"normalized": false,
|
553 |
+
"rstrip": false,
|
554 |
+
"single_word": false,
|
555 |
+
"special": false
|
556 |
+
},
|
557 |
+
"72": {
|
558 |
+
"content": "[/VAR_NAME]",
|
559 |
+
"lstrip": false,
|
560 |
+
"normalized": false,
|
561 |
+
"rstrip": false,
|
562 |
+
"single_word": false,
|
563 |
+
"special": false
|
564 |
+
},
|
565 |
+
"73": {
|
566 |
+
"content": "[/VAR_DESC]",
|
567 |
+
"lstrip": false,
|
568 |
+
"normalized": false,
|
569 |
+
"rstrip": false,
|
570 |
+
"single_word": false,
|
571 |
+
"special": false
|
572 |
+
},
|
573 |
+
"74": {
|
574 |
+
"content": "[/VAR_VAL]",
|
575 |
+
"lstrip": false,
|
576 |
+
"normalized": false,
|
577 |
+
"rstrip": false,
|
578 |
+
"single_word": false,
|
579 |
+
"special": false
|
580 |
+
},
|
581 |
+
"75": {
|
582 |
+
"content": "[/ASSAY_NAME]",
|
583 |
+
"lstrip": false,
|
584 |
+
"normalized": false,
|
585 |
+
"rstrip": false,
|
586 |
+
"single_word": false,
|
587 |
+
"special": false
|
588 |
+
},
|
589 |
+
"76": {
|
590 |
+
"content": "[/ASSAY_DESC]",
|
591 |
+
"lstrip": false,
|
592 |
+
"normalized": false,
|
593 |
+
"rstrip": false,
|
594 |
+
"single_word": false,
|
595 |
+
"special": false
|
596 |
+
}
|
597 |
+
},
|
598 |
+
"bos_token": "<bos>",
|
599 |
+
"clean_up_tokenization_spaces": false,
|
600 |
+
"eos_token": "<eos>",
|
601 |
+
"legacy": null,
|
602 |
+
"model_max_length": 1000000000000000019884624838656,
|
603 |
+
"pad_token": "<pad>",
|
604 |
+
"sp_model_kwargs": {},
|
605 |
+
"spaces_between_special_tokens": false,
|
606 |
+
"tokenizer_class": "GemmaTokenizer",
|
607 |
+
"unk_token": "<unk>",
|
608 |
+
"use_default_system_prompt": false
|
609 |
+
}
|