RylanSchaeffer commited on
Commit
cdf4aa0
1 Parent(s): 902b326

End of training

Browse files
.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
README.md ADDED
@@ -0,0 +1,428 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: gemma
3
+ base_model: google/gemma-2-2b
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: collapse_gemma-2-2b_hs2_accumulate_iter19_sftsd1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # collapse_gemma-2-2b_hs2_accumulate_iter19_sftsd1
17
+
18
+ This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.0989
21
+ - Num Input Tokens Seen: 97347672
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 8e-06
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 16
43
+ - seed: 1
44
+ - gradient_accumulation_steps: 16
45
+ - total_train_batch_size: 128
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: constant_with_warmup
48
+ - lr_scheduler_warmup_ratio: 0.05
49
+ - num_epochs: 1
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
54
+ |:-------------:|:------:|:----:|:---------------:|:-----------------:|
55
+ | No log | 0 | 0 | 1.3909 | 0 |
56
+ | 1.7174 | 0.0027 | 5 | 1.3909 | 266872 |
57
+ | 1.6111 | 0.0055 | 10 | 1.3836 | 533480 |
58
+ | 1.6539 | 0.0082 | 15 | 1.3631 | 798752 |
59
+ | 1.5642 | 0.0109 | 20 | 1.3338 | 1064288 |
60
+ | 1.6072 | 0.0137 | 25 | 1.2943 | 1338000 |
61
+ | 1.3696 | 0.0164 | 30 | 1.2521 | 1599120 |
62
+ | 1.3166 | 0.0191 | 35 | 1.2246 | 1860216 |
63
+ | 1.2964 | 0.0219 | 40 | 1.1980 | 2128840 |
64
+ | 1.1507 | 0.0246 | 45 | 1.1899 | 2388008 |
65
+ | 1.0819 | 0.0273 | 50 | 1.2120 | 2646856 |
66
+ | 0.9372 | 0.0301 | 55 | 1.2402 | 2912968 |
67
+ | 0.8892 | 0.0328 | 60 | 1.2765 | 3168864 |
68
+ | 0.66 | 0.0355 | 65 | 1.3017 | 3441624 |
69
+ | 0.6357 | 0.0383 | 70 | 1.2970 | 3709896 |
70
+ | 0.5769 | 0.0410 | 75 | 1.3026 | 3977528 |
71
+ | 0.462 | 0.0437 | 80 | 1.3114 | 4243944 |
72
+ | 0.4417 | 0.0465 | 85 | 1.3083 | 4504216 |
73
+ | 0.3348 | 0.0492 | 90 | 1.2831 | 4774880 |
74
+ | 0.3377 | 0.0519 | 95 | 1.2634 | 5037776 |
75
+ | 0.2137 | 0.0547 | 100 | 1.2311 | 5309968 |
76
+ | 0.2449 | 0.0574 | 105 | 1.2508 | 5576496 |
77
+ | 0.2124 | 0.0601 | 110 | 1.2161 | 5841760 |
78
+ | 0.143 | 0.0629 | 115 | 1.2250 | 6108464 |
79
+ | 0.1943 | 0.0656 | 120 | 1.2239 | 6379128 |
80
+ | 0.2212 | 0.0683 | 125 | 1.2073 | 6641224 |
81
+ | 0.2491 | 0.0711 | 130 | 1.2136 | 6907672 |
82
+ | 0.1946 | 0.0738 | 135 | 1.1992 | 7171984 |
83
+ | 0.2037 | 0.0765 | 140 | 1.2021 | 7442496 |
84
+ | 0.1578 | 0.0793 | 145 | 1.1970 | 7705752 |
85
+ | 0.167 | 0.0820 | 150 | 1.2024 | 7974728 |
86
+ | 0.1721 | 0.0847 | 155 | 1.1955 | 8241928 |
87
+ | 0.1745 | 0.0875 | 160 | 1.1828 | 8512416 |
88
+ | 0.1834 | 0.0902 | 165 | 1.1924 | 8783416 |
89
+ | 0.195 | 0.0930 | 170 | 1.1873 | 9051112 |
90
+ | 0.1586 | 0.0957 | 175 | 1.1778 | 9320688 |
91
+ | 0.253 | 0.0984 | 180 | 1.1801 | 9584016 |
92
+ | 0.1373 | 0.1012 | 185 | 1.1771 | 9852488 |
93
+ | 0.1344 | 0.1039 | 190 | 1.1859 | 10123040 |
94
+ | 0.1969 | 0.1066 | 195 | 1.1784 | 10395672 |
95
+ | 0.1556 | 0.1094 | 200 | 1.1778 | 10667736 |
96
+ | 0.1264 | 0.1121 | 205 | 1.1808 | 10931120 |
97
+ | 0.1954 | 0.1148 | 210 | 1.1764 | 11198256 |
98
+ | 0.1253 | 0.1176 | 215 | 1.1737 | 11460848 |
99
+ | 0.1299 | 0.1203 | 220 | 1.1787 | 11728464 |
100
+ | 0.1308 | 0.1230 | 225 | 1.1751 | 11996864 |
101
+ | 0.1496 | 0.1258 | 230 | 1.1661 | 12265288 |
102
+ | 0.1035 | 0.1285 | 235 | 1.1726 | 12531848 |
103
+ | 0.1098 | 0.1312 | 240 | 1.1701 | 12801200 |
104
+ | 0.1262 | 0.1340 | 245 | 1.1676 | 13069368 |
105
+ | 0.1547 | 0.1367 | 250 | 1.1687 | 13337576 |
106
+ | 0.112 | 0.1394 | 255 | 1.1666 | 13599152 |
107
+ | 0.1908 | 0.1422 | 260 | 1.1635 | 13861552 |
108
+ | 0.1643 | 0.1449 | 265 | 1.1591 | 14125760 |
109
+ | 0.1394 | 0.1476 | 270 | 1.1643 | 14394032 |
110
+ | 0.1175 | 0.1504 | 275 | 1.1596 | 14666560 |
111
+ | 0.1004 | 0.1531 | 280 | 1.1663 | 14930664 |
112
+ | 0.0763 | 0.1558 | 285 | 1.1717 | 15192168 |
113
+ | 0.1751 | 0.1586 | 290 | 1.1629 | 15452408 |
114
+ | 0.0951 | 0.1613 | 295 | 1.1617 | 15718392 |
115
+ | 0.1146 | 0.1640 | 300 | 1.1615 | 15986280 |
116
+ | 0.148 | 0.1668 | 305 | 1.1575 | 16250824 |
117
+ | 0.1276 | 0.1695 | 310 | 1.1590 | 16517136 |
118
+ | 0.1763 | 0.1722 | 315 | 1.1576 | 16782864 |
119
+ | 0.1252 | 0.1750 | 320 | 1.1569 | 17051768 |
120
+ | 0.1352 | 0.1777 | 325 | 1.1591 | 17326792 |
121
+ | 0.114 | 0.1804 | 330 | 1.1520 | 17591712 |
122
+ | 0.2198 | 0.1832 | 335 | 1.1503 | 17856864 |
123
+ | 0.1552 | 0.1859 | 340 | 1.1514 | 18117776 |
124
+ | 0.1374 | 0.1886 | 345 | 1.1528 | 18380616 |
125
+ | 0.112 | 0.1914 | 350 | 1.1516 | 18651352 |
126
+ | 0.1037 | 0.1941 | 355 | 1.1473 | 18919872 |
127
+ | 0.0999 | 0.1968 | 360 | 1.1535 | 19188072 |
128
+ | 0.1332 | 0.1996 | 365 | 1.1504 | 19453480 |
129
+ | 0.1847 | 0.2023 | 370 | 1.1541 | 19721152 |
130
+ | 0.071 | 0.2050 | 375 | 1.1536 | 19991456 |
131
+ | 0.1044 | 0.2078 | 380 | 1.1497 | 20254144 |
132
+ | 0.0751 | 0.2105 | 385 | 1.1494 | 20519720 |
133
+ | 0.0616 | 0.2132 | 390 | 1.1556 | 20783688 |
134
+ | 0.1662 | 0.2160 | 395 | 1.1532 | 21044896 |
135
+ | 0.1196 | 0.2187 | 400 | 1.1444 | 21312752 |
136
+ | 0.1694 | 0.2214 | 405 | 1.1478 | 21578272 |
137
+ | 0.2183 | 0.2242 | 410 | 1.1483 | 21848096 |
138
+ | 0.1136 | 0.2269 | 415 | 1.1427 | 22107584 |
139
+ | 0.1043 | 0.2296 | 420 | 1.1470 | 22363472 |
140
+ | 0.149 | 0.2324 | 425 | 1.1466 | 22638288 |
141
+ | 0.0572 | 0.2351 | 430 | 1.1492 | 22906352 |
142
+ | 0.0534 | 0.2378 | 435 | 1.1495 | 23162496 |
143
+ | 0.1239 | 0.2406 | 440 | 1.1466 | 23431224 |
144
+ | 0.1872 | 0.2433 | 445 | 1.1444 | 23701840 |
145
+ | 0.1271 | 0.2460 | 450 | 1.1474 | 23967120 |
146
+ | 0.0885 | 0.2488 | 455 | 1.1438 | 24233048 |
147
+ | 0.1312 | 0.2515 | 460 | 1.1429 | 24501112 |
148
+ | 0.1024 | 0.2542 | 465 | 1.1422 | 24771456 |
149
+ | 0.0965 | 0.2570 | 470 | 1.1436 | 25043256 |
150
+ | 0.0869 | 0.2597 | 475 | 1.1468 | 25308600 |
151
+ | 0.1391 | 0.2624 | 480 | 1.1416 | 25578912 |
152
+ | 0.1503 | 0.2652 | 485 | 1.1383 | 25846392 |
153
+ | 0.1101 | 0.2679 | 490 | 1.1464 | 26120528 |
154
+ | 0.1043 | 0.2706 | 495 | 1.1441 | 26383104 |
155
+ | 0.1182 | 0.2734 | 500 | 1.1391 | 26651176 |
156
+ | 0.0894 | 0.2761 | 505 | 1.1393 | 26915624 |
157
+ | 0.1544 | 0.2789 | 510 | 1.1397 | 27177368 |
158
+ | 0.1456 | 0.2816 | 515 | 1.1360 | 27447576 |
159
+ | 0.1584 | 0.2843 | 520 | 1.1373 | 27713256 |
160
+ | 0.099 | 0.2871 | 525 | 1.1432 | 27973272 |
161
+ | 0.1098 | 0.2898 | 530 | 1.1403 | 28228976 |
162
+ | 0.1108 | 0.2925 | 535 | 1.1378 | 28490496 |
163
+ | 0.1822 | 0.2953 | 540 | 1.1367 | 28765928 |
164
+ | 0.1631 | 0.2980 | 545 | 1.1340 | 29034624 |
165
+ | 0.1329 | 0.3007 | 550 | 1.1336 | 29302688 |
166
+ | 0.1422 | 0.3035 | 555 | 1.1334 | 29564784 |
167
+ | 0.1367 | 0.3062 | 560 | 1.1344 | 29840384 |
168
+ | 0.0854 | 0.3089 | 565 | 1.1351 | 30106576 |
169
+ | 0.1498 | 0.3117 | 570 | 1.1309 | 30378728 |
170
+ | 0.1591 | 0.3144 | 575 | 1.1319 | 30647712 |
171
+ | 0.1223 | 0.3171 | 580 | 1.1338 | 30917512 |
172
+ | 0.127 | 0.3199 | 585 | 1.1334 | 31187240 |
173
+ | 0.1535 | 0.3226 | 590 | 1.1310 | 31450016 |
174
+ | 0.1413 | 0.3253 | 595 | 1.1323 | 31715368 |
175
+ | 0.155 | 0.3281 | 600 | 1.1366 | 31979272 |
176
+ | 0.1003 | 0.3308 | 605 | 1.1341 | 32244656 |
177
+ | 0.0931 | 0.3335 | 610 | 1.1303 | 32510112 |
178
+ | 0.1586 | 0.3363 | 615 | 1.1299 | 32775624 |
179
+ | 0.1098 | 0.3390 | 620 | 1.1318 | 33045312 |
180
+ | 0.1126 | 0.3417 | 625 | 1.1315 | 33315344 |
181
+ | 0.1441 | 0.3445 | 630 | 1.1288 | 33577168 |
182
+ | 0.1377 | 0.3472 | 635 | 1.1275 | 33845000 |
183
+ | 0.1506 | 0.3499 | 640 | 1.1302 | 34113832 |
184
+ | 0.1645 | 0.3527 | 645 | 1.1304 | 34381504 |
185
+ | 0.1134 | 0.3554 | 650 | 1.1293 | 34647712 |
186
+ | 0.0611 | 0.3581 | 655 | 1.1297 | 34917120 |
187
+ | 0.1077 | 0.3609 | 660 | 1.1313 | 35184000 |
188
+ | 0.0922 | 0.3636 | 665 | 1.1290 | 35451320 |
189
+ | 0.1285 | 0.3663 | 670 | 1.1254 | 35713528 |
190
+ | 0.1775 | 0.3691 | 675 | 1.1269 | 35979648 |
191
+ | 0.1231 | 0.3718 | 680 | 1.1264 | 36251280 |
192
+ | 0.0869 | 0.3745 | 685 | 1.1267 | 36523080 |
193
+ | 0.0755 | 0.3773 | 690 | 1.1253 | 36792800 |
194
+ | 0.1084 | 0.3800 | 695 | 1.1256 | 37061576 |
195
+ | 0.165 | 0.3827 | 700 | 1.1245 | 37327536 |
196
+ | 0.0832 | 0.3855 | 705 | 1.1248 | 37595088 |
197
+ | 0.1449 | 0.3882 | 710 | 1.1255 | 37853128 |
198
+ | 0.1484 | 0.3909 | 715 | 1.1254 | 38118408 |
199
+ | 0.09 | 0.3937 | 720 | 1.1238 | 38389056 |
200
+ | 0.113 | 0.3964 | 725 | 1.1243 | 38660160 |
201
+ | 0.1209 | 0.3991 | 730 | 1.1241 | 38933408 |
202
+ | 0.1019 | 0.4019 | 735 | 1.1241 | 39203408 |
203
+ | 0.0974 | 0.4046 | 740 | 1.1241 | 39472776 |
204
+ | 0.1233 | 0.4073 | 745 | 1.1244 | 39735160 |
205
+ | 0.101 | 0.4101 | 750 | 1.1258 | 39997392 |
206
+ | 0.1051 | 0.4128 | 755 | 1.1240 | 40264792 |
207
+ | 0.1002 | 0.4155 | 760 | 1.1228 | 40531920 |
208
+ | 0.1039 | 0.4183 | 765 | 1.1228 | 40798440 |
209
+ | 0.1661 | 0.4210 | 770 | 1.1213 | 41065784 |
210
+ | 0.1615 | 0.4237 | 775 | 1.1208 | 41333064 |
211
+ | 0.1364 | 0.4265 | 780 | 1.1209 | 41604728 |
212
+ | 0.1646 | 0.4292 | 785 | 1.1200 | 41872328 |
213
+ | 0.1234 | 0.4319 | 790 | 1.1210 | 42139912 |
214
+ | 0.1313 | 0.4347 | 795 | 1.1219 | 42397864 |
215
+ | 0.1858 | 0.4374 | 800 | 1.1201 | 42663312 |
216
+ | 0.1786 | 0.4401 | 805 | 1.1196 | 42928792 |
217
+ | 0.1706 | 0.4429 | 810 | 1.1215 | 43193840 |
218
+ | 0.1255 | 0.4456 | 815 | 1.1221 | 43457720 |
219
+ | 0.1275 | 0.4483 | 820 | 1.1205 | 43721200 |
220
+ | 0.1364 | 0.4511 | 825 | 1.1197 | 43981648 |
221
+ | 0.1311 | 0.4538 | 830 | 1.1208 | 44243536 |
222
+ | 0.1631 | 0.4565 | 835 | 1.1188 | 44508888 |
223
+ | 0.0923 | 0.4593 | 840 | 1.1175 | 44771440 |
224
+ | 0.1563 | 0.4620 | 845 | 1.1187 | 45042352 |
225
+ | 0.1156 | 0.4648 | 850 | 1.1180 | 45308520 |
226
+ | 0.0881 | 0.4675 | 855 | 1.1167 | 45581968 |
227
+ | 0.1758 | 0.4702 | 860 | 1.1189 | 45843704 |
228
+ | 0.0746 | 0.4730 | 865 | 1.1177 | 46113504 |
229
+ | 0.1186 | 0.4757 | 870 | 1.1182 | 46385088 |
230
+ | 0.0735 | 0.4784 | 875 | 1.1213 | 46646384 |
231
+ | 0.2116 | 0.4812 | 880 | 1.1207 | 46917848 |
232
+ | 0.1127 | 0.4839 | 885 | 1.1182 | 47182968 |
233
+ | 0.1042 | 0.4866 | 890 | 1.1196 | 47446872 |
234
+ | 0.1461 | 0.4894 | 895 | 1.1195 | 47705216 |
235
+ | 0.0872 | 0.4921 | 900 | 1.1166 | 47967064 |
236
+ | 0.1396 | 0.4948 | 905 | 1.1179 | 48227312 |
237
+ | 0.0739 | 0.4976 | 910 | 1.1200 | 48489816 |
238
+ | 0.1089 | 0.5003 | 915 | 1.1187 | 48761464 |
239
+ | 0.1124 | 0.5030 | 920 | 1.1156 | 49033200 |
240
+ | 0.1094 | 0.5058 | 925 | 1.1175 | 49292616 |
241
+ | 0.0829 | 0.5085 | 930 | 1.1193 | 49552456 |
242
+ | 0.1111 | 0.5112 | 935 | 1.1186 | 49826560 |
243
+ | 0.1273 | 0.5140 | 940 | 1.1157 | 50094336 |
244
+ | 0.0794 | 0.5167 | 945 | 1.1146 | 50354616 |
245
+ | 0.1021 | 0.5194 | 950 | 1.1163 | 50621536 |
246
+ | 0.0732 | 0.5222 | 955 | 1.1158 | 50887048 |
247
+ | 0.0998 | 0.5249 | 960 | 1.1159 | 51151256 |
248
+ | 0.1084 | 0.5276 | 965 | 1.1155 | 51412592 |
249
+ | 0.1076 | 0.5304 | 970 | 1.1158 | 51688216 |
250
+ | 0.1269 | 0.5331 | 975 | 1.1162 | 51953136 |
251
+ | 0.1242 | 0.5358 | 980 | 1.1123 | 52220944 |
252
+ | 0.1208 | 0.5386 | 985 | 1.1121 | 52491440 |
253
+ | 0.1058 | 0.5413 | 990 | 1.1161 | 52756560 |
254
+ | 0.1193 | 0.5440 | 995 | 1.1158 | 53021512 |
255
+ | 0.1141 | 0.5468 | 1000 | 1.1148 | 53285184 |
256
+ | 0.0977 | 0.5495 | 1005 | 1.1143 | 53551680 |
257
+ | 0.1648 | 0.5522 | 1010 | 1.1152 | 53810640 |
258
+ | 0.0852 | 0.5550 | 1015 | 1.1145 | 54082336 |
259
+ | 0.0862 | 0.5577 | 1020 | 1.1149 | 54344200 |
260
+ | 0.1324 | 0.5604 | 1025 | 1.1131 | 54614792 |
261
+ | 0.1159 | 0.5632 | 1030 | 1.1129 | 54878824 |
262
+ | 0.1012 | 0.5659 | 1035 | 1.1133 | 55141696 |
263
+ | 0.1036 | 0.5686 | 1040 | 1.1129 | 55408024 |
264
+ | 0.1005 | 0.5714 | 1045 | 1.1143 | 55673224 |
265
+ | 0.099 | 0.5741 | 1050 | 1.1144 | 55932544 |
266
+ | 0.0815 | 0.5768 | 1055 | 1.1137 | 56204976 |
267
+ | 0.1428 | 0.5796 | 1060 | 1.1144 | 56473248 |
268
+ | 0.1014 | 0.5823 | 1065 | 1.1131 | 56736352 |
269
+ | 0.1504 | 0.5850 | 1070 | 1.1119 | 57002088 |
270
+ | 0.1862 | 0.5878 | 1075 | 1.1121 | 57270184 |
271
+ | 0.1479 | 0.5905 | 1080 | 1.1120 | 57535360 |
272
+ | 0.0756 | 0.5932 | 1085 | 1.1126 | 57795104 |
273
+ | 0.0757 | 0.5960 | 1090 | 1.1120 | 58060920 |
274
+ | 0.0789 | 0.5987 | 1095 | 1.1123 | 58324808 |
275
+ | 0.1916 | 0.6014 | 1100 | 1.1130 | 58597928 |
276
+ | 0.071 | 0.6042 | 1105 | 1.1138 | 58865144 |
277
+ | 0.0851 | 0.6069 | 1110 | 1.1145 | 59128872 |
278
+ | 0.1405 | 0.6096 | 1115 | 1.1131 | 59387232 |
279
+ | 0.1295 | 0.6124 | 1120 | 1.1129 | 59651736 |
280
+ | 0.1431 | 0.6151 | 1125 | 1.1125 | 59915648 |
281
+ | 0.0855 | 0.6178 | 1130 | 1.1110 | 60179680 |
282
+ | 0.0987 | 0.6206 | 1135 | 1.1112 | 60444144 |
283
+ | 0.1198 | 0.6233 | 1140 | 1.1123 | 60721040 |
284
+ | 0.0887 | 0.6260 | 1145 | 1.1132 | 60988096 |
285
+ | 0.0983 | 0.6288 | 1150 | 1.1129 | 61258776 |
286
+ | 0.1265 | 0.6315 | 1155 | 1.1103 | 61527712 |
287
+ | 0.1088 | 0.6342 | 1160 | 1.1103 | 61794696 |
288
+ | 0.1348 | 0.6370 | 1165 | 1.1102 | 62054248 |
289
+ | 0.1188 | 0.6397 | 1170 | 1.1095 | 62319720 |
290
+ | 0.1353 | 0.6424 | 1175 | 1.1085 | 62583520 |
291
+ | 0.1576 | 0.6452 | 1180 | 1.1094 | 62846952 |
292
+ | 0.144 | 0.6479 | 1185 | 1.1093 | 63109192 |
293
+ | 0.1301 | 0.6507 | 1190 | 1.1102 | 63376000 |
294
+ | 0.1294 | 0.6534 | 1195 | 1.1087 | 63649096 |
295
+ | 0.0582 | 0.6561 | 1200 | 1.1069 | 63912744 |
296
+ | 0.1204 | 0.6589 | 1205 | 1.1078 | 64183184 |
297
+ | 0.1144 | 0.6616 | 1210 | 1.1104 | 64449936 |
298
+ | 0.1283 | 0.6643 | 1215 | 1.1106 | 64721056 |
299
+ | 0.1285 | 0.6671 | 1220 | 1.1077 | 64989128 |
300
+ | 0.1485 | 0.6698 | 1225 | 1.1069 | 65260248 |
301
+ | 0.1212 | 0.6725 | 1230 | 1.1095 | 65526968 |
302
+ | 0.1125 | 0.6753 | 1235 | 1.1114 | 65799712 |
303
+ | 0.1163 | 0.6780 | 1240 | 1.1083 | 66060384 |
304
+ | 0.1114 | 0.6807 | 1245 | 1.1078 | 66326384 |
305
+ | 0.1346 | 0.6835 | 1250 | 1.1074 | 66593160 |
306
+ | 0.1733 | 0.6862 | 1255 | 1.1087 | 66862232 |
307
+ | 0.1032 | 0.6889 | 1260 | 1.1088 | 67126144 |
308
+ | 0.1231 | 0.6917 | 1265 | 1.1073 | 67392880 |
309
+ | 0.1085 | 0.6944 | 1270 | 1.1074 | 67654488 |
310
+ | 0.0974 | 0.6971 | 1275 | 1.1098 | 67925984 |
311
+ | 0.143 | 0.6999 | 1280 | 1.1086 | 68188296 |
312
+ | 0.0838 | 0.7026 | 1285 | 1.1080 | 68448560 |
313
+ | 0.0976 | 0.7053 | 1290 | 1.1078 | 68708864 |
314
+ | 0.1292 | 0.7081 | 1295 | 1.1082 | 68978056 |
315
+ | 0.1044 | 0.7108 | 1300 | 1.1066 | 69243568 |
316
+ | 0.0977 | 0.7135 | 1305 | 1.1062 | 69515200 |
317
+ | 0.1286 | 0.7163 | 1310 | 1.1068 | 69778120 |
318
+ | 0.0776 | 0.7190 | 1315 | 1.1091 | 70048128 |
319
+ | 0.1029 | 0.7217 | 1320 | 1.1088 | 70318440 |
320
+ | 0.1214 | 0.7245 | 1325 | 1.1049 | 70585080 |
321
+ | 0.1093 | 0.7272 | 1330 | 1.1057 | 70848152 |
322
+ | 0.1311 | 0.7299 | 1335 | 1.1075 | 71114672 |
323
+ | 0.1728 | 0.7327 | 1340 | 1.1072 | 71381384 |
324
+ | 0.0732 | 0.7354 | 1345 | 1.1070 | 71643776 |
325
+ | 0.1181 | 0.7381 | 1350 | 1.1057 | 71913728 |
326
+ | 0.1417 | 0.7409 | 1355 | 1.1044 | 72172432 |
327
+ | 0.1179 | 0.7436 | 1360 | 1.1044 | 72443984 |
328
+ | 0.1062 | 0.7463 | 1365 | 1.1062 | 72706712 |
329
+ | 0.1212 | 0.7491 | 1370 | 1.1062 | 72966264 |
330
+ | 0.0653 | 0.7518 | 1375 | 1.1064 | 73229856 |
331
+ | 0.0924 | 0.7545 | 1380 | 1.1070 | 73494304 |
332
+ | 0.1094 | 0.7573 | 1385 | 1.1106 | 73749552 |
333
+ | 0.077 | 0.7600 | 1390 | 1.1096 | 74017720 |
334
+ | 0.0813 | 0.7627 | 1395 | 1.1070 | 74288168 |
335
+ | 0.0769 | 0.7655 | 1400 | 1.1065 | 74552176 |
336
+ | 0.1347 | 0.7682 | 1405 | 1.1064 | 74824184 |
337
+ | 0.1235 | 0.7709 | 1410 | 1.1061 | 75096184 |
338
+ | 0.0896 | 0.7737 | 1415 | 1.1064 | 75362984 |
339
+ | 0.0577 | 0.7764 | 1420 | 1.1071 | 75627968 |
340
+ | 0.1215 | 0.7791 | 1425 | 1.1068 | 75894216 |
341
+ | 0.1134 | 0.7819 | 1430 | 1.1058 | 76159136 |
342
+ | 0.1123 | 0.7846 | 1435 | 1.1058 | 76419272 |
343
+ | 0.1205 | 0.7873 | 1440 | 1.1040 | 76685336 |
344
+ | 0.1133 | 0.7901 | 1445 | 1.1027 | 76957096 |
345
+ | 0.1248 | 0.7928 | 1450 | 1.1040 | 77217888 |
346
+ | 0.0701 | 0.7955 | 1455 | 1.1051 | 77488320 |
347
+ | 0.1221 | 0.7983 | 1460 | 1.1049 | 77757352 |
348
+ | 0.0991 | 0.8010 | 1465 | 1.1030 | 78023408 |
349
+ | 0.089 | 0.8037 | 1470 | 1.1040 | 78288408 |
350
+ | 0.1273 | 0.8065 | 1475 | 1.1056 | 78558544 |
351
+ | 0.0915 | 0.8092 | 1480 | 1.1055 | 78824864 |
352
+ | 0.0628 | 0.8119 | 1485 | 1.1039 | 79099824 |
353
+ | 0.1077 | 0.8147 | 1490 | 1.1039 | 79365768 |
354
+ | 0.1935 | 0.8174 | 1495 | 1.1029 | 79628872 |
355
+ | 0.0713 | 0.8201 | 1500 | 1.1043 | 79900120 |
356
+ | 0.0789 | 0.8229 | 1505 | 1.1056 | 80163648 |
357
+ | 0.123 | 0.8256 | 1510 | 1.1051 | 80432696 |
358
+ | 0.1038 | 0.8283 | 1515 | 1.1049 | 80694800 |
359
+ | 0.1123 | 0.8311 | 1520 | 1.1051 | 80959272 |
360
+ | 0.132 | 0.8338 | 1525 | 1.1041 | 81223352 |
361
+ | 0.0983 | 0.8366 | 1530 | 1.1025 | 81498336 |
362
+ | 0.1214 | 0.8393 | 1535 | 1.1018 | 81766760 |
363
+ | 0.1245 | 0.8420 | 1540 | 1.1025 | 82042960 |
364
+ | 0.1174 | 0.8448 | 1545 | 1.1025 | 82314968 |
365
+ | 0.1163 | 0.8475 | 1550 | 1.1035 | 82580512 |
366
+ | 0.1451 | 0.8502 | 1555 | 1.1045 | 82846256 |
367
+ | 0.0875 | 0.8530 | 1560 | 1.1049 | 83108696 |
368
+ | 0.1221 | 0.8557 | 1565 | 1.1036 | 83372312 |
369
+ | 0.1077 | 0.8584 | 1570 | 1.1036 | 83638264 |
370
+ | 0.0804 | 0.8612 | 1575 | 1.1036 | 83894392 |
371
+ | 0.0911 | 0.8639 | 1580 | 1.1037 | 84161608 |
372
+ | 0.1219 | 0.8666 | 1585 | 1.1021 | 84424240 |
373
+ | 0.1646 | 0.8694 | 1590 | 1.1017 | 84688504 |
374
+ | 0.0952 | 0.8721 | 1595 | 1.1033 | 84950376 |
375
+ | 0.062 | 0.8748 | 1600 | 1.1045 | 85213256 |
376
+ | 0.067 | 0.8776 | 1605 | 1.1032 | 85481688 |
377
+ | 0.1024 | 0.8803 | 1610 | 1.1029 | 85751680 |
378
+ | 0.0792 | 0.8830 | 1615 | 1.1034 | 86021808 |
379
+ | 0.1521 | 0.8858 | 1620 | 1.1025 | 86289944 |
380
+ | 0.0585 | 0.8885 | 1625 | 1.1008 | 86549808 |
381
+ | 0.092 | 0.8912 | 1630 | 1.1009 | 86813904 |
382
+ | 0.0779 | 0.8940 | 1635 | 1.1019 | 87072840 |
383
+ | 0.1313 | 0.8967 | 1640 | 1.1027 | 87337552 |
384
+ | 0.1186 | 0.8994 | 1645 | 1.1029 | 87600144 |
385
+ | 0.1334 | 0.9022 | 1650 | 1.1008 | 87867616 |
386
+ | 0.1465 | 0.9049 | 1655 | 1.1005 | 88132784 |
387
+ | 0.0896 | 0.9076 | 1660 | 1.1007 | 88400488 |
388
+ | 0.0844 | 0.9104 | 1665 | 1.1014 | 88661864 |
389
+ | 0.1133 | 0.9131 | 1670 | 1.0998 | 88930432 |
390
+ | 0.1254 | 0.9158 | 1675 | 1.0997 | 89197224 |
391
+ | 0.0872 | 0.9186 | 1680 | 1.1013 | 89459416 |
392
+ | 0.0894 | 0.9213 | 1685 | 1.1026 | 89714824 |
393
+ | 0.0966 | 0.9240 | 1690 | 1.1038 | 89973008 |
394
+ | 0.1306 | 0.9268 | 1695 | 1.1028 | 90242312 |
395
+ | 0.0966 | 0.9295 | 1700 | 1.1016 | 90516664 |
396
+ | 0.109 | 0.9322 | 1705 | 1.1015 | 90782296 |
397
+ | 0.1459 | 0.9350 | 1710 | 1.1029 | 91046216 |
398
+ | 0.1263 | 0.9377 | 1715 | 1.1004 | 91314592 |
399
+ | 0.1455 | 0.9404 | 1720 | 1.0983 | 91581592 |
400
+ | 0.1634 | 0.9432 | 1725 | 1.0994 | 91845936 |
401
+ | 0.0472 | 0.9459 | 1730 | 1.1003 | 92114760 |
402
+ | 0.0649 | 0.9486 | 1735 | 1.1010 | 92377432 |
403
+ | 0.1087 | 0.9514 | 1740 | 1.1003 | 92639184 |
404
+ | 0.1317 | 0.9541 | 1745 | 1.1001 | 92903664 |
405
+ | 0.1633 | 0.9568 | 1750 | 1.1007 | 93179160 |
406
+ | 0.094 | 0.9596 | 1755 | 1.1005 | 93443368 |
407
+ | 0.0891 | 0.9623 | 1760 | 1.1010 | 93705928 |
408
+ | 0.1061 | 0.9650 | 1765 | 1.1010 | 93969520 |
409
+ | 0.1436 | 0.9678 | 1770 | 1.1004 | 94239728 |
410
+ | 0.0803 | 0.9705 | 1775 | 1.0998 | 94506160 |
411
+ | 0.0969 | 0.9732 | 1780 | 1.1000 | 94762856 |
412
+ | 0.0774 | 0.9760 | 1785 | 1.0999 | 95024512 |
413
+ | 0.1144 | 0.9787 | 1790 | 1.1006 | 95295264 |
414
+ | 0.1836 | 0.9814 | 1795 | 1.0992 | 95565808 |
415
+ | 0.0989 | 0.9842 | 1800 | 1.0981 | 95836072 |
416
+ | 0.0852 | 0.9869 | 1805 | 1.0993 | 96100928 |
417
+ | 0.0859 | 0.9896 | 1810 | 1.0999 | 96375008 |
418
+ | 0.1832 | 0.9924 | 1815 | 1.0995 | 96648680 |
419
+ | 0.0998 | 0.9951 | 1820 | 1.0992 | 96918672 |
420
+ | 0.0748 | 0.9978 | 1825 | 1.0992 | 97185832 |
421
+
422
+
423
+ ### Framework versions
424
+
425
+ - Transformers 4.44.0
426
+ - Pytorch 2.4.0+cu121
427
+ - Datasets 2.20.0
428
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-2-2b",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 2304,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 9216,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "gemma2",
21
+ "num_attention_heads": 8,
22
+ "num_hidden_layers": 26,
23
+ "num_key_value_heads": 4,
24
+ "pad_token_id": 0,
25
+ "query_pre_attn_scalar": 256,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_theta": 10000.0,
28
+ "sliding_window": 4096,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.44.0",
31
+ "use_cache": true,
32
+ "vocab_size": 256000
33
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.44.0"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e24c9a152063494c35d5eeb057812b1aef8e42a2ec7feed886a63dd2909ee6fc
3
+ size 4988025760
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55e8dc5814efc815343460c16366f4d10385732ebdd55085b4af34a97893a2a
3
+ size 240691728
model.safetensors.index.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5228683776
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.norm.weight": "model-00002-of-00002.safetensors"
294
+ }
295
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
3
+ size 17525357
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,2012 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "additional_special_tokens": [
1999
+ "<start_of_turn>",
2000
+ "<end_of_turn>"
2001
+ ],
2002
+ "bos_token": "<bos>",
2003
+ "clean_up_tokenization_spaces": false,
2004
+ "eos_token": "<eos>",
2005
+ "model_max_length": 1000000000000000019884624838656,
2006
+ "pad_token": "<pad>",
2007
+ "sp_model_kwargs": {},
2008
+ "spaces_between_special_tokens": false,
2009
+ "tokenizer_class": "GemmaTokenizer",
2010
+ "unk_token": "<unk>",
2011
+ "use_default_system_prompt": false
2012
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0623c14a85efabd43369e67f70bf65882e95757a5d70309cd698949036f3b8
3
+ size 5624