IlyasMoutawwakil HF Staff commited on
Commit
baa0dbb
·
verified ·
1 Parent(s): f644a7f

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. FlavaImageCodebook/config.json +14 -0
  2. FlavaImageCodebook/model.safetensors +3 -0
  3. FlavaImageCodebook/preprocessor_config.json +58 -0
  4. FlavaImageCodebook/tokenizer.json +1174 -0
  5. FlavaImageCodebook/tokenizer_config.json +16 -0
  6. afmoe/AfmoeForCausalLM/chat_template.jinja +68 -0
  7. afmoe/AfmoeForCausalLM/config.json +44 -0
  8. afmoe/AfmoeForCausalLM/generation_config.json +10 -0
  9. afmoe/AfmoeForCausalLM/model.safetensors +3 -0
  10. afmoe/AfmoeForCausalLM/tokenizer.json +4415 -0
  11. afmoe/AfmoeForCausalLM/tokenizer_config.json +13 -0
  12. afmoe/AfmoeModel/chat_template.jinja +68 -0
  13. afmoe/AfmoeModel/config.json +44 -0
  14. afmoe/AfmoeModel/model.safetensors +3 -0
  15. afmoe/AfmoeModel/tokenizer.json +4415 -0
  16. afmoe/AfmoeModel/tokenizer_config.json +13 -0
  17. aimv2/Aimv2Model/config.json +50 -0
  18. aimv2/Aimv2Model/model.safetensors +3 -0
  19. aimv2/Aimv2Model/preprocessor_config.json +27 -0
  20. aimv2/Aimv2Model/tokenizer.json +3735 -0
  21. aimv2/Aimv2Model/tokenizer_config.json +15 -0
  22. aimv2_text_model/Aimv2TextModel/config.json +23 -0
  23. aimv2_text_model/Aimv2TextModel/model.safetensors +3 -0
  24. aimv2_text_model/Aimv2TextModel/preprocessor_config.json +29 -0
  25. aimv2_text_model/Aimv2TextModel/tokenizer.json +3735 -0
  26. aimv2_text_model/Aimv2TextModel/tokenizer_config.json +15 -0
  27. aimv2_vision_model/Aimv2VisionModel/config.json +25 -0
  28. aimv2_vision_model/Aimv2VisionModel/model.safetensors +3 -0
  29. aimv2_vision_model/Aimv2VisionModel/preprocessor_config.json +27 -0
  30. aimv2_vision_model/Aimv2VisionModel/tokenizer.json +3735 -0
  31. aimv2_vision_model/Aimv2VisionModel/tokenizer_config.json +15 -0
  32. albert/AlbertForMaskedLM/config.json +28 -0
  33. albert/AlbertForMaskedLM/model.safetensors +3 -0
  34. albert/AlbertForMaskedLM/tokenizer.json +0 -0
  35. albert/AlbertForMaskedLM/tokenizer_config.json +18 -0
  36. albert/AlbertForMultipleChoice/config.json +28 -0
  37. albert/AlbertForMultipleChoice/model.safetensors +3 -0
  38. albert/AlbertForMultipleChoice/tokenizer.json +0 -0
  39. albert/AlbertForMultipleChoice/tokenizer_config.json +18 -0
  40. albert/AlbertForPreTraining/config.json +28 -0
  41. albert/AlbertForPreTraining/model.safetensors +3 -0
  42. albert/AlbertForPreTraining/tokenizer.json +0 -0
  43. albert/AlbertForPreTraining/tokenizer_config.json +18 -0
  44. albert/AlbertForQuestionAnswering/config.json +28 -0
  45. albert/AlbertForQuestionAnswering/model.safetensors +3 -0
  46. albert/AlbertForQuestionAnswering/tokenizer.json +0 -0
  47. albert/AlbertForQuestionAnswering/tokenizer_config.json +18 -0
  48. albert/AlbertForSequenceClassification/config.json +28 -0
  49. albert/AlbertForSequenceClassification/model.safetensors +3 -0
  50. albert/AlbertForSequenceClassification/tokenizer.json +0 -0
FlavaImageCodebook/config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FlavaImageCodebook"
4
+ ],
5
+ "dtype": "float32",
6
+ "freeze": true,
7
+ "hidden_size": 32,
8
+ "initializer_range": 0.02,
9
+ "input_channels": 3,
10
+ "num_blocks_per_group": 2,
11
+ "num_groups": 2,
12
+ "transformers_version": "5.15.0.dev0",
13
+ "vocab_size": 1024
14
+ }
FlavaImageCodebook/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52beec0b854031c7a27c0e55e50c2537e62169b923d99eaac0372f4775b3346
3
+ size 3398040
FlavaImageCodebook/preprocessor_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "codebook_crop_size": {
3
+ "height": 112,
4
+ "width": 112
5
+ },
6
+ "codebook_do_center_crop": true,
7
+ "codebook_do_map_pixels": true,
8
+ "codebook_do_normalize": true,
9
+ "codebook_do_rescale": true,
10
+ "codebook_do_resize": true,
11
+ "codebook_image_mean": [
12
+ 0.0,
13
+ 0.0,
14
+ 0.0
15
+ ],
16
+ "codebook_image_std": [
17
+ 1.0,
18
+ 1.0,
19
+ 1.0
20
+ ],
21
+ "codebook_resample": 1,
22
+ "codebook_rescale_factor": 0.00392156862745098,
23
+ "codebook_size": {
24
+ "height": 112,
25
+ "width": 112
26
+ },
27
+ "crop_size": {
28
+ "height": 224,
29
+ "width": 224
30
+ },
31
+ "do_center_crop": true,
32
+ "do_normalize": true,
33
+ "do_rescale": true,
34
+ "do_resize": true,
35
+ "image_mean": [
36
+ 0.48145466,
37
+ 0.4578275,
38
+ 0.40821073
39
+ ],
40
+ "image_processor_type": "FlavaImageProcessor",
41
+ "image_std": [
42
+ 0.26862954,
43
+ 0.26130258,
44
+ 0.27577711
45
+ ],
46
+ "input_size_patches": 14,
47
+ "mask_group_min_aspect_ratio": 0.3,
48
+ "mask_group_min_patches": 16,
49
+ "resample": 3,
50
+ "rescale_factor": 0.00392156862745098,
51
+ "return_codebook_pixels": false,
52
+ "return_image_mask": false,
53
+ "size": {
54
+ "height": 224,
55
+ "width": 224
56
+ },
57
+ "total_mask_patches": 75
58
+ }
FlavaImageCodebook/tokenizer.json ADDED
@@ -0,0 +1,1174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": {
53
+ "type": "BertNormalizer",
54
+ "clean_text": true,
55
+ "handle_chinese_chars": true,
56
+ "strip_accents": null,
57
+ "lowercase": true
58
+ },
59
+ "pre_tokenizer": {
60
+ "type": "BertPreTokenizer"
61
+ },
62
+ "post_processor": {
63
+ "type": "TemplateProcessing",
64
+ "single": [
65
+ {
66
+ "SpecialToken": {
67
+ "id": "[CLS]",
68
+ "type_id": 0
69
+ }
70
+ },
71
+ {
72
+ "Sequence": {
73
+ "id": "A",
74
+ "type_id": 0
75
+ }
76
+ },
77
+ {
78
+ "SpecialToken": {
79
+ "id": "[SEP]",
80
+ "type_id": 0
81
+ }
82
+ }
83
+ ],
84
+ "pair": [
85
+ {
86
+ "SpecialToken": {
87
+ "id": "[CLS]",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "SpecialToken": {
99
+ "id": "[SEP]",
100
+ "type_id": 0
101
+ }
102
+ },
103
+ {
104
+ "Sequence": {
105
+ "id": "B",
106
+ "type_id": 1
107
+ }
108
+ },
109
+ {
110
+ "SpecialToken": {
111
+ "id": "[SEP]",
112
+ "type_id": 1
113
+ }
114
+ }
115
+ ],
116
+ "special_tokens": {
117
+ "[CLS]": {
118
+ "id": "[CLS]",
119
+ "ids": [
120
+ 2
121
+ ],
122
+ "tokens": [
123
+ "[CLS]"
124
+ ]
125
+ },
126
+ "[SEP]": {
127
+ "id": "[SEP]",
128
+ "ids": [
129
+ 3
130
+ ],
131
+ "tokens": [
132
+ "[SEP]"
133
+ ]
134
+ }
135
+ }
136
+ },
137
+ "decoder": {
138
+ "type": "WordPiece",
139
+ "prefix": "##",
140
+ "cleanup": true
141
+ },
142
+ "model": {
143
+ "type": "WordPiece",
144
+ "unk_token": "[UNK]",
145
+ "continuing_subword_prefix": "##",
146
+ "max_input_chars_per_word": 100,
147
+ "vocab": {
148
+ "[PAD]": 0,
149
+ "[UNK]": 1,
150
+ "[CLS]": 2,
151
+ "[SEP]": 3,
152
+ "[MASK]": 4,
153
+ "!": 5,
154
+ "\"": 6,
155
+ "#": 7,
156
+ "$": 8,
157
+ "%": 9,
158
+ "&": 10,
159
+ "'": 11,
160
+ "(": 12,
161
+ ")": 13,
162
+ "*": 14,
163
+ "+": 15,
164
+ ",": 16,
165
+ "-": 17,
166
+ ".": 18,
167
+ "/": 19,
168
+ "0": 20,
169
+ "1": 21,
170
+ "2": 22,
171
+ "3": 23,
172
+ "4": 24,
173
+ "5": 25,
174
+ "6": 26,
175
+ "7": 27,
176
+ "8": 28,
177
+ "9": 29,
178
+ ":": 30,
179
+ ";": 31,
180
+ "<": 32,
181
+ "=": 33,
182
+ ">": 34,
183
+ "?": 35,
184
+ "@": 36,
185
+ "[": 37,
186
+ "]": 38,
187
+ "^": 39,
188
+ "`": 40,
189
+ "a": 41,
190
+ "b": 42,
191
+ "c": 43,
192
+ "d": 44,
193
+ "e": 45,
194
+ "f": 46,
195
+ "g": 47,
196
+ "h": 48,
197
+ "i": 49,
198
+ "j": 50,
199
+ "k": 51,
200
+ "l": 52,
201
+ "m": 53,
202
+ "n": 54,
203
+ "o": 55,
204
+ "p": 56,
205
+ "q": 57,
206
+ "r": 58,
207
+ "s": 59,
208
+ "t": 60,
209
+ "u": 61,
210
+ "v": 62,
211
+ "w": 63,
212
+ "x": 64,
213
+ "y": 65,
214
+ "z": 66,
215
+ "~": 67,
216
+ "£": 68,
217
+ "°": 69,
218
+ "²": 70,
219
+ "´": 71,
220
+ "µ": 72,
221
+ "º": 73,
222
+ "×": 74,
223
+ "ß": 75,
224
+ "æ": 76,
225
+ "đ": 77,
226
+ "ł": 78,
227
+ "ə": 79,
228
+ "ɡ": 80,
229
+ "ɪ": 81,
230
+ "ˈ": 82,
231
+ "α": 83,
232
+ "β": 84,
233
+ "γ": 85,
234
+ "δ": 86,
235
+ "ε": 87,
236
+ "η": 88,
237
+ "θ": 89,
238
+ "ι": 90,
239
+ "κ": 91,
240
+ "λ": 92,
241
+ "μ": 93,
242
+ "ν": 94,
243
+ "ξ": 95,
244
+ "ο": 96,
245
+ "ρ": 97,
246
+ "ς": 98,
247
+ "σ": 99,
248
+ "τ": 100,
249
+ "υ": 101,
250
+ "χ": 102,
251
+ "а": 103,
252
+ "в": 104,
253
+ "з": 105,
254
+ "и": 106,
255
+ "к": 107,
256
+ "н": 108,
257
+ "р": 109,
258
+ "с": 110,
259
+ "ы": 111,
260
+ "є": 112,
261
+ "ה": 113,
262
+ "מ": 114,
263
+ "צ": 115,
264
+ "ש": 116,
265
+ "ا": 117,
266
+ "ت": 118,
267
+ "ث": 119,
268
+ "د": 120,
269
+ "س": 121,
270
+ "م": 122,
271
+ "ي": 123,
272
+ "ก": 124,
273
+ "ค": 125,
274
+ "ง": 126,
275
+ "ช": 127,
276
+ "ซ": 128,
277
+ "ญ": 129,
278
+ "ฐ": 130,
279
+ "ณ": 131,
280
+ "ด": 132,
281
+ "ต": 133,
282
+ "บ": 134,
283
+ "ป": 135,
284
+ "พ": 136,
285
+ "ภ": 137,
286
+ "ม": 138,
287
+ "ย": 139,
288
+ "ร": 140,
289
+ "ล": 141,
290
+ "ว": 142,
291
+ "ศ": 143,
292
+ "ษ": 144,
293
+ "ส": 145,
294
+ "ห": 146,
295
+ "อ": 147,
296
+ "า": 148,
297
+ "เ": 149,
298
+ "แ": 150,
299
+ "ไ": 151,
300
+ "ᵻ": 152,
301
+ "–": 153,
302
+ "—": 154,
303
+ "‘": 155,
304
+ "’": 156,
305
+ "“": 157,
306
+ "”": 158,
307
+ "†": 159,
308
+ "‡": 160,
309
+ "…": 161,
310
+ "⁄": 162,
311
+ "₤": 163,
312
+ "₹": 164,
313
+ "→": 165,
314
+ "−": 166,
315
+ "い": 167,
316
+ "う": 168,
317
+ "か": 169,
318
+ "き": 170,
319
+ "く": 171,
320
+ "し": 172,
321
+ "た": 173,
322
+ "つ": 174,
323
+ "な": 175,
324
+ "の": 176,
325
+ "め": 177,
326
+ "も": 178,
327
+ "ら": 179,
328
+ "ァ": 180,
329
+ "ア": 181,
330
+ "ウ": 182,
331
+ "キ": 183,
332
+ "ュ": 184,
333
+ "リ": 185,
334
+ "ル": 186,
335
+ "乙": 187,
336
+ "光": 188,
337
+ "其": 189,
338
+ "具": 190,
339
+ "华": 191,
340
+ "厂": 192,
341
+ "名": 193,
342
+ "君": 194,
343
+ "命": 195,
344
+ "咲": 196,
345
+ "場": 197,
346
+ "女": 198,
347
+ "建": 199,
348
+ "戦": 200,
349
+ "日": 201,
350
+ "旭": 202,
351
+ "灯": 203,
352
+ "玩": 204,
353
+ "琪": 205,
354
+ "瘡": 206,
355
+ "肖": 207,
356
+ "花": 208,
357
+ "誓": 209,
358
+ "誰": 210,
359
+ "许": 211,
360
+ "赤": 212,
361
+ "運": 213,
362
+ "銃": 214,
363
+ "願": 215,
364
+ "3": 216,
365
+ "##s": 217,
366
+ "##o": 218,
367
+ "##t": 219,
368
+ "##p": 220,
369
+ "##e": 221,
370
+ "##i": 222,
371
+ "##a": 223,
372
+ "##f": 224,
373
+ "##d": 225,
374
+ "##r": 226,
375
+ "##n": 227,
376
+ "##l": 228,
377
+ "##u": 229,
378
+ "##g": 230,
379
+ "##h": 231,
380
+ "##w": 232,
381
+ "##v": 233,
382
+ "##m": 234,
383
+ "##b": 235,
384
+ "##j": 236,
385
+ "##c": 237,
386
+ "##k": 238,
387
+ "##y": 239,
388
+ "##x": 240,
389
+ "##q": 241,
390
+ "##8": 242,
391
+ "##5": 243,
392
+ "##2": 244,
393
+ "##0": 245,
394
+ "##6": 246,
395
+ "##z": 247,
396
+ "##4": 248,
397
+ "##3": 249,
398
+ "##ล": 250,
399
+ "##ว": 251,
400
+ "##ง": 252,
401
+ "##พ": 253,
402
+ "##ไ": 254,
403
+ "##ช": 255,
404
+ "##ย": 256,
405
+ "##า": 257,
406
+ "##ร": 258,
407
+ "##9": 259,
408
+ "##7": 260,
409
+ "##1": 261,
410
+ "##の": 262,
411
+ "##し": 263,
412
+ "##も": 264,
413
+ "##ภ": 265,
414
+ "##ด": 266,
415
+ "##γ": 267,
416
+ "##ρ": 268,
417
+ "##ο": 269,
418
+ "##ς": 270,
419
+ "##ł": 271,
420
+ "##ε": 272,
421
+ "##τ": 273,
422
+ "##ν": 274,
423
+ "##đ": 275,
424
+ "##ي": 276,
425
+ "##س": 277,
426
+ "##د": 278,
427
+ "##م": 279,
428
+ "##ت": 280,
429
+ "##β": 281,
430
+ "##ウ": 282,
431
+ "##ァ": 283,
432
+ "##ル": 284,
433
+ "##キ": 285,
434
+ "##ュ": 286,
435
+ "##リ": 287,
436
+ "##ア": 288,
437
+ "##3": 289,
438
+ "##ש": 290,
439
+ "##מ": 291,
440
+ "##צ": 292,
441
+ "##ה": 293,
442
+ "##θ": 294,
443
+ "##η": 295,
444
+ "##μ": 296,
445
+ "##ι": 297,
446
+ "##р": 298,
447
+ "##а": 299,
448
+ "##с": 300,
449
+ "##н": 301,
450
+ "##ы": 302,
451
+ "##и": 303,
452
+ "##な": 304,
453
+ "##き": 305,
454
+ "##ɪ": 306,
455
+ "##แ": 307,
456
+ "##ก": 308,
457
+ "##α": 309,
458
+ "##χ": 310,
459
+ "##つ": 311,
460
+ "##か": 312,
461
+ "##た": 313,
462
+ "##め": 314,
463
+ "##υ": 315,
464
+ "##є": 316,
465
+ "##λ": 317,
466
+ "##º": 318,
467
+ "##ป": 319,
468
+ "##ら": 320,
469
+ "##ß": 321,
470
+ "##в": 322,
471
+ "##к": 323,
472
+ "##з": 324,
473
+ "##อ": 325,
474
+ "##ษ": 326,
475
+ "##ฐ": 327,
476
+ "##ซ": 328,
477
+ "##ξ": 329,
478
+ "##ث": 330,
479
+ "##ค": 331,
480
+ "##ต": 332,
481
+ "##ɡ": 333,
482
+ "##æ": 334,
483
+ "##ᵻ": 335,
484
+ "##ə": 336,
485
+ "##ณ": 337,
486
+ "##ม": 338,
487
+ "##เ": 339,
488
+ "th": 340,
489
+ "the": 341,
490
+ "##er": 342,
491
+ "##in": 343,
492
+ "##ed": 344,
493
+ "##on": 345,
494
+ "##nd": 346,
495
+ "##at": 347,
496
+ "##or": 348,
497
+ "##es": 349,
498
+ "in": 350,
499
+ "##en": 351,
500
+ "##ar": 352,
501
+ "of": 353,
502
+ "##it": 354,
503
+ "##al": 355,
504
+ "##an": 356,
505
+ "##is": 357,
506
+ "##ing": 358,
507
+ "##as": 359,
508
+ "and": 360,
509
+ "##ic": 361,
510
+ "to": 362,
511
+ "##ou": 363,
512
+ "##ion": 364,
513
+ "##re": 365,
514
+ "##om": 366,
515
+ "##el": 367,
516
+ "##il": 368,
517
+ "##ol": 369,
518
+ "##ec": 370,
519
+ "##ent": 371,
520
+ "##st": 372,
521
+ "##th": 373,
522
+ "##ur": 374,
523
+ "on": 375,
524
+ "##am": 376,
525
+ "##ad": 377,
526
+ "st": 378,
527
+ "##et": 379,
528
+ "was": 380,
529
+ "##ac": 381,
530
+ "##ro": 382,
531
+ "for": 383,
532
+ "##ir": 384,
533
+ "wh": 385,
534
+ "as": 386,
535
+ "##ly": 387,
536
+ "re": 388,
537
+ "##id": 389,
538
+ "##ith": 390,
539
+ "##iv": 391,
540
+ "##le": 392,
541
+ "##ation": 393,
542
+ "al": 394,
543
+ "##ig": 395,
544
+ "##ers": 396,
545
+ "is": 397,
546
+ "##im": 398,
547
+ "with": 399,
548
+ "##ch": 400,
549
+ "##ay": 401,
550
+ "that": 402,
551
+ "be": 403,
552
+ "##ow": 404,
553
+ "##ts": 405,
554
+ "##em": 406,
555
+ "##ter": 407,
556
+ "an": 408,
557
+ "sh": 409,
558
+ "ch": 410,
559
+ "##ul": 411,
560
+ "##ut": 412,
561
+ "##ot": 413,
562
+ "##um": 414,
563
+ "he": 415,
564
+ "##us": 416,
565
+ "con": 417,
566
+ "fr": 418,
567
+ "by": 419,
568
+ "at": 420,
569
+ "##os": 421,
570
+ "his": 422,
571
+ "##est": 423,
572
+ "##ra": 424,
573
+ "19": 425,
574
+ "##ver": 426,
575
+ "##ce": 427,
576
+ "##and": 428,
577
+ "##av": 429,
578
+ "##od": 430,
579
+ "##ag": 431,
580
+ "##ere": 432,
581
+ "com": 433,
582
+ "se": 434,
583
+ "de": 435,
584
+ "##ies": 436,
585
+ "it": 437,
586
+ "20": 438,
587
+ "##ain": 439,
588
+ "##ct": 440,
589
+ "pro": 441,
590
+ "su": 442,
591
+ "##ist": 443,
592
+ "##ess": 444,
593
+ "ar": 445,
594
+ "##op": 446,
595
+ "from": 447,
596
+ "or": 448,
597
+ "##oc": 449,
598
+ "##ew": 450,
599
+ "##pp": 451,
600
+ "##if": 452,
601
+ "##ity": 453,
602
+ "were": 454,
603
+ "##igh": 455,
604
+ "##ich": 456,
605
+ "##ish": 457,
606
+ "ex": 458,
607
+ "pr": 459,
608
+ "##un": 460,
609
+ "##all": 461,
610
+ "pl": 462,
611
+ "##ate": 463,
612
+ "le": 464,
613
+ "##ated": 465,
614
+ "##ord": 466,
615
+ "##se": 467,
616
+ "##ect": 468,
617
+ "##ia": 469,
618
+ "un": 470,
619
+ "##ort": 471,
620
+ "##ab": 472,
621
+ "are": 473,
622
+ "##ear": 474,
623
+ "##ill": 475,
624
+ "##ak": 476,
625
+ "##gh": 477,
626
+ "##ber": 478,
627
+ "##pt": 479,
628
+ "##ther": 480,
629
+ "sp": 481,
630
+ "tr": 482,
631
+ "##ud": 483,
632
+ "##ard": 484,
633
+ "##ian": 485,
634
+ "##art": 486,
635
+ "##ld": 487,
636
+ "##ial": 488,
637
+ "##ong": 489,
638
+ "which": 490,
639
+ "##ame": 491,
640
+ "##ip": 492,
641
+ "had": 493,
642
+ "##og": 494,
643
+ "##ment": 495,
644
+ "rec": 496,
645
+ "##ive": 497,
646
+ "##ough": 498,
647
+ "##ound": 499,
648
+ "##rit": 500,
649
+ "##ov": 501,
650
+ "##ore": 502,
651
+ "not": 503,
652
+ "##ost": 504,
653
+ "##our": 505,
654
+ "##ant": 506,
655
+ "##ell": 507,
656
+ "##ap": 508,
657
+ "##ue": 509,
658
+ "cl": 510,
659
+ "en": 511,
660
+ "##ib": 512,
661
+ "af": 513,
662
+ "##ast": 514,
663
+ "her": 515,
664
+ "##ge": 516,
665
+ "##ave": 517,
666
+ "##ary": 518,
667
+ "ac": 519,
668
+ "tw": 520,
669
+ "all": 521,
670
+ "##ack": 522,
671
+ "wor": 523,
672
+ "##ust": 524,
673
+ "##ical": 525,
674
+ "200": 526,
675
+ "this": 527,
676
+ "she": 528,
677
+ "##ine": 529,
678
+ "##ight": 530,
679
+ "am": 531,
680
+ "##so": 532,
681
+ "##pl": 533,
682
+ "inc": 534,
683
+ "also": 535,
684
+ "##ure": 536,
685
+ "rel": 537,
686
+ "##out": 538,
687
+ "##ru": 539,
688
+ "their": 540,
689
+ "ad": 541,
690
+ "##ach": 542,
691
+ "##oll": 543,
692
+ "has": 544,
693
+ "comm": 545,
694
+ "##ie": 546,
695
+ "##qu": 547,
696
+ "##ous": 548,
697
+ "bo": 549,
698
+ "ab": 550,
699
+ "fir": 551,
700
+ "sc": 552,
701
+ "per": 553,
702
+ "##ath": 554,
703
+ "##ome": 555,
704
+ "##ide": 556,
705
+ "one": 557,
706
+ "##ub": 558,
707
+ "after": 559,
708
+ "cont": 560,
709
+ "##ign": 561,
710
+ "new": 562,
711
+ "te": 563,
712
+ "its": 564,
713
+ "res": 565,
714
+ "##oun": 566,
715
+ "tim": 567,
716
+ "201": 568,
717
+ "##ition": 569,
718
+ "fe": 570,
719
+ "first": 571,
720
+ "two": 572,
721
+ "fin": 573,
722
+ "##ater": 574,
723
+ "int": 575,
724
+ "man": 576,
725
+ "##ass": 577,
726
+ "##ke": 578,
727
+ "##ations": 579,
728
+ "pol": 580,
729
+ "##wn": 581,
730
+ "but": 582,
731
+ "##ans": 583,
732
+ "go": 584,
733
+ "##ual": 585,
734
+ "car": 586,
735
+ "mar": 587,
736
+ "##act": 588,
737
+ "they": 589,
738
+ "des": 590,
739
+ "ind": 591,
740
+ "##00": 592,
741
+ "im": 593,
742
+ "##ond": 594,
743
+ "play": 595,
744
+ "18": 596,
745
+ "##ould": 597,
746
+ "off": 598,
747
+ "##ory": 599,
748
+ "ag": 600,
749
+ "have": 601,
750
+ "##iz": 602,
751
+ "year": 603,
752
+ "who": 604,
753
+ "##per": 605,
754
+ "##orm": 606,
755
+ "##uring": 607,
756
+ "##own": 608,
757
+ "##nder": 609,
758
+ "##ire": 610,
759
+ "##du": 611,
760
+ "bec": 612,
761
+ "##ied": 613,
762
+ "##ph": 614,
763
+ "me": 615,
764
+ "co": 616,
765
+ "##ff": 617,
766
+ "##ance": 618,
767
+ "been": 619,
768
+ "##ok": 620,
769
+ "##ely": 621,
770
+ "rep": 622,
771
+ "##age": 623,
772
+ "dis": 624,
773
+ "##ree": 625,
774
+ "app": 626,
775
+ "##ason": 627,
776
+ "##ence": 628,
777
+ "us": 629,
778
+ "part": 630,
779
+ "##lud": 631,
780
+ "bl": 632,
781
+ "air": 633,
782
+ "##ult": 634,
783
+ "gr": 635,
784
+ "ser": 636,
785
+ "##ents": 637,
786
+ "##ions": 638,
787
+ "##old": 639,
788
+ "god": 640,
789
+ "over": 641,
790
+ "pre": 642,
791
+ "sec": 643,
792
+ "##ry": 644,
793
+ "##ember": 645,
794
+ "##ric": 646,
795
+ "##ited": 647,
796
+ "other": 648,
797
+ "ev": 649,
798
+ "fl": 650,
799
+ "dec": 651,
800
+ "up": 652,
801
+ "##ite": 653,
802
+ "##ile": 654,
803
+ "during": 655,
804
+ "ne": 656,
805
+ "##ities": 657,
806
+ "act": 658,
807
+ "can": 659,
808
+ "time": 660,
809
+ "fil": 661,
810
+ "under": 662,
811
+ "ear": 663,
812
+ "mus": 664,
813
+ "comp": 665,
814
+ "##vi": 666,
815
+ "includ": 667,
816
+ "##ced": 668,
817
+ "##ang": 669,
818
+ "##ade": 670,
819
+ "##ks": 671,
820
+ "##olog": 672,
821
+ "##ose": 673,
822
+ "form": 674,
823
+ "##ase": 675,
824
+ "film": 676,
825
+ "record": 677,
826
+ "##te": 678,
827
+ "##one": 679,
828
+ "inter": 680,
829
+ "season": 681,
830
+ "war": 682,
831
+ "##ased": 683,
832
+ "##erm": 684,
833
+ "more": 685,
834
+ "##ace": 686,
835
+ "alb": 687,
836
+ "##ates": 688,
837
+ "them": 689,
838
+ "##ens": 690,
839
+ "ass": 691,
840
+ "reg": 692,
841
+ "cons": 693,
842
+ "we": 694,
843
+ "##ubl": 695,
844
+ "##ild": 696,
845
+ "##cc": 697,
846
+ "most": 698,
847
+ "##fer": 699,
848
+ "##ors": 700,
849
+ "##ice": 701,
850
+ "rem": 702,
851
+ "album": 703,
852
+ "##land": 704,
853
+ "##ted": 705,
854
+ "char": 706,
855
+ "##oin": 707,
856
+ "##ward": 708,
857
+ "##ail": 709,
858
+ "##ft": 710,
859
+ "may": 711,
860
+ "##ally": 712,
861
+ "##ole": 713,
862
+ "##able": 714,
863
+ "gen": 715,
864
+ "no": 716,
865
+ "sch": 717,
866
+ "cent": 718,
867
+ "spec": 719,
868
+ "acc": 720,
869
+ "him": 721,
870
+ "##rough": 722,
871
+ "high": 723,
872
+ "##gan": 724,
873
+ "there": 725,
874
+ "min": 726,
875
+ "##gr": 727,
876
+ "ant": 728,
877
+ "mon": 729,
878
+ "##ings": 730,
879
+ "##les": 731,
880
+ "into": 732,
881
+ "199": 733,
882
+ "##reat": 734,
883
+ "##urn": 735,
884
+ "bu": 736,
885
+ "##ces": 737,
886
+ "when": 738,
887
+ "end": 739,
888
+ "nor": 740,
889
+ "out": 741,
890
+ "kn": 742,
891
+ "some": 743,
892
+ "##hip": 744,
893
+ "chr": 745,
894
+ "city": 746,
895
+ "##rib": 747,
896
+ "work": 748,
897
+ "##ix": 749,
898
+ "##form": 750,
899
+ "second": 751,
900
+ "pe": 752,
901
+ "##ved": 753,
902
+ "##ock": 754,
903
+ "##ction": 755,
904
+ "brit": 756,
905
+ "publ": 757,
906
+ "sou": 758,
907
+ "##ered": 759,
908
+ "##ular": 760,
909
+ "##orn": 761,
910
+ "arch": 762,
911
+ "##ve": 763,
912
+ "##ames": 764,
913
+ "##ordan": 765,
914
+ "four": 766,
915
+ "jordan": 767,
916
+ "hist": 768,
917
+ "##ational": 769,
918
+ "ro": 770,
919
+ "##ood": 771,
920
+ "##aw": 772,
921
+ "team": 773,
922
+ "sub": 774,
923
+ "em": 775,
924
+ "three": 776,
925
+ "only": 777,
926
+ "att": 778,
927
+ "par": 779,
928
+ "##res": 780,
929
+ "win": 781,
930
+ "bet": 782,
931
+ "later": 783,
932
+ "##ons": 784,
933
+ "num": 785,
934
+ "produ": 786,
935
+ "again": 787,
936
+ "ret": 788,
937
+ "##vel": 789,
938
+ "##ae": 790,
939
+ "##eld": 791,
940
+ "rele": 792,
941
+ "ph": 793,
942
+ "sy": 794,
943
+ "##oss": 795,
944
+ "imp": 796,
945
+ "game": 797,
946
+ "li": 798,
947
+ "##way": 799,
948
+ "through": 800,
949
+ "##we": 801,
950
+ "whe": 802,
951
+ "inst": 803,
952
+ "dep": 804,
953
+ "##ished": 805,
954
+ "would": 806,
955
+ "##aus": 807,
956
+ "##ict": 808,
957
+ "##erson": 809,
958
+ "long": 810,
959
+ "while": 811,
960
+ "##end": 812,
961
+ "##iss": 813,
962
+ "##ount": 814,
963
+ "sur": 815,
964
+ "##als": 816,
965
+ "ma": 817,
966
+ "these": 818,
967
+ "being": 819,
968
+ "about": 820,
969
+ "##ri": 821,
970
+ "than": 822,
971
+ "##ull": 823,
972
+ "##vest": 824,
973
+ "##ins": 825,
974
+ "##ork": 826,
975
+ "##ick": 827,
976
+ "br": 828,
977
+ "col": 829,
978
+ "arm": 830,
979
+ "how": 831,
980
+ "lar": 832,
981
+ "##ony": 833,
982
+ "many": 834,
983
+ "do": 835,
984
+ "##tle": 836,
985
+ "##eler": 837,
986
+ "pres": 838,
987
+ "writ": 839,
988
+ "such": 840,
989
+ "sa": 841,
990
+ "sm": 842,
991
+ "##ake": 843,
992
+ "##urch": 844,
993
+ "bro": 845,
994
+ "##ily": 846,
995
+ "so": 847,
996
+ "au": 848,
997
+ "##tern": 849,
998
+ "gal": 850,
999
+ "town": 851,
1000
+ "wheeler": 852,
1001
+ "##ific": 853,
1002
+ "##ious": 854,
1003
+ "betwe": 855,
1004
+ "between": 856,
1005
+ "where": 857,
1006
+ "sever": 858,
1007
+ "##ism": 859,
1008
+ "gener": 860,
1009
+ "##aeolog": 861,
1010
+ "000": 862,
1011
+ "bel": 863,
1012
+ "def": 864,
1013
+ "north": 865,
1014
+ "made": 866,
1015
+ "art": 867,
1016
+ "##ollow": 868,
1017
+ "##air": 869,
1018
+ "pop": 870,
1019
+ "music": 871,
1020
+ "archaeolog": 872,
1021
+ "follow": 873,
1022
+ "jo": 874,
1023
+ "song": 875,
1024
+ "##other": 876,
1025
+ "##arn": 877,
1026
+ "el": 878,
1027
+ "##red": 879,
1028
+ "##ating": 880,
1029
+ "ship": 881,
1030
+ "supp": 882,
1031
+ "##amp": 883,
1032
+ "south": 884,
1033
+ "loc": 885,
1034
+ "sign": 886,
1035
+ "exp": 887,
1036
+ "##ove": 888,
1037
+ "##though": 889,
1038
+ "although": 890,
1039
+ "world": 891,
1040
+ "##fore": 892,
1041
+ "##ower": 893,
1042
+ "christ": 894,
1043
+ "british": 895,
1044
+ "##veston": 896,
1045
+ "galveston": 897,
1046
+ "day": 898,
1047
+ "both": 899,
1048
+ "desc": 900,
1049
+ "dire": 901,
1050
+ "germ": 902,
1051
+ "##iet": 903,
1052
+ "church": 904,
1053
+ "command": 905,
1054
+ "met": 906,
1055
+ "##ten": 907,
1056
+ "##hn": 908,
1057
+ "##ised": 909,
1058
+ "stud": 910,
1059
+ "##row": 911,
1060
+ "contr": 912,
1061
+ "cre": 913,
1062
+ "oper": 914,
1063
+ "lead": 915,
1064
+ "call": 916,
1065
+ "div": 917,
1066
+ "ob": 918,
1067
+ "number": 919,
1068
+ "then": 920,
1069
+ "##oup": 921,
1070
+ "##ool": 922,
1071
+ "##ning": 923,
1072
+ "##eric": 924,
1073
+ "years": 925,
1074
+ "gods": 926,
1075
+ "sing": 927,
1076
+ "##up": 928,
1077
+ "##ics": 929,
1078
+ "care": 930,
1079
+ "gu": 931,
1080
+ "nov": 932,
1081
+ "york": 933,
1082
+ "##ever": 934,
1083
+ "state": 935,
1084
+ "##ife": 936,
1085
+ "trans": 937,
1086
+ "used": 938,
1087
+ "early": 939,
1088
+ "##ived": 940,
1089
+ "several": 941,
1090
+ "##gy": 942,
1091
+ "##ern": 943,
1092
+ "##io": 944,
1093
+ "##ute": 945,
1094
+ "add": 946,
1095
+ "main": 947,
1096
+ "well": 948,
1097
+ "##ale": 949,
1098
+ "##sp": 950,
1099
+ "class": 951,
1100
+ "##view": 952,
1101
+ "direct": 953,
1102
+ "crit": 954,
1103
+ "my": 955,
1104
+ "var": 956,
1105
+ "##ron": 957,
1106
+ "before": 958,
1107
+ "prom": 959,
1108
+ "##ause": 960,
1109
+ "bar": 961,
1110
+ "dist": 962,
1111
+ "dif": 963,
1112
+ "qu": 964,
1113
+ "##ral": 965,
1114
+ "##ste": 966,
1115
+ "##ected": 967,
1116
+ "united": 968,
1117
+ "back": 969,
1118
+ "orig": 970,
1119
+ "perform": 971,
1120
+ "offic": 972,
1121
+ "tra": 973,
1122
+ "americ": 974,
1123
+ "##fl": 975,
1124
+ "##ures": 976,
1125
+ "##elf": 977,
1126
+ "school": 978,
1127
+ "peop": 979,
1128
+ "bat": 980,
1129
+ "sl": 981,
1130
+ "##ivers": 982,
1131
+ "against": 983,
1132
+ "##ress": 984,
1133
+ "##ists": 985,
1134
+ "est": 986,
1135
+ "##kel": 987,
1136
+ "book": 988,
1137
+ "disc": 989,
1138
+ "port": 990,
1139
+ "##az": 991,
1140
+ "##ros": 992,
1141
+ "eng": 993,
1142
+ "became": 994,
1143
+ "count": 995,
1144
+ "found": 996,
1145
+ "##ty": 997,
1146
+ "##ery": 998,
1147
+ "states": 999,
1148
+ "##ized": 1000,
1149
+ "like": 1001,
1150
+ "origin": 1002,
1151
+ "hum": 1003,
1152
+ "##ield": 1004,
1153
+ "##its": 1005,
1154
+ "##emb": 1006,
1155
+ "198": 1007,
1156
+ "194": 1008,
1157
+ "antim": 1009,
1158
+ "people": 1010,
1159
+ "award": 1011,
1160
+ "ge": 1012,
1161
+ "##raft": 1013,
1162
+ "lo": 1014,
1163
+ "lit": 1015,
1164
+ "resp": 1016,
1165
+ "remain": 1017,
1166
+ "known": 1018,
1167
+ "##stein": 1019,
1168
+ "public": 1020,
1169
+ "fur": 1021,
1170
+ "however": 1022,
1171
+ "said": 1023
1172
+ }
1173
+ }
1174
+ }
FlavaImageCodebook/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "processor_class": "FlavaProcessor",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
afmoe/AfmoeForCausalLM/chat_template.jinja ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {%- if '</think>' in content %}
27
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
28
+ {%- endif %}
29
+ {{- '<|im_start|>' + message.role + '\n' }}
30
+ {% generation %}
31
+ {{- content }}
32
+ {%- if message.tool_calls %}
33
+ {%- for tool_call in message.tool_calls %}
34
+ {%- if (loop.first and content) or (not loop.first) %}
35
+ {{- '\n' }}
36
+ {%- endif %}
37
+ {%- if tool_call.function %}
38
+ {%- set tool_call = tool_call.function %}
39
+ {%- endif %}
40
+ {{- '<tool_call>\n{"name": "' }}
41
+ {{- tool_call.name }}
42
+ {{- '", "arguments": ' }}
43
+ {%- if tool_call.arguments is string %}
44
+ {{- tool_call.arguments }}
45
+ {%- else %}
46
+ {{- tool_call.arguments | tojson }}
47
+ {%- endif %}
48
+ {{- '}\n</tool_call>' }}
49
+ {%- endfor %}
50
+ {%- endif %}
51
+ {{- '<|im_end|>' }}
52
+ {% endgeneration %}
53
+ {{- '\n' }}
54
+ {%- elif message.role == "tool" %}
55
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
56
+ {{- '<|im_start|>user' }}
57
+ {%- endif %}
58
+ {{- '\n<tool_response>\n' }}
59
+ {{- content }}
60
+ {{- '\n</tool_response>' }}
61
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
62
+ {{- '<|im_end|>\n' }}
63
+ {%- endif %}
64
+ {%- endif %}
65
+ {%- endfor %}
66
+ {%- if add_generation_prompt %}
67
+ {{- '<|im_start|>assistant\n<think>\n' }}
68
+ {%- endif %}
afmoe/AfmoeForCausalLM/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AfmoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "global_attn_every_n_layers": 2,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 16,
16
+ "layer_types": [
17
+ "sliding_attention",
18
+ "full_attention"
19
+ ],
20
+ "max_position_embeddings": 128,
21
+ "model_type": "afmoe",
22
+ "moe_intermediate_size": 16,
23
+ "mup_enabled": false,
24
+ "num_attention_heads": 16,
25
+ "num_dense_layers": 1,
26
+ "num_experts": 4,
27
+ "num_experts_per_tok": 2,
28
+ "num_hidden_layers": 2,
29
+ "num_key_value_heads": 16,
30
+ "num_shared_experts": 2,
31
+ "output_router_logits": false,
32
+ "pad_token_id": 0,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_parameters": {
35
+ "rope_theta": 10000.0,
36
+ "rope_type": "default"
37
+ },
38
+ "route_scale": 1.0,
39
+ "sliding_window": 128,
40
+ "tie_word_embeddings": false,
41
+ "transformers_version": "5.15.0.dev0",
42
+ "use_cache": false,
43
+ "vocab_size": 1026
44
+ }
afmoe/AfmoeForCausalLM/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.15.0.dev0",
9
+ "use_cache": false
10
+ }
afmoe/AfmoeForCausalLM/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f5cd9b163c342edbac86dbe7216019f0843c9d644cbdcef85b8ffd53d45aa5
3
+ size 2935656
afmoe/AfmoeForCausalLM/tokenizer.json ADDED
@@ -0,0 +1,4415 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|begin_of_text|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|end_of_text|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<|im_end|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<|eot_id|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "<|start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 6,
62
+ "content": "<|channel|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 7,
71
+ "content": "<|message|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 8,
80
+ "content": "<|end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 9,
89
+ "content": "<|fitm_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 10,
98
+ "content": "<|fitm_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 11,
107
+ "content": "<|fitm_hole|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 12,
116
+ "content": "<|pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 13,
125
+ "content": "<|reserved_special_2|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 14,
134
+ "content": "<|reserved_special_3|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 15,
143
+ "content": "<|reserved_special_4|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 16,
152
+ "content": "<|reserved_special_5|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 17,
161
+ "content": "<|reserved_special_6|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 18,
170
+ "content": "<|reserved_special_7|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 19,
179
+ "content": "<|reserved_special_8|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 20,
188
+ "content": "<|reserved_special_9|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 21,
197
+ "content": "<|reserved_special_10|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 22,
206
+ "content": "<|reserved_special_11|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 23,
215
+ "content": "<|reserved_special_12|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 24,
224
+ "content": "<|reserved_special_13|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 25,
233
+ "content": "<|reserved_special_14|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 26,
242
+ "content": "<|reserved_special_15|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 27,
251
+ "content": "<|reserved_special_16|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 28,
260
+ "content": "<|reserved_special_17|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 29,
269
+ "content": "<|reserved_special_18|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 1024,
278
+ "content": "<think>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": false
284
+ },
285
+ {
286
+ "id": 1025,
287
+ "content": "</think>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": false
293
+ }
294
+ ],
295
+ "normalizer": {
296
+ "type": "Sequence",
297
+ "normalizers": []
298
+ },
299
+ "pre_tokenizer": {
300
+ "type": "Sequence",
301
+ "pretokenizers": [
302
+ {
303
+ "type": "Digits",
304
+ "individual_digits": false
305
+ },
306
+ {
307
+ "type": "Split",
308
+ "pattern": {
309
+ "Regex": "\\p{Nd}{1,510}(?=(?>\\p{Nd}{510})*(?:\\P{Nd}|$))|\\G\\p{Nd}{510}"
310
+ },
311
+ "behavior": "Isolated",
312
+ "invert": false
313
+ },
314
+ {
315
+ "type": "Split",
316
+ "pattern": {
317
+ "Regex": "\\A\\p{Nd}{1,2}(?=\\p{Nd}{3}+\\z)"
318
+ },
319
+ "behavior": "Isolated",
320
+ "invert": false
321
+ },
322
+ {
323
+ "type": "Split",
324
+ "pattern": {
325
+ "Regex": "\\A\\p{Nd}{3}|\\G\\p{Nd}{3}"
326
+ },
327
+ "behavior": "Isolated",
328
+ "invert": false
329
+ },
330
+ {
331
+ "type": "Split",
332
+ "pattern": {
333
+ "Regex": "(?:[\\u4E00-\\u9FFF\\u3040-\\u309F\\u30A0-\\u30FF\\u3400-\\u4DBF\\uf900-\\uFAFF\\uFF65-\\uFF9F\\u2F00-\\u2FDF]+|[\\u0E00-\\u0E7F]+|[\\u0E80-\\u0EFF]+|[\\u1780-\\u17FF]+|[\\u1000-\\u109F\\uAA60-\\uAA7F\\uA9E0-\\uA9FF]+|[\\uAC00-\\uD7AF\\u1100-\\u11FF]+)"
334
+ },
335
+ "behavior": "Isolated",
336
+ "invert": false
337
+ },
338
+ {
339
+ "type": "Split",
340
+ "pattern": {
341
+ "Regex": "[!\"#$%&'()*+,\\-./:;<=>?@\\[\\\\\\]^_`{|}~][A-Za-z]+|[^\r\n\\p{L}\\p{P}\\p{S}]?[\\p{L}\\p{M}]+| ?[\\p{P}\\p{S}]+[\r\n]*|\\s*[\r\n]+|\\s+(?!\\S)|\\s+"
342
+ },
343
+ "behavior": "Isolated",
344
+ "invert": false
345
+ },
346
+ {
347
+ "type": "ByteLevel",
348
+ "add_prefix_space": false,
349
+ "trim_offsets": true,
350
+ "use_regex": false
351
+ }
352
+ ]
353
+ },
354
+ "post_processor": {
355
+ "type": "Sequence",
356
+ "processors": [
357
+ {
358
+ "type": "ByteLevel",
359
+ "add_prefix_space": true,
360
+ "trim_offsets": false,
361
+ "use_regex": true
362
+ },
363
+ {
364
+ "type": "TemplateProcessing",
365
+ "single": [
366
+ {
367
+ "SpecialToken": {
368
+ "id": "<|begin_of_text|>",
369
+ "type_id": 0
370
+ }
371
+ },
372
+ {
373
+ "Sequence": {
374
+ "id": "A",
375
+ "type_id": 0
376
+ }
377
+ }
378
+ ],
379
+ "pair": [
380
+ {
381
+ "SpecialToken": {
382
+ "id": "<|begin_of_text|>",
383
+ "type_id": 0
384
+ }
385
+ },
386
+ {
387
+ "Sequence": {
388
+ "id": "A",
389
+ "type_id": 0
390
+ }
391
+ },
392
+ {
393
+ "SpecialToken": {
394
+ "id": "<|begin_of_text|>",
395
+ "type_id": 0
396
+ }
397
+ },
398
+ {
399
+ "Sequence": {
400
+ "id": "B",
401
+ "type_id": 0
402
+ }
403
+ }
404
+ ],
405
+ "special_tokens": {
406
+ "<|begin_of_text|>": {
407
+ "id": "<|begin_of_text|>",
408
+ "ids": [
409
+ 0
410
+ ],
411
+ "tokens": [
412
+ "<|begin_of_text|>"
413
+ ]
414
+ }
415
+ }
416
+ }
417
+ ]
418
+ },
419
+ "decoder": {
420
+ "type": "ByteLevel",
421
+ "add_prefix_space": true,
422
+ "trim_offsets": true,
423
+ "use_regex": true
424
+ },
425
+ "model": {
426
+ "type": "BPE",
427
+ "dropout": null,
428
+ "unk_token": null,
429
+ "continuing_subword_prefix": null,
430
+ "end_of_word_suffix": null,
431
+ "fuse_unk": false,
432
+ "byte_fallback": false,
433
+ "ignore_merges": false,
434
+ "vocab": {
435
+ "<|begin_of_text|>": 0,
436
+ "<|end_of_text|>": 1,
437
+ "<|im_start|>": 2,
438
+ "<|im_end|>": 3,
439
+ "<|eot_id|>": 4,
440
+ "<|start|>": 5,
441
+ "<|channel|>": 6,
442
+ "<|message|>": 7,
443
+ "<|end|>": 8,
444
+ "<|fitm_start|>": 9,
445
+ "<|fitm_end|>": 10,
446
+ "<|fitm_hole|>": 11,
447
+ "<|pad|>": 12,
448
+ "<|reserved_special_2|>": 13,
449
+ "<|reserved_special_3|>": 14,
450
+ "<|reserved_special_4|>": 15,
451
+ "<|reserved_special_5|>": 16,
452
+ "<|reserved_special_6|>": 17,
453
+ "<|reserved_special_7|>": 18,
454
+ "<|reserved_special_8|>": 19,
455
+ "<|reserved_special_9|>": 20,
456
+ "<|reserved_special_10|>": 21,
457
+ "<|reserved_special_11|>": 22,
458
+ "<|reserved_special_12|>": 23,
459
+ "<|reserved_special_13|>": 24,
460
+ "<|reserved_special_14|>": 25,
461
+ "<|reserved_special_15|>": 26,
462
+ "<|reserved_special_16|>": 27,
463
+ "<|reserved_special_17|>": 28,
464
+ "<|reserved_special_18|>": 29,
465
+ "!": 30,
466
+ "\"": 31,
467
+ "#": 32,
468
+ "$": 33,
469
+ "%": 34,
470
+ "&": 35,
471
+ "'": 36,
472
+ "(": 37,
473
+ ")": 38,
474
+ "*": 39,
475
+ "+": 40,
476
+ ",": 41,
477
+ "-": 42,
478
+ ".": 43,
479
+ "/": 44,
480
+ "0": 45,
481
+ "1": 46,
482
+ "2": 47,
483
+ "3": 48,
484
+ "4": 49,
485
+ "5": 50,
486
+ "6": 51,
487
+ "7": 52,
488
+ "8": 53,
489
+ "9": 54,
490
+ ":": 55,
491
+ ";": 56,
492
+ "<": 57,
493
+ "=": 58,
494
+ ">": 59,
495
+ "?": 60,
496
+ "@": 61,
497
+ "A": 62,
498
+ "B": 63,
499
+ "C": 64,
500
+ "D": 65,
501
+ "E": 66,
502
+ "F": 67,
503
+ "G": 68,
504
+ "H": 69,
505
+ "I": 70,
506
+ "J": 71,
507
+ "K": 72,
508
+ "L": 73,
509
+ "M": 74,
510
+ "N": 75,
511
+ "O": 76,
512
+ "P": 77,
513
+ "Q": 78,
514
+ "R": 79,
515
+ "S": 80,
516
+ "T": 81,
517
+ "U": 82,
518
+ "V": 83,
519
+ "W": 84,
520
+ "X": 85,
521
+ "Y": 86,
522
+ "Z": 87,
523
+ "[": 88,
524
+ "\\": 89,
525
+ "]": 90,
526
+ "^": 91,
527
+ "_": 92,
528
+ "`": 93,
529
+ "a": 94,
530
+ "b": 95,
531
+ "c": 96,
532
+ "d": 97,
533
+ "e": 98,
534
+ "f": 99,
535
+ "g": 100,
536
+ "h": 101,
537
+ "i": 102,
538
+ "j": 103,
539
+ "k": 104,
540
+ "l": 105,
541
+ "m": 106,
542
+ "n": 107,
543
+ "o": 108,
544
+ "p": 109,
545
+ "q": 110,
546
+ "r": 111,
547
+ "s": 112,
548
+ "t": 113,
549
+ "u": 114,
550
+ "v": 115,
551
+ "w": 116,
552
+ "x": 117,
553
+ "y": 118,
554
+ "z": 119,
555
+ "{": 120,
556
+ "|": 121,
557
+ "}": 122,
558
+ "~": 123,
559
+ "¡": 124,
560
+ "¢": 125,
561
+ "£": 126,
562
+ "¤": 127,
563
+ "¥": 128,
564
+ "¦": 129,
565
+ "§": 130,
566
+ "¨": 131,
567
+ "©": 132,
568
+ "ª": 133,
569
+ "«": 134,
570
+ "¬": 135,
571
+ "®": 136,
572
+ "¯": 137,
573
+ "°": 138,
574
+ "±": 139,
575
+ "²": 140,
576
+ "³": 141,
577
+ "´": 142,
578
+ "µ": 143,
579
+ "¶": 144,
580
+ "·": 145,
581
+ "¸": 146,
582
+ "¹": 147,
583
+ "º": 148,
584
+ "»": 149,
585
+ "¼": 150,
586
+ "½": 151,
587
+ "¾": 152,
588
+ "¿": 153,
589
+ "À": 154,
590
+ "Á": 155,
591
+ "Â": 156,
592
+ "Ã": 157,
593
+ "Ä": 158,
594
+ "Å": 159,
595
+ "Æ": 160,
596
+ "Ç": 161,
597
+ "È": 162,
598
+ "É": 163,
599
+ "Ê": 164,
600
+ "Ë": 165,
601
+ "Ì": 166,
602
+ "Í": 167,
603
+ "Î": 168,
604
+ "Ï": 169,
605
+ "Ð": 170,
606
+ "Ñ": 171,
607
+ "Ò": 172,
608
+ "Ó": 173,
609
+ "Ô": 174,
610
+ "Õ": 175,
611
+ "Ö": 176,
612
+ "×": 177,
613
+ "Ø": 178,
614
+ "Ù": 179,
615
+ "Ú": 180,
616
+ "Û": 181,
617
+ "Ü": 182,
618
+ "Ý": 183,
619
+ "Þ": 184,
620
+ "ß": 185,
621
+ "à": 186,
622
+ "á": 187,
623
+ "â": 188,
624
+ "ã": 189,
625
+ "ä": 190,
626
+ "å": 191,
627
+ "æ": 192,
628
+ "ç": 193,
629
+ "è": 194,
630
+ "é": 195,
631
+ "ê": 196,
632
+ "ë": 197,
633
+ "ì": 198,
634
+ "í": 199,
635
+ "î": 200,
636
+ "ï": 201,
637
+ "ð": 202,
638
+ "ñ": 203,
639
+ "ò": 204,
640
+ "ó": 205,
641
+ "ô": 206,
642
+ "õ": 207,
643
+ "ö": 208,
644
+ "÷": 209,
645
+ "ø": 210,
646
+ "ù": 211,
647
+ "ú": 212,
648
+ "û": 213,
649
+ "ü": 214,
650
+ "ý": 215,
651
+ "þ": 216,
652
+ "ÿ": 217,
653
+ "Ā": 218,
654
+ "ā": 219,
655
+ "Ă": 220,
656
+ "ă": 221,
657
+ "Ą": 222,
658
+ "ą": 223,
659
+ "Ć": 224,
660
+ "ć": 225,
661
+ "Ĉ": 226,
662
+ "ĉ": 227,
663
+ "Ċ": 228,
664
+ "ċ": 229,
665
+ "Č": 230,
666
+ "č": 231,
667
+ "Ď": 232,
668
+ "ď": 233,
669
+ "Đ": 234,
670
+ "đ": 235,
671
+ "Ē": 236,
672
+ "ē": 237,
673
+ "Ĕ": 238,
674
+ "ĕ": 239,
675
+ "Ė": 240,
676
+ "ė": 241,
677
+ "Ę": 242,
678
+ "ę": 243,
679
+ "Ě": 244,
680
+ "ě": 245,
681
+ "Ĝ": 246,
682
+ "ĝ": 247,
683
+ "Ğ": 248,
684
+ "ğ": 249,
685
+ "Ġ": 250,
686
+ "ġ": 251,
687
+ "Ģ": 252,
688
+ "ģ": 253,
689
+ "Ĥ": 254,
690
+ "ĥ": 255,
691
+ "Ħ": 256,
692
+ "ħ": 257,
693
+ "Ĩ": 258,
694
+ "ĩ": 259,
695
+ "Ī": 260,
696
+ "ī": 261,
697
+ "Ĭ": 262,
698
+ "ĭ": 263,
699
+ "Į": 264,
700
+ "į": 265,
701
+ "İ": 266,
702
+ "ı": 267,
703
+ "IJ": 268,
704
+ "ij": 269,
705
+ "Ĵ": 270,
706
+ "ĵ": 271,
707
+ "Ķ": 272,
708
+ "ķ": 273,
709
+ "ĸ": 274,
710
+ "Ĺ": 275,
711
+ "ĺ": 276,
712
+ "Ļ": 277,
713
+ "ļ": 278,
714
+ "Ľ": 279,
715
+ "ľ": 280,
716
+ "Ŀ": 281,
717
+ "ŀ": 282,
718
+ "Ł": 283,
719
+ "ł": 284,
720
+ "Ń": 285,
721
+ "Ġt": 286,
722
+ "he": 287,
723
+ "Ġa": 288,
724
+ "in": 289,
725
+ "Ġthe": 290,
726
+ "er": 291,
727
+ "on": 292,
728
+ "Ġ,": 293,
729
+ "re": 294,
730
+ "Ġs": 295,
731
+ "ed": 296,
732
+ "Ġo": 297,
733
+ "nd": 298,
734
+ "Ġw": 299,
735
+ "at": 300,
736
+ "Ġ.": 301,
737
+ "or": 302,
738
+ "it": 303,
739
+ "is": 304,
740
+ "Ġc": 305,
741
+ "es": 306,
742
+ "Ġf": 307,
743
+ "en": 308,
744
+ "Ġof": 309,
745
+ "ar": 310,
746
+ "al": 311,
747
+ "Ġin": 312,
748
+ "Ġb": 313,
749
+ "an": 314,
750
+ "Ġp": 315,
751
+ "ing": 316,
752
+ "as": 317,
753
+ "Ġand": 318,
754
+ "ic": 319,
755
+ "Ġto": 320,
756
+ "Ġm": 321,
757
+ "ro": 322,
758
+ "Ġd": 323,
759
+ "Ġh": 324,
760
+ "ion": 325,
761
+ "le": 326,
762
+ "ĠT": 327,
763
+ "ou": 328,
764
+ "Ġre": 329,
765
+ "Ġ=": 330,
766
+ "ĠA": 331,
767
+ "Ġ\"": 332,
768
+ "ĠS": 333,
769
+ "Ġth": 334,
770
+ "ent": 335,
771
+ "il": 336,
772
+ "st": 337,
773
+ "Ġ@": 338,
774
+ "el": 339,
775
+ "ĠC": 340,
776
+ "ĠĊ": 341,
777
+ "ol": 342,
778
+ "Ġl": 343,
779
+ "Ġn": 344,
780
+ "om": 345,
781
+ "Ġe": 346,
782
+ "ct": 347,
783
+ "am": 348,
784
+ "ad": 349,
785
+ "Ġg": 350,
786
+ "Ġwas": 351,
787
+ "ur": 352,
788
+ "Ġon": 353,
789
+ "ĠThe": 354,
790
+ "ĠI": 355,
791
+ "im": 356,
792
+ "-@": 357,
793
+ "Ġ@-@": 358,
794
+ "Ġbe": 359,
795
+ "ly": 360,
796
+ "ĠM": 361,
797
+ "id": 362,
798
+ "Ġfor": 363,
799
+ "ir": 364,
800
+ "ch": 365,
801
+ "ĠB": 366,
802
+ "iv": 367,
803
+ "ot": 368,
804
+ "Ġ'": 369,
805
+ "ith": 370,
806
+ "ation": 371,
807
+ "ra": 372,
808
+ "ig": 373,
809
+ "Ġas": 374,
810
+ "et": 375,
811
+ "ow": 376,
812
+ "us": 377,
813
+ "ut": 378,
814
+ "Ġst": 379,
815
+ "ce": 380,
816
+ "Ġwith": 381,
817
+ "ĠP": 382,
818
+ "ers": 383,
819
+ "Ġhe": 384,
820
+ "Ġthat": 385,
821
+ "ay": 386,
822
+ "Ġis": 387,
823
+ "ĠH": 388,
824
+ "ul": 389,
825
+ "ĠG": 390,
826
+ "ĠF": 391,
827
+ "Ġal": 392,
828
+ "ĠR": 393,
829
+ "ĠN": 394,
830
+ "ist": 395,
831
+ "um": 396,
832
+ "em": 397,
833
+ "Ġwh": 398,
834
+ "ĠW": 399,
835
+ "est": 400,
836
+ "Ġby": 401,
837
+ "un": 402,
838
+ "Ġan": 403,
839
+ "ver": 404,
840
+ "os": 405,
841
+ "th": 406,
842
+ "Ġ)": 407,
843
+ "Ġ(": 408,
844
+ "ter": 409,
845
+ "Ġcon": 410,
846
+ "ĠJ": 411,
847
+ "rom": 412,
848
+ "ĠD": 413,
849
+ "Ġat": 414,
850
+ "Ġse": 415,
851
+ "and": 416,
852
+ "od": 417,
853
+ "ĠL": 418,
854
+ "av": 419,
855
+ "Ġit": 420,
856
+ "00": 421,
857
+ "Ġde": 422,
858
+ "ag": 423,
859
+ "her": 424,
860
+ "ies": 425,
861
+ "pe": 426,
862
+ "ĠE": 427,
863
+ "ain": 428,
864
+ "ck": 429,
865
+ "Ġhis": 430,
866
+ "ri": 431,
867
+ "Ġfrom": 432,
868
+ "ere": 433,
869
+ "res": 434,
870
+ "ort": 435,
871
+ "Ġpro": 436,
872
+ "if": 437,
873
+ "Ġcom": 438,
874
+ "ew": 439,
875
+ "ity": 440,
876
+ "Ġwere": 441,
877
+ "Ġv": 442,
878
+ "ate": 443,
879
+ "ĠIn": 444,
880
+ "Ġsu": 445,
881
+ "ĠO": 446,
882
+ "op": 447,
883
+ "Ġor": 448,
884
+ "ich": 449,
885
+ "ore": 450,
886
+ "all": 451,
887
+ "igh": 452,
888
+ "ated": 453,
889
+ "ord": 454,
890
+ "se": 455,
891
+ "ill": 456,
892
+ "art": 457,
893
+ "Ġex": 458,
894
+ "ab": 459,
895
+ "pt": 460,
896
+ "Ġch": 461,
897
+ "Ġsh": 462,
898
+ "ld": 463,
899
+ "Ġpl": 464,
900
+ "pp": 465,
901
+ "ak": 466,
902
+ "Ġare": 467,
903
+ "ber": 468,
904
+ "gh": 469,
905
+ "ess": 470,
906
+ "ud": 471,
907
+ "Ġâ": 472,
908
+ "ant": 473,
909
+ "ard": 474,
910
+ "rou": 475,
911
+ "ong": 476,
912
+ "ĠU": 477,
913
+ "ru": 478,
914
+ "ia": 479,
915
+ "qu": 480,
916
+ "Ġwhich": 481,
917
+ "ĠâĢ": 482,
918
+ "ame": 483,
919
+ "ment": 484,
920
+ "ĠCh": 485,
921
+ "Ġle": 486,
922
+ "rit": 487,
923
+ "Ġhad": 488,
924
+ "ial": 489,
925
+ "ian": 490,
926
+ "og": 491,
927
+ "red": 492,
928
+ "ĠK": 493,
929
+ "ĠSt": 494,
930
+ "ive": 495,
931
+ "oc": 496,
932
+ "ip": 497,
933
+ "ov": 498,
934
+ "Ġ;": 499,
935
+ "Ġr": 500,
936
+ "ish": 501,
937
+ "ost": 502,
938
+ "our": 503,
939
+ "Ġar": 504,
940
+ "Ġu": 505,
941
+ "Ġnot": 506,
942
+ "ear": 507,
943
+ "ight": 508,
944
+ "ast": 509,
945
+ "ac": 510,
946
+ "Ġy": 511,
947
+ "Ġk": 512,
948
+ "ave": 513,
949
+ "ary": 514,
950
+ "ell": 515,
951
+ "ther": 516,
952
+ "ction": 517,
953
+ "ical": 518,
954
+ "nt": 519,
955
+ "own": 520,
956
+ "cc": 521,
957
+ "Ġinc": 522,
958
+ "ine": 523,
959
+ "ge": 524,
960
+ "ide": 525,
961
+ "ust": 526,
962
+ "ĠâĢĵ": 527,
963
+ "Ġher": 528,
964
+ "so": 529,
965
+ "ap": 530,
966
+ "ue": 531,
967
+ "ure": 532,
968
+ "ork": 533,
969
+ "ran": 534,
970
+ "out": 535,
971
+ "Ġalso": 536,
972
+ "Ġtheir": 537,
973
+ "Ġhas": 538,
974
+ "wo": 539,
975
+ "Ġun": 540,
976
+ "ous": 541,
977
+ "ff": 542,
978
+ "ign": 543,
979
+ "fter": 544,
980
+ "ĠV": 545,
981
+ "ub": 546,
982
+ "Ġrec": 547,
983
+ "ome": 548,
984
+ "01": 549,
985
+ "Ġcl": 550,
986
+ ".@": 551,
987
+ "Ġ@.@": 552,
988
+ "Ġcont": 553,
989
+ "irst": 554,
990
+ "ĠHe": 555,
991
+ "Ġte": 556,
992
+ "ition": 557,
993
+ "ater": 558,
994
+ "Ġper": 559,
995
+ "ass": 560,
996
+ "ack": 561,
997
+ "ations": 562,
998
+ "ie": 563,
999
+ "Ġits": 564,
1000
+ "Ġab": 565,
1001
+ "pl": 566,
1002
+ "Ġone": 567,
1003
+ "Ġint": 568,
1004
+ "Ġsc": 569,
1005
+ "Ġfirst": 570,
1006
+ "ond": 571,
1007
+ "ime": 572,
1008
+ "hed": 573,
1009
+ "Ġ:": 574,
1010
+ "orm": 575,
1011
+ "ult": 576,
1012
+ "ould": 577,
1013
+ "ory": 578,
1014
+ "Ġwho": 579,
1015
+ "Ġwhe": 580,
1016
+ "ĠTh": 581,
1017
+ "per": 582,
1018
+ "Ġbut": 583,
1019
+ "Ġhave": 584,
1020
+ "Ġtwo": 585,
1021
+ "nder": 586,
1022
+ "ĠAl": 587,
1023
+ "ect": 588,
1024
+ "Ġthis": 589,
1025
+ "ok": 590,
1026
+ "ark": 591,
1027
+ "uring": 592,
1028
+ "du": 593,
1029
+ "ire": 594,
1030
+ "ough": 595,
1031
+ "ual": 596,
1032
+ "Ġall": 597,
1033
+ "ĠY": 598,
1034
+ "iz": 599,
1035
+ "mer": 600,
1036
+ "Ġus": 601,
1037
+ "ach": 602,
1038
+ "oll": 603,
1039
+ "Ġbeen": 604,
1040
+ "Ġplay": 605,
1041
+ "Ġres": 606,
1042
+ "ree": 607,
1043
+ "Ġshe": 608,
1044
+ ",@": 609,
1045
+ "Ġ@,@": 610,
1046
+ "age": 611,
1047
+ "Ġoff": 612,
1048
+ "ey": 613,
1049
+ "Ġcomp": 614,
1050
+ "Ġag": 615,
1051
+ "ason": 616,
1052
+ "port": 617,
1053
+ "oin": 618,
1054
+ "Ġad": 619,
1055
+ "Ġyear": 620,
1056
+ "Ġim": 621,
1057
+ "ĠIt": 622,
1058
+ "ence": 623,
1059
+ "Ġpart": 624,
1060
+ "Ġdes": 625,
1061
+ "ke": 626,
1062
+ "ric": 627,
1063
+ "are": 628,
1064
+ "ry": 629,
1065
+ "lud": 630,
1066
+ "Ġbec": 631,
1067
+ "te": 632,
1068
+ "Ġj": 633,
1069
+ "Ġother": 634,
1070
+ "ely": 635,
1071
+ "Ġdis": 636,
1072
+ "ph": 637,
1073
+ "Ġman": 638,
1074
+ "ound": 639,
1075
+ "old": 640,
1076
+ "Ġspe": 641,
1077
+ "act": 642,
1078
+ "Ġro": 643,
1079
+ "Ġafter": 644,
1080
+ "ance": 645,
1081
+ "ath": 646,
1082
+ "Ġen": 647,
1083
+ "ited": 648,
1084
+ "ĠUn": 649,
1085
+ "Ġgo": 650,
1086
+ "ib": 651,
1087
+ "ile": 652,
1088
+ "Ġthey": 653,
1089
+ "ite": 654,
1090
+ "man": 655,
1091
+ "ities": 656,
1092
+ "Ġover": 657,
1093
+ "ced": 658,
1094
+ "ents": 659,
1095
+ "ors": 660,
1096
+ "round": 661,
1097
+ "ilm": 662,
1098
+ "Ġinclud": 663,
1099
+ "Ġpre": 664,
1100
+ "ĠRe": 665,
1101
+ "vi": 666,
1102
+ "olog": 667,
1103
+ "ted": 668,
1104
+ "ade": 669,
1105
+ "ied": 670,
1106
+ "ose": 671,
1107
+ "ase": 672,
1108
+ "Ġcomm": 673,
1109
+ "Ġtime": 674,
1110
+ "Ġser": 675,
1111
+ "inal": 676,
1112
+ "Ġseason": 677,
1113
+ "99": 678,
1114
+ "ased": 679,
1115
+ "Ġout": 680,
1116
+ "ice": 681,
1117
+ "ĠAr": 682,
1118
+ "ates": 683,
1119
+ "ress": 684,
1120
+ "Ġup": 685,
1121
+ "ĠSe": 686,
1122
+ "ft": 687,
1123
+ "Ġthem": 688,
1124
+ "ubl": 689,
1125
+ "les": 690,
1126
+ "ild": 691,
1127
+ "Ġsp": 692,
1128
+ "Ġev": 693,
1129
+ "Ġmore": 694,
1130
+ "land": 695,
1131
+ "bum": 696,
1132
+ "fer": 697,
1133
+ "ces": 698,
1134
+ "Ġnew": 699,
1135
+ "gan": 700,
1136
+ "rough": 701,
1137
+ "able": 702,
1138
+ "ron": 703,
1139
+ "ts": 704,
1140
+ "ĠDe": 705,
1141
+ "ace": 706,
1142
+ "Ġne": 707,
1143
+ "Ġgod": 708,
1144
+ "ock": 709,
1145
+ "Ġalbum": 710,
1146
+ "rib": 711,
1147
+ "ward": 712,
1148
+ "Ġrem": 713,
1149
+ "Ġsec": 714,
1150
+ "Ġunder": 715,
1151
+ "wn": 716,
1152
+ "Ġwork": 717,
1153
+ "ered": 718,
1154
+ "ĠSh": 719,
1155
+ "ind": 720,
1156
+ "ens": 721,
1157
+ "Ġrel": 722,
1158
+ "Ġfilm": 723,
1159
+ "use": 724,
1160
+ "Ġhim": 725,
1161
+ "ings": 726,
1162
+ "ount": 727,
1163
+ "Ġrecord": 728,
1164
+ "Ġspec": 729,
1165
+ "ĠWhe": 730,
1166
+ "Ġinto": 731,
1167
+ "arn": 732,
1168
+ "reat": 733,
1169
+ "hip": 734,
1170
+ "one": 735,
1171
+ "orn": 736,
1172
+ "Ġinter": 737,
1173
+ "urn": 738,
1174
+ "ail": 739,
1175
+ "Ġfe": 740,
1176
+ "ember": 741,
1177
+ "Ġcons": 742,
1178
+ "form": 743,
1179
+ "ix": 744,
1180
+ "ved": 745,
1181
+ "Ġmost": 746,
1182
+ "Ġreg": 747,
1183
+ "ational": 748,
1184
+ "ern": 749,
1185
+ "arly": 750,
1186
+ "ĠPol": 751,
1187
+ "Ġact": 752,
1188
+ "oy": 753,
1189
+ "ink": 754,
1190
+ "ames": 755,
1191
+ "ordan": 756,
1192
+ "ĠJordan": 757,
1193
+ "ĠOn": 758,
1194
+ "Ġair": 759,
1195
+ "ĠAs": 760,
1196
+ "Ġduring": 761,
1197
+ "ĠBrit": 762,
1198
+ "ions": 763,
1199
+ "aw": 764,
1200
+ "Ġco": 765,
1201
+ "Ġfl": 766,
1202
+ "ee": 767,
1203
+ "oth": 768,
1204
+ "ae": 769,
1205
+ "vel": 770,
1206
+ "Ġtra": 771,
1207
+ "ons": 772,
1208
+ "ang": 773,
1209
+ "ick": 774,
1210
+ "Ġass": 775,
1211
+ "Ġatt": 776,
1212
+ "Ġra": 777,
1213
+ "oss": 778,
1214
+ "Ġsub": 779,
1215
+ "Ġkn": 780,
1216
+ "Ġonly": 781,
1217
+ "Ġagain": 782,
1218
+ "way": 783,
1219
+ "000": 784,
1220
+ "ans": 785,
1221
+ "Ġme": 786,
1222
+ "Ġnum": 787,
1223
+ "Ġform": 788,
1224
+ "iss": 789,
1225
+ "Ġpubl": 790,
1226
+ "ng": 791,
1227
+ "ished": 792,
1228
+ "arg": 793,
1229
+ "Ġret": 794,
1230
+ "Ġrele": 795,
1231
+ "Ġwould": 796,
1232
+ "een": 797,
1233
+ "ve": 798,
1234
+ "Ġfour": 799,
1235
+ "ict": 800,
1236
+ "Ġthree": 801,
1237
+ "erson": 802,
1238
+ "tle": 803,
1239
+ "Ġprodu": 804,
1240
+ "Ġmon": 805,
1241
+ "Ġteam": 806,
1242
+ "ook": 807,
1243
+ "orth": 808,
1244
+ "ĠShe": 809,
1245
+ "Ġend": 810,
1246
+ "ars": 811,
1247
+ "Ġbet": 812,
1248
+ "vest": 813,
1249
+ "Ġbu": 814,
1250
+ "Ġsecond": 815,
1251
+ "Ġthan": 816,
1252
+ "ste": 817,
1253
+ "ĠIs": 818,
1254
+ "ĠInd": 819,
1255
+ "Ġbeing": 820,
1256
+ "Ġdec": 821,
1257
+ "ood": 822,
1258
+ "Ġcan": 823,
1259
+ "ener": 824,
1260
+ "Ġthrough": 825,
1261
+ "Ġabout": 826,
1262
+ "Ġcent": 827,
1263
+ "cted": 828,
1264
+ "Ġapp": 829,
1265
+ "Ġwhen": 830,
1266
+ "Ġlater": 831,
1267
+ "ower": 832,
1268
+ "ull": 833,
1269
+ "ony": 834,
1270
+ "ole": 835,
1271
+ "eler": 836,
1272
+ "Ġacc": 837,
1273
+ "Ġpe": 838,
1274
+ "ake": 839,
1275
+ "ike": 840,
1276
+ "ily": 841,
1277
+ "rist": 842,
1278
+ "Ġac": 843,
1279
+ "Ġind": 844,
1280
+ "ĠWheeler": 845,
1281
+ "ĠLe": 846,
1282
+ "outh": 847,
1283
+ "ĠCom": 848,
1284
+ "usic": 849,
1285
+ "ular": 850,
1286
+ "ious": 851,
1287
+ "ween": 852,
1288
+ "Ġsome": 853,
1289
+ "urch": 854,
1290
+ "end": 855,
1291
+ "ism": 856,
1292
+ "chae": 857,
1293
+ "ĠNew": 858,
1294
+ "chaeolog": 859,
1295
+ "aid": 860,
1296
+ "Ġwrit": 861,
1297
+ "als": 862,
1298
+ "Ġdo": 863,
1299
+ "Ġsuch": 864,
1300
+ "ollow": 865,
1301
+ "ally": 866,
1302
+ "ten": 867,
1303
+ "Ġam": 868,
1304
+ "ins": 869,
1305
+ "Ġpol": 870,
1306
+ "Ġmade": 871,
1307
+ "ific": 872,
1308
+ "Ġmet": 873,
1309
+ "Ġgame": 874,
1310
+ "iel": 875,
1311
+ "Ġhist": 876,
1312
+ "ute": 877,
1313
+ "ĠGal": 878,
1314
+ "Ġwhere": 879,
1315
+ "fore": 880,
1316
+ "ating": 881,
1317
+ "Ġrep": 882,
1318
+ "resent": 883,
1319
+ "ject": 884,
1320
+ "Ġsy": 885,
1321
+ "orld": 886,
1322
+ "Ġpr": 887,
1323
+ "Ġbl": 888,
1324
+ "amp": 889,
1325
+ "iet": 890,
1326
+ "ob": 891,
1327
+ "Ġap": 892,
1328
+ "though": 893,
1329
+ "ove": 894,
1330
+ "ĠBritish": 895,
1331
+ "Ġbetween": 896,
1332
+ "veston": 897,
1333
+ "ĠGalveston": 898,
1334
+ "erman": 899,
1335
+ "row": 900,
1336
+ "Ġant": 901,
1337
+ "Ġship": 902,
1338
+ "ĠChrist": 903,
1339
+ "az": 904,
1340
+ "ool": 905,
1341
+ "Ġthere": 906,
1342
+ "Ġsign": 907,
1343
+ "ĠBl": 908,
1344
+ "Ġsur": 909,
1345
+ "ised": 910,
1346
+ "ired": 911,
1347
+ "ĠYork": 912,
1348
+ "94": 913,
1349
+ "led": 914,
1350
+ "Ġcity": 915,
1351
+ "ĠAll": 916,
1352
+ "98": 917,
1353
+ "up": 918,
1354
+ "Ġchar": 919,
1355
+ "Ġsong": 920,
1356
+ "Ġcall": 921,
1357
+ "ĠGerman": 922,
1358
+ "Ġmany": 923,
1359
+ "Ġnumber": 924,
1360
+ "Ġhigh": 925,
1361
+ "ug": 926,
1362
+ "ics": 927,
1363
+ "ican": 928,
1364
+ "Ġmin": 929,
1365
+ "Ġloc": 930,
1366
+ "Ġno": 931,
1367
+ "Ġwhile": 932,
1368
+ "air": 933,
1369
+ "Ġqu": 934,
1370
+ "Ġboth": 935,
1371
+ "Ġele": 936,
1372
+ "rans": 937,
1373
+ "Ġsupp": 938,
1374
+ "ever": 939,
1375
+ "ĠTown": 940,
1376
+ "ivers": 941,
1377
+ "ife": 942,
1378
+ "Ġlead": 943,
1379
+ "Ġused": 944,
1380
+ "hes": 945,
1381
+ "ived": 946,
1382
+ "veral": 947,
1383
+ "Ġthen": 948,
1384
+ "Ġso": 949,
1385
+ "Ġyears": 950,
1386
+ "Ġgods": 951,
1387
+ "gy": 952,
1388
+ "ren": 953,
1389
+ "Ġlong": 954,
1390
+ "Ġdesc": 955,
1391
+ "91": 956,
1392
+ "Ġbel": 957,
1393
+ "oh": 958,
1394
+ "view": 959,
1395
+ "ause": 960,
1396
+ "ale": 961,
1397
+ "ros": 962,
1398
+ "other": 963,
1399
+ "elf": 964,
1400
+ "ning": 965,
1401
+ "ral": 966,
1402
+ "Ġfollow": 967,
1403
+ "ĠUnited": 968,
1404
+ "Ġdif": 969,
1405
+ "ĠAmer": 970,
1406
+ "very": 971,
1407
+ "ures": 972,
1408
+ "Ġsch": 973,
1409
+ "Ġday": 974,
1410
+ "Ġent": 975,
1411
+ "Ġwell": 976,
1412
+ "Ġmain": 977,
1413
+ "ĠThis": 978,
1414
+ "Ġtr": 979,
1415
+ "Ġdef": 980,
1416
+ "20": 981,
1417
+ "Ġob": 982,
1418
+ "Ġcre": 983,
1419
+ "tern": 984,
1420
+ "ty": 985,
1421
+ "ĠCl": 986,
1422
+ "Ġem": 987,
1423
+ "Ġbefore": 988,
1424
+ "ists": 989,
1425
+ "ĠMar": 990,
1426
+ "raft": 991,
1427
+ "Ġbecame": 992,
1428
+ "Ġthese": 993,
1429
+ "emb": 994,
1430
+ "Ġperform": 995,
1431
+ "Ġagainst": 996,
1432
+ "ah": 997,
1433
+ "ople": 998,
1434
+ "ized": 999,
1435
+ "ield": 1000,
1436
+ "Ġappe": 1001,
1437
+ "stru": 1002,
1438
+ "Ġdep": 1003,
1439
+ "30": 1004,
1440
+ "Ġoper": 1005,
1441
+ "Ġpop": 1006,
1442
+ "Ġknown": 1007,
1443
+ "stein": 1008,
1444
+ "io": 1009,
1445
+ "ys": 1010,
1446
+ "ĠZ": 1011,
1447
+ "Ġcar": 1012,
1448
+ "Ġcol": 1013,
1449
+ "ident": 1014,
1450
+ "owever": 1015,
1451
+ "cept": 1016,
1452
+ "Ġremain": 1017,
1453
+ "son": 1018,
1454
+ "Ġstud": 1019,
1455
+ "Ġincluding": 1020,
1456
+ "Ġ%": 1021,
1457
+ "ĠAnd": 1022,
1458
+ "Ġorig": 1023
1459
+ },
1460
+ "merges": [
1461
+ [
1462
+ "Ġ",
1463
+ "t"
1464
+ ],
1465
+ [
1466
+ "h",
1467
+ "e"
1468
+ ],
1469
+ [
1470
+ "Ġ",
1471
+ "a"
1472
+ ],
1473
+ [
1474
+ "i",
1475
+ "n"
1476
+ ],
1477
+ [
1478
+ "Ġt",
1479
+ "he"
1480
+ ],
1481
+ [
1482
+ "e",
1483
+ "r"
1484
+ ],
1485
+ [
1486
+ "o",
1487
+ "n"
1488
+ ],
1489
+ [
1490
+ "Ġ",
1491
+ ","
1492
+ ],
1493
+ [
1494
+ "r",
1495
+ "e"
1496
+ ],
1497
+ [
1498
+ "Ġ",
1499
+ "s"
1500
+ ],
1501
+ [
1502
+ "e",
1503
+ "d"
1504
+ ],
1505
+ [
1506
+ "Ġ",
1507
+ "o"
1508
+ ],
1509
+ [
1510
+ "n",
1511
+ "d"
1512
+ ],
1513
+ [
1514
+ "Ġ",
1515
+ "w"
1516
+ ],
1517
+ [
1518
+ "a",
1519
+ "t"
1520
+ ],
1521
+ [
1522
+ "Ġ",
1523
+ "."
1524
+ ],
1525
+ [
1526
+ "o",
1527
+ "r"
1528
+ ],
1529
+ [
1530
+ "i",
1531
+ "t"
1532
+ ],
1533
+ [
1534
+ "i",
1535
+ "s"
1536
+ ],
1537
+ [
1538
+ "Ġ",
1539
+ "c"
1540
+ ],
1541
+ [
1542
+ "e",
1543
+ "s"
1544
+ ],
1545
+ [
1546
+ "Ġ",
1547
+ "f"
1548
+ ],
1549
+ [
1550
+ "e",
1551
+ "n"
1552
+ ],
1553
+ [
1554
+ "Ġo",
1555
+ "f"
1556
+ ],
1557
+ [
1558
+ "a",
1559
+ "r"
1560
+ ],
1561
+ [
1562
+ "a",
1563
+ "l"
1564
+ ],
1565
+ [
1566
+ "Ġ",
1567
+ "in"
1568
+ ],
1569
+ [
1570
+ "Ġ",
1571
+ "b"
1572
+ ],
1573
+ [
1574
+ "a",
1575
+ "n"
1576
+ ],
1577
+ [
1578
+ "Ġ",
1579
+ "p"
1580
+ ],
1581
+ [
1582
+ "in",
1583
+ "g"
1584
+ ],
1585
+ [
1586
+ "a",
1587
+ "s"
1588
+ ],
1589
+ [
1590
+ "Ġa",
1591
+ "nd"
1592
+ ],
1593
+ [
1594
+ "i",
1595
+ "c"
1596
+ ],
1597
+ [
1598
+ "Ġt",
1599
+ "o"
1600
+ ],
1601
+ [
1602
+ "Ġ",
1603
+ "m"
1604
+ ],
1605
+ [
1606
+ "r",
1607
+ "o"
1608
+ ],
1609
+ [
1610
+ "Ġ",
1611
+ "d"
1612
+ ],
1613
+ [
1614
+ "Ġ",
1615
+ "h"
1616
+ ],
1617
+ [
1618
+ "i",
1619
+ "on"
1620
+ ],
1621
+ [
1622
+ "l",
1623
+ "e"
1624
+ ],
1625
+ [
1626
+ "Ġ",
1627
+ "T"
1628
+ ],
1629
+ [
1630
+ "o",
1631
+ "u"
1632
+ ],
1633
+ [
1634
+ "Ġ",
1635
+ "re"
1636
+ ],
1637
+ [
1638
+ "Ġ",
1639
+ "="
1640
+ ],
1641
+ [
1642
+ "Ġ",
1643
+ "A"
1644
+ ],
1645
+ [
1646
+ "Ġ",
1647
+ "\""
1648
+ ],
1649
+ [
1650
+ "Ġ",
1651
+ "S"
1652
+ ],
1653
+ [
1654
+ "Ġt",
1655
+ "h"
1656
+ ],
1657
+ [
1658
+ "en",
1659
+ "t"
1660
+ ],
1661
+ [
1662
+ "i",
1663
+ "l"
1664
+ ],
1665
+ [
1666
+ "s",
1667
+ "t"
1668
+ ],
1669
+ [
1670
+ "Ġ",
1671
+ "@"
1672
+ ],
1673
+ [
1674
+ "e",
1675
+ "l"
1676
+ ],
1677
+ [
1678
+ "Ġ",
1679
+ "C"
1680
+ ],
1681
+ [
1682
+ "Ġ",
1683
+ "Ċ"
1684
+ ],
1685
+ [
1686
+ "o",
1687
+ "l"
1688
+ ],
1689
+ [
1690
+ "Ġ",
1691
+ "l"
1692
+ ],
1693
+ [
1694
+ "Ġ",
1695
+ "n"
1696
+ ],
1697
+ [
1698
+ "o",
1699
+ "m"
1700
+ ],
1701
+ [
1702
+ "Ġ",
1703
+ "e"
1704
+ ],
1705
+ [
1706
+ "c",
1707
+ "t"
1708
+ ],
1709
+ [
1710
+ "a",
1711
+ "m"
1712
+ ],
1713
+ [
1714
+ "a",
1715
+ "d"
1716
+ ],
1717
+ [
1718
+ "Ġ",
1719
+ "g"
1720
+ ],
1721
+ [
1722
+ "Ġw",
1723
+ "as"
1724
+ ],
1725
+ [
1726
+ "u",
1727
+ "r"
1728
+ ],
1729
+ [
1730
+ "Ġ",
1731
+ "on"
1732
+ ],
1733
+ [
1734
+ "ĠT",
1735
+ "he"
1736
+ ],
1737
+ [
1738
+ "Ġ",
1739
+ "I"
1740
+ ],
1741
+ [
1742
+ "i",
1743
+ "m"
1744
+ ],
1745
+ [
1746
+ "-",
1747
+ "@"
1748
+ ],
1749
+ [
1750
+ "Ġ@",
1751
+ "-@"
1752
+ ],
1753
+ [
1754
+ "Ġb",
1755
+ "e"
1756
+ ],
1757
+ [
1758
+ "l",
1759
+ "y"
1760
+ ],
1761
+ [
1762
+ "Ġ",
1763
+ "M"
1764
+ ],
1765
+ [
1766
+ "i",
1767
+ "d"
1768
+ ],
1769
+ [
1770
+ "Ġf",
1771
+ "or"
1772
+ ],
1773
+ [
1774
+ "i",
1775
+ "r"
1776
+ ],
1777
+ [
1778
+ "c",
1779
+ "h"
1780
+ ],
1781
+ [
1782
+ "Ġ",
1783
+ "B"
1784
+ ],
1785
+ [
1786
+ "i",
1787
+ "v"
1788
+ ],
1789
+ [
1790
+ "o",
1791
+ "t"
1792
+ ],
1793
+ [
1794
+ "Ġ",
1795
+ "'"
1796
+ ],
1797
+ [
1798
+ "it",
1799
+ "h"
1800
+ ],
1801
+ [
1802
+ "at",
1803
+ "ion"
1804
+ ],
1805
+ [
1806
+ "r",
1807
+ "a"
1808
+ ],
1809
+ [
1810
+ "i",
1811
+ "g"
1812
+ ],
1813
+ [
1814
+ "Ġa",
1815
+ "s"
1816
+ ],
1817
+ [
1818
+ "e",
1819
+ "t"
1820
+ ],
1821
+ [
1822
+ "o",
1823
+ "w"
1824
+ ],
1825
+ [
1826
+ "u",
1827
+ "s"
1828
+ ],
1829
+ [
1830
+ "u",
1831
+ "t"
1832
+ ],
1833
+ [
1834
+ "Ġs",
1835
+ "t"
1836
+ ],
1837
+ [
1838
+ "c",
1839
+ "e"
1840
+ ],
1841
+ [
1842
+ "Ġw",
1843
+ "ith"
1844
+ ],
1845
+ [
1846
+ "Ġ",
1847
+ "P"
1848
+ ],
1849
+ [
1850
+ "er",
1851
+ "s"
1852
+ ],
1853
+ [
1854
+ "Ġ",
1855
+ "he"
1856
+ ],
1857
+ [
1858
+ "Ġth",
1859
+ "at"
1860
+ ],
1861
+ [
1862
+ "a",
1863
+ "y"
1864
+ ],
1865
+ [
1866
+ "Ġ",
1867
+ "is"
1868
+ ],
1869
+ [
1870
+ "Ġ",
1871
+ "H"
1872
+ ],
1873
+ [
1874
+ "u",
1875
+ "l"
1876
+ ],
1877
+ [
1878
+ "Ġ",
1879
+ "G"
1880
+ ],
1881
+ [
1882
+ "Ġ",
1883
+ "F"
1884
+ ],
1885
+ [
1886
+ "Ġa",
1887
+ "l"
1888
+ ],
1889
+ [
1890
+ "Ġ",
1891
+ "R"
1892
+ ],
1893
+ [
1894
+ "Ġ",
1895
+ "N"
1896
+ ],
1897
+ [
1898
+ "is",
1899
+ "t"
1900
+ ],
1901
+ [
1902
+ "u",
1903
+ "m"
1904
+ ],
1905
+ [
1906
+ "e",
1907
+ "m"
1908
+ ],
1909
+ [
1910
+ "Ġw",
1911
+ "h"
1912
+ ],
1913
+ [
1914
+ "Ġ",
1915
+ "W"
1916
+ ],
1917
+ [
1918
+ "es",
1919
+ "t"
1920
+ ],
1921
+ [
1922
+ "Ġb",
1923
+ "y"
1924
+ ],
1925
+ [
1926
+ "u",
1927
+ "n"
1928
+ ],
1929
+ [
1930
+ "Ġa",
1931
+ "n"
1932
+ ],
1933
+ [
1934
+ "v",
1935
+ "er"
1936
+ ],
1937
+ [
1938
+ "o",
1939
+ "s"
1940
+ ],
1941
+ [
1942
+ "t",
1943
+ "h"
1944
+ ],
1945
+ [
1946
+ "Ġ",
1947
+ ")"
1948
+ ],
1949
+ [
1950
+ "Ġ",
1951
+ "("
1952
+ ],
1953
+ [
1954
+ "t",
1955
+ "er"
1956
+ ],
1957
+ [
1958
+ "Ġc",
1959
+ "on"
1960
+ ],
1961
+ [
1962
+ "Ġ",
1963
+ "J"
1964
+ ],
1965
+ [
1966
+ "ro",
1967
+ "m"
1968
+ ],
1969
+ [
1970
+ "Ġ",
1971
+ "D"
1972
+ ],
1973
+ [
1974
+ "Ġa",
1975
+ "t"
1976
+ ],
1977
+ [
1978
+ "Ġs",
1979
+ "e"
1980
+ ],
1981
+ [
1982
+ "a",
1983
+ "nd"
1984
+ ],
1985
+ [
1986
+ "o",
1987
+ "d"
1988
+ ],
1989
+ [
1990
+ "Ġ",
1991
+ "L"
1992
+ ],
1993
+ [
1994
+ "a",
1995
+ "v"
1996
+ ],
1997
+ [
1998
+ "Ġ",
1999
+ "it"
2000
+ ],
2001
+ [
2002
+ "0",
2003
+ "0"
2004
+ ],
2005
+ [
2006
+ "Ġd",
2007
+ "e"
2008
+ ],
2009
+ [
2010
+ "a",
2011
+ "g"
2012
+ ],
2013
+ [
2014
+ "he",
2015
+ "r"
2016
+ ],
2017
+ [
2018
+ "i",
2019
+ "es"
2020
+ ],
2021
+ [
2022
+ "p",
2023
+ "e"
2024
+ ],
2025
+ [
2026
+ "Ġ",
2027
+ "E"
2028
+ ],
2029
+ [
2030
+ "a",
2031
+ "in"
2032
+ ],
2033
+ [
2034
+ "c",
2035
+ "k"
2036
+ ],
2037
+ [
2038
+ "Ġh",
2039
+ "is"
2040
+ ],
2041
+ [
2042
+ "r",
2043
+ "i"
2044
+ ],
2045
+ [
2046
+ "Ġf",
2047
+ "rom"
2048
+ ],
2049
+ [
2050
+ "er",
2051
+ "e"
2052
+ ],
2053
+ [
2054
+ "re",
2055
+ "s"
2056
+ ],
2057
+ [
2058
+ "or",
2059
+ "t"
2060
+ ],
2061
+ [
2062
+ "Ġp",
2063
+ "ro"
2064
+ ],
2065
+ [
2066
+ "i",
2067
+ "f"
2068
+ ],
2069
+ [
2070
+ "Ġc",
2071
+ "om"
2072
+ ],
2073
+ [
2074
+ "e",
2075
+ "w"
2076
+ ],
2077
+ [
2078
+ "it",
2079
+ "y"
2080
+ ],
2081
+ [
2082
+ "Ġw",
2083
+ "ere"
2084
+ ],
2085
+ [
2086
+ "Ġ",
2087
+ "v"
2088
+ ],
2089
+ [
2090
+ "at",
2091
+ "e"
2092
+ ],
2093
+ [
2094
+ "ĠI",
2095
+ "n"
2096
+ ],
2097
+ [
2098
+ "Ġs",
2099
+ "u"
2100
+ ],
2101
+ [
2102
+ "Ġ",
2103
+ "O"
2104
+ ],
2105
+ [
2106
+ "o",
2107
+ "p"
2108
+ ],
2109
+ [
2110
+ "Ġo",
2111
+ "r"
2112
+ ],
2113
+ [
2114
+ "ic",
2115
+ "h"
2116
+ ],
2117
+ [
2118
+ "o",
2119
+ "re"
2120
+ ],
2121
+ [
2122
+ "al",
2123
+ "l"
2124
+ ],
2125
+ [
2126
+ "ig",
2127
+ "h"
2128
+ ],
2129
+ [
2130
+ "at",
2131
+ "ed"
2132
+ ],
2133
+ [
2134
+ "or",
2135
+ "d"
2136
+ ],
2137
+ [
2138
+ "s",
2139
+ "e"
2140
+ ],
2141
+ [
2142
+ "il",
2143
+ "l"
2144
+ ],
2145
+ [
2146
+ "ar",
2147
+ "t"
2148
+ ],
2149
+ [
2150
+ "Ġe",
2151
+ "x"
2152
+ ],
2153
+ [
2154
+ "a",
2155
+ "b"
2156
+ ],
2157
+ [
2158
+ "p",
2159
+ "t"
2160
+ ],
2161
+ [
2162
+ "Ġc",
2163
+ "h"
2164
+ ],
2165
+ [
2166
+ "Ġs",
2167
+ "h"
2168
+ ],
2169
+ [
2170
+ "l",
2171
+ "d"
2172
+ ],
2173
+ [
2174
+ "Ġp",
2175
+ "l"
2176
+ ],
2177
+ [
2178
+ "p",
2179
+ "p"
2180
+ ],
2181
+ [
2182
+ "a",
2183
+ "k"
2184
+ ],
2185
+ [
2186
+ "Ġa",
2187
+ "re"
2188
+ ],
2189
+ [
2190
+ "b",
2191
+ "er"
2192
+ ],
2193
+ [
2194
+ "g",
2195
+ "h"
2196
+ ],
2197
+ [
2198
+ "es",
2199
+ "s"
2200
+ ],
2201
+ [
2202
+ "u",
2203
+ "d"
2204
+ ],
2205
+ [
2206
+ "Ġ",
2207
+ "â"
2208
+ ],
2209
+ [
2210
+ "an",
2211
+ "t"
2212
+ ],
2213
+ [
2214
+ "ar",
2215
+ "d"
2216
+ ],
2217
+ [
2218
+ "ro",
2219
+ "u"
2220
+ ],
2221
+ [
2222
+ "on",
2223
+ "g"
2224
+ ],
2225
+ [
2226
+ "Ġ",
2227
+ "U"
2228
+ ],
2229
+ [
2230
+ "r",
2231
+ "u"
2232
+ ],
2233
+ [
2234
+ "i",
2235
+ "a"
2236
+ ],
2237
+ [
2238
+ "q",
2239
+ "u"
2240
+ ],
2241
+ [
2242
+ "Ġwh",
2243
+ "ich"
2244
+ ],
2245
+ [
2246
+ "Ġâ",
2247
+ "Ģ"
2248
+ ],
2249
+ [
2250
+ "am",
2251
+ "e"
2252
+ ],
2253
+ [
2254
+ "m",
2255
+ "ent"
2256
+ ],
2257
+ [
2258
+ "ĠC",
2259
+ "h"
2260
+ ],
2261
+ [
2262
+ "Ġ",
2263
+ "le"
2264
+ ],
2265
+ [
2266
+ "r",
2267
+ "it"
2268
+ ],
2269
+ [
2270
+ "Ġh",
2271
+ "ad"
2272
+ ],
2273
+ [
2274
+ "i",
2275
+ "al"
2276
+ ],
2277
+ [
2278
+ "i",
2279
+ "an"
2280
+ ],
2281
+ [
2282
+ "o",
2283
+ "g"
2284
+ ],
2285
+ [
2286
+ "re",
2287
+ "d"
2288
+ ],
2289
+ [
2290
+ "Ġ",
2291
+ "K"
2292
+ ],
2293
+ [
2294
+ "ĠS",
2295
+ "t"
2296
+ ],
2297
+ [
2298
+ "iv",
2299
+ "e"
2300
+ ],
2301
+ [
2302
+ "o",
2303
+ "c"
2304
+ ],
2305
+ [
2306
+ "i",
2307
+ "p"
2308
+ ],
2309
+ [
2310
+ "o",
2311
+ "v"
2312
+ ],
2313
+ [
2314
+ "Ġ",
2315
+ ";"
2316
+ ],
2317
+ [
2318
+ "Ġ",
2319
+ "r"
2320
+ ],
2321
+ [
2322
+ "is",
2323
+ "h"
2324
+ ],
2325
+ [
2326
+ "o",
2327
+ "st"
2328
+ ],
2329
+ [
2330
+ "ou",
2331
+ "r"
2332
+ ],
2333
+ [
2334
+ "Ġa",
2335
+ "r"
2336
+ ],
2337
+ [
2338
+ "Ġ",
2339
+ "u"
2340
+ ],
2341
+ [
2342
+ "Ġn",
2343
+ "ot"
2344
+ ],
2345
+ [
2346
+ "e",
2347
+ "ar"
2348
+ ],
2349
+ [
2350
+ "igh",
2351
+ "t"
2352
+ ],
2353
+ [
2354
+ "as",
2355
+ "t"
2356
+ ],
2357
+ [
2358
+ "a",
2359
+ "c"
2360
+ ],
2361
+ [
2362
+ "Ġ",
2363
+ "y"
2364
+ ],
2365
+ [
2366
+ "Ġ",
2367
+ "k"
2368
+ ],
2369
+ [
2370
+ "av",
2371
+ "e"
2372
+ ],
2373
+ [
2374
+ "ar",
2375
+ "y"
2376
+ ],
2377
+ [
2378
+ "el",
2379
+ "l"
2380
+ ],
2381
+ [
2382
+ "t",
2383
+ "her"
2384
+ ],
2385
+ [
2386
+ "ct",
2387
+ "ion"
2388
+ ],
2389
+ [
2390
+ "ic",
2391
+ "al"
2392
+ ],
2393
+ [
2394
+ "n",
2395
+ "t"
2396
+ ],
2397
+ [
2398
+ "ow",
2399
+ "n"
2400
+ ],
2401
+ [
2402
+ "c",
2403
+ "c"
2404
+ ],
2405
+ [
2406
+ "Ġin",
2407
+ "c"
2408
+ ],
2409
+ [
2410
+ "in",
2411
+ "e"
2412
+ ],
2413
+ [
2414
+ "g",
2415
+ "e"
2416
+ ],
2417
+ [
2418
+ "id",
2419
+ "e"
2420
+ ],
2421
+ [
2422
+ "u",
2423
+ "st"
2424
+ ],
2425
+ [
2426
+ "ĠâĢ",
2427
+ "ĵ"
2428
+ ],
2429
+ [
2430
+ "Ġhe",
2431
+ "r"
2432
+ ],
2433
+ [
2434
+ "s",
2435
+ "o"
2436
+ ],
2437
+ [
2438
+ "a",
2439
+ "p"
2440
+ ],
2441
+ [
2442
+ "u",
2443
+ "e"
2444
+ ],
2445
+ [
2446
+ "u",
2447
+ "re"
2448
+ ],
2449
+ [
2450
+ "or",
2451
+ "k"
2452
+ ],
2453
+ [
2454
+ "r",
2455
+ "an"
2456
+ ],
2457
+ [
2458
+ "ou",
2459
+ "t"
2460
+ ],
2461
+ [
2462
+ "Ġal",
2463
+ "so"
2464
+ ],
2465
+ [
2466
+ "Ġthe",
2467
+ "ir"
2468
+ ],
2469
+ [
2470
+ "Ġh",
2471
+ "as"
2472
+ ],
2473
+ [
2474
+ "w",
2475
+ "o"
2476
+ ],
2477
+ [
2478
+ "Ġ",
2479
+ "un"
2480
+ ],
2481
+ [
2482
+ "ou",
2483
+ "s"
2484
+ ],
2485
+ [
2486
+ "f",
2487
+ "f"
2488
+ ],
2489
+ [
2490
+ "ig",
2491
+ "n"
2492
+ ],
2493
+ [
2494
+ "f",
2495
+ "ter"
2496
+ ],
2497
+ [
2498
+ "Ġ",
2499
+ "V"
2500
+ ],
2501
+ [
2502
+ "u",
2503
+ "b"
2504
+ ],
2505
+ [
2506
+ "Ġre",
2507
+ "c"
2508
+ ],
2509
+ [
2510
+ "om",
2511
+ "e"
2512
+ ],
2513
+ [
2514
+ "0",
2515
+ "1"
2516
+ ],
2517
+ [
2518
+ "Ġc",
2519
+ "l"
2520
+ ],
2521
+ [
2522
+ ".",
2523
+ "@"
2524
+ ],
2525
+ [
2526
+ "Ġ@",
2527
+ ".@"
2528
+ ],
2529
+ [
2530
+ "Ġcon",
2531
+ "t"
2532
+ ],
2533
+ [
2534
+ "ir",
2535
+ "st"
2536
+ ],
2537
+ [
2538
+ "ĠH",
2539
+ "e"
2540
+ ],
2541
+ [
2542
+ "Ġt",
2543
+ "e"
2544
+ ],
2545
+ [
2546
+ "it",
2547
+ "ion"
2548
+ ],
2549
+ [
2550
+ "at",
2551
+ "er"
2552
+ ],
2553
+ [
2554
+ "Ġp",
2555
+ "er"
2556
+ ],
2557
+ [
2558
+ "as",
2559
+ "s"
2560
+ ],
2561
+ [
2562
+ "a",
2563
+ "ck"
2564
+ ],
2565
+ [
2566
+ "ation",
2567
+ "s"
2568
+ ],
2569
+ [
2570
+ "i",
2571
+ "e"
2572
+ ],
2573
+ [
2574
+ "Ġit",
2575
+ "s"
2576
+ ],
2577
+ [
2578
+ "Ġa",
2579
+ "b"
2580
+ ],
2581
+ [
2582
+ "p",
2583
+ "l"
2584
+ ],
2585
+ [
2586
+ "Ġon",
2587
+ "e"
2588
+ ],
2589
+ [
2590
+ "Ġin",
2591
+ "t"
2592
+ ],
2593
+ [
2594
+ "Ġs",
2595
+ "c"
2596
+ ],
2597
+ [
2598
+ "Ġf",
2599
+ "irst"
2600
+ ],
2601
+ [
2602
+ "on",
2603
+ "d"
2604
+ ],
2605
+ [
2606
+ "im",
2607
+ "e"
2608
+ ],
2609
+ [
2610
+ "he",
2611
+ "d"
2612
+ ],
2613
+ [
2614
+ "Ġ",
2615
+ ":"
2616
+ ],
2617
+ [
2618
+ "or",
2619
+ "m"
2620
+ ],
2621
+ [
2622
+ "ul",
2623
+ "t"
2624
+ ],
2625
+ [
2626
+ "ou",
2627
+ "ld"
2628
+ ],
2629
+ [
2630
+ "or",
2631
+ "y"
2632
+ ],
2633
+ [
2634
+ "Ġwh",
2635
+ "o"
2636
+ ],
2637
+ [
2638
+ "Ġw",
2639
+ "he"
2640
+ ],
2641
+ [
2642
+ "ĠT",
2643
+ "h"
2644
+ ],
2645
+ [
2646
+ "p",
2647
+ "er"
2648
+ ],
2649
+ [
2650
+ "Ġb",
2651
+ "ut"
2652
+ ],
2653
+ [
2654
+ "Ġh",
2655
+ "ave"
2656
+ ],
2657
+ [
2658
+ "Ġt",
2659
+ "wo"
2660
+ ],
2661
+ [
2662
+ "nd",
2663
+ "er"
2664
+ ],
2665
+ [
2666
+ "ĠA",
2667
+ "l"
2668
+ ],
2669
+ [
2670
+ "e",
2671
+ "ct"
2672
+ ],
2673
+ [
2674
+ "Ġth",
2675
+ "is"
2676
+ ],
2677
+ [
2678
+ "o",
2679
+ "k"
2680
+ ],
2681
+ [
2682
+ "ar",
2683
+ "k"
2684
+ ],
2685
+ [
2686
+ "ur",
2687
+ "ing"
2688
+ ],
2689
+ [
2690
+ "d",
2691
+ "u"
2692
+ ],
2693
+ [
2694
+ "i",
2695
+ "re"
2696
+ ],
2697
+ [
2698
+ "ou",
2699
+ "gh"
2700
+ ],
2701
+ [
2702
+ "u",
2703
+ "al"
2704
+ ],
2705
+ [
2706
+ "Ġal",
2707
+ "l"
2708
+ ],
2709
+ [
2710
+ "Ġ",
2711
+ "Y"
2712
+ ],
2713
+ [
2714
+ "i",
2715
+ "z"
2716
+ ],
2717
+ [
2718
+ "m",
2719
+ "er"
2720
+ ],
2721
+ [
2722
+ "Ġ",
2723
+ "us"
2724
+ ],
2725
+ [
2726
+ "a",
2727
+ "ch"
2728
+ ],
2729
+ [
2730
+ "ol",
2731
+ "l"
2732
+ ],
2733
+ [
2734
+ "Ġbe",
2735
+ "en"
2736
+ ],
2737
+ [
2738
+ "Ġpl",
2739
+ "ay"
2740
+ ],
2741
+ [
2742
+ "Ġre",
2743
+ "s"
2744
+ ],
2745
+ [
2746
+ "re",
2747
+ "e"
2748
+ ],
2749
+ [
2750
+ "Ġs",
2751
+ "he"
2752
+ ],
2753
+ [
2754
+ ",",
2755
+ "@"
2756
+ ],
2757
+ [
2758
+ "Ġ@",
2759
+ ",@"
2760
+ ],
2761
+ [
2762
+ "ag",
2763
+ "e"
2764
+ ],
2765
+ [
2766
+ "Ġof",
2767
+ "f"
2768
+ ],
2769
+ [
2770
+ "e",
2771
+ "y"
2772
+ ],
2773
+ [
2774
+ "Ġcom",
2775
+ "p"
2776
+ ],
2777
+ [
2778
+ "Ġa",
2779
+ "g"
2780
+ ],
2781
+ [
2782
+ "as",
2783
+ "on"
2784
+ ],
2785
+ [
2786
+ "p",
2787
+ "ort"
2788
+ ],
2789
+ [
2790
+ "o",
2791
+ "in"
2792
+ ],
2793
+ [
2794
+ "Ġa",
2795
+ "d"
2796
+ ],
2797
+ [
2798
+ "Ġy",
2799
+ "ear"
2800
+ ],
2801
+ [
2802
+ "Ġ",
2803
+ "im"
2804
+ ],
2805
+ [
2806
+ "ĠI",
2807
+ "t"
2808
+ ],
2809
+ [
2810
+ "en",
2811
+ "ce"
2812
+ ],
2813
+ [
2814
+ "Ġp",
2815
+ "art"
2816
+ ],
2817
+ [
2818
+ "Ġd",
2819
+ "es"
2820
+ ],
2821
+ [
2822
+ "k",
2823
+ "e"
2824
+ ],
2825
+ [
2826
+ "r",
2827
+ "ic"
2828
+ ],
2829
+ [
2830
+ "a",
2831
+ "re"
2832
+ ],
2833
+ [
2834
+ "r",
2835
+ "y"
2836
+ ],
2837
+ [
2838
+ "l",
2839
+ "ud"
2840
+ ],
2841
+ [
2842
+ "Ġbe",
2843
+ "c"
2844
+ ],
2845
+ [
2846
+ "t",
2847
+ "e"
2848
+ ],
2849
+ [
2850
+ "Ġ",
2851
+ "j"
2852
+ ],
2853
+ [
2854
+ "Ġo",
2855
+ "ther"
2856
+ ],
2857
+ [
2858
+ "el",
2859
+ "y"
2860
+ ],
2861
+ [
2862
+ "Ġd",
2863
+ "is"
2864
+ ],
2865
+ [
2866
+ "p",
2867
+ "h"
2868
+ ],
2869
+ [
2870
+ "Ġm",
2871
+ "an"
2872
+ ],
2873
+ [
2874
+ "ou",
2875
+ "nd"
2876
+ ],
2877
+ [
2878
+ "ol",
2879
+ "d"
2880
+ ],
2881
+ [
2882
+ "Ġs",
2883
+ "pe"
2884
+ ],
2885
+ [
2886
+ "a",
2887
+ "ct"
2888
+ ],
2889
+ [
2890
+ "Ġ",
2891
+ "ro"
2892
+ ],
2893
+ [
2894
+ "Ġa",
2895
+ "fter"
2896
+ ],
2897
+ [
2898
+ "an",
2899
+ "ce"
2900
+ ],
2901
+ [
2902
+ "at",
2903
+ "h"
2904
+ ],
2905
+ [
2906
+ "Ġ",
2907
+ "en"
2908
+ ],
2909
+ [
2910
+ "it",
2911
+ "ed"
2912
+ ],
2913
+ [
2914
+ "ĠU",
2915
+ "n"
2916
+ ],
2917
+ [
2918
+ "Ġg",
2919
+ "o"
2920
+ ],
2921
+ [
2922
+ "i",
2923
+ "b"
2924
+ ],
2925
+ [
2926
+ "i",
2927
+ "le"
2928
+ ],
2929
+ [
2930
+ "Ġthe",
2931
+ "y"
2932
+ ],
2933
+ [
2934
+ "it",
2935
+ "e"
2936
+ ],
2937
+ [
2938
+ "m",
2939
+ "an"
2940
+ ],
2941
+ [
2942
+ "it",
2943
+ "ies"
2944
+ ],
2945
+ [
2946
+ "Ġo",
2947
+ "ver"
2948
+ ],
2949
+ [
2950
+ "c",
2951
+ "ed"
2952
+ ],
2953
+ [
2954
+ "ent",
2955
+ "s"
2956
+ ],
2957
+ [
2958
+ "or",
2959
+ "s"
2960
+ ],
2961
+ [
2962
+ "rou",
2963
+ "nd"
2964
+ ],
2965
+ [
2966
+ "il",
2967
+ "m"
2968
+ ],
2969
+ [
2970
+ "Ġinc",
2971
+ "lud"
2972
+ ],
2973
+ [
2974
+ "Ġp",
2975
+ "re"
2976
+ ],
2977
+ [
2978
+ "ĠR",
2979
+ "e"
2980
+ ],
2981
+ [
2982
+ "v",
2983
+ "i"
2984
+ ],
2985
+ [
2986
+ "ol",
2987
+ "og"
2988
+ ],
2989
+ [
2990
+ "t",
2991
+ "ed"
2992
+ ],
2993
+ [
2994
+ "ad",
2995
+ "e"
2996
+ ],
2997
+ [
2998
+ "i",
2999
+ "ed"
3000
+ ],
3001
+ [
3002
+ "os",
3003
+ "e"
3004
+ ],
3005
+ [
3006
+ "as",
3007
+ "e"
3008
+ ],
3009
+ [
3010
+ "Ġcom",
3011
+ "m"
3012
+ ],
3013
+ [
3014
+ "Ġt",
3015
+ "ime"
3016
+ ],
3017
+ [
3018
+ "Ġs",
3019
+ "er"
3020
+ ],
3021
+ [
3022
+ "in",
3023
+ "al"
3024
+ ],
3025
+ [
3026
+ "Ġse",
3027
+ "ason"
3028
+ ],
3029
+ [
3030
+ "9",
3031
+ "9"
3032
+ ],
3033
+ [
3034
+ "as",
3035
+ "ed"
3036
+ ],
3037
+ [
3038
+ "Ġo",
3039
+ "ut"
3040
+ ],
3041
+ [
3042
+ "ic",
3043
+ "e"
3044
+ ],
3045
+ [
3046
+ "ĠA",
3047
+ "r"
3048
+ ],
3049
+ [
3050
+ "at",
3051
+ "es"
3052
+ ],
3053
+ [
3054
+ "res",
3055
+ "s"
3056
+ ],
3057
+ [
3058
+ "Ġu",
3059
+ "p"
3060
+ ],
3061
+ [
3062
+ "ĠS",
3063
+ "e"
3064
+ ],
3065
+ [
3066
+ "f",
3067
+ "t"
3068
+ ],
3069
+ [
3070
+ "Ġthe",
3071
+ "m"
3072
+ ],
3073
+ [
3074
+ "ub",
3075
+ "l"
3076
+ ],
3077
+ [
3078
+ "l",
3079
+ "es"
3080
+ ],
3081
+ [
3082
+ "il",
3083
+ "d"
3084
+ ],
3085
+ [
3086
+ "Ġs",
3087
+ "p"
3088
+ ],
3089
+ [
3090
+ "Ġe",
3091
+ "v"
3092
+ ],
3093
+ [
3094
+ "Ġm",
3095
+ "ore"
3096
+ ],
3097
+ [
3098
+ "l",
3099
+ "and"
3100
+ ],
3101
+ [
3102
+ "b",
3103
+ "um"
3104
+ ],
3105
+ [
3106
+ "f",
3107
+ "er"
3108
+ ],
3109
+ [
3110
+ "c",
3111
+ "es"
3112
+ ],
3113
+ [
3114
+ "Ġn",
3115
+ "ew"
3116
+ ],
3117
+ [
3118
+ "g",
3119
+ "an"
3120
+ ],
3121
+ [
3122
+ "rou",
3123
+ "gh"
3124
+ ],
3125
+ [
3126
+ "ab",
3127
+ "le"
3128
+ ],
3129
+ [
3130
+ "r",
3131
+ "on"
3132
+ ],
3133
+ [
3134
+ "t",
3135
+ "s"
3136
+ ],
3137
+ [
3138
+ "ĠD",
3139
+ "e"
3140
+ ],
3141
+ [
3142
+ "a",
3143
+ "ce"
3144
+ ],
3145
+ [
3146
+ "Ġn",
3147
+ "e"
3148
+ ],
3149
+ [
3150
+ "Ġg",
3151
+ "od"
3152
+ ],
3153
+ [
3154
+ "o",
3155
+ "ck"
3156
+ ],
3157
+ [
3158
+ "Ġal",
3159
+ "bum"
3160
+ ],
3161
+ [
3162
+ "ri",
3163
+ "b"
3164
+ ],
3165
+ [
3166
+ "w",
3167
+ "ard"
3168
+ ],
3169
+ [
3170
+ "Ġre",
3171
+ "m"
3172
+ ],
3173
+ [
3174
+ "Ġse",
3175
+ "c"
3176
+ ],
3177
+ [
3178
+ "Ġu",
3179
+ "nder"
3180
+ ],
3181
+ [
3182
+ "w",
3183
+ "n"
3184
+ ],
3185
+ [
3186
+ "Ġw",
3187
+ "ork"
3188
+ ],
3189
+ [
3190
+ "er",
3191
+ "ed"
3192
+ ],
3193
+ [
3194
+ "ĠS",
3195
+ "h"
3196
+ ],
3197
+ [
3198
+ "in",
3199
+ "d"
3200
+ ],
3201
+ [
3202
+ "en",
3203
+ "s"
3204
+ ],
3205
+ [
3206
+ "Ġre",
3207
+ "l"
3208
+ ],
3209
+ [
3210
+ "Ġf",
3211
+ "ilm"
3212
+ ],
3213
+ [
3214
+ "us",
3215
+ "e"
3216
+ ],
3217
+ [
3218
+ "Ġh",
3219
+ "im"
3220
+ ],
3221
+ [
3222
+ "ing",
3223
+ "s"
3224
+ ],
3225
+ [
3226
+ "ou",
3227
+ "nt"
3228
+ ],
3229
+ [
3230
+ "Ġrec",
3231
+ "ord"
3232
+ ],
3233
+ [
3234
+ "Ġspe",
3235
+ "c"
3236
+ ],
3237
+ [
3238
+ "ĠW",
3239
+ "he"
3240
+ ],
3241
+ [
3242
+ "Ġint",
3243
+ "o"
3244
+ ],
3245
+ [
3246
+ "ar",
3247
+ "n"
3248
+ ],
3249
+ [
3250
+ "re",
3251
+ "at"
3252
+ ],
3253
+ [
3254
+ "h",
3255
+ "ip"
3256
+ ],
3257
+ [
3258
+ "on",
3259
+ "e"
3260
+ ],
3261
+ [
3262
+ "or",
3263
+ "n"
3264
+ ],
3265
+ [
3266
+ "Ġin",
3267
+ "ter"
3268
+ ],
3269
+ [
3270
+ "ur",
3271
+ "n"
3272
+ ],
3273
+ [
3274
+ "a",
3275
+ "il"
3276
+ ],
3277
+ [
3278
+ "Ġf",
3279
+ "e"
3280
+ ],
3281
+ [
3282
+ "em",
3283
+ "ber"
3284
+ ],
3285
+ [
3286
+ "Ġcon",
3287
+ "s"
3288
+ ],
3289
+ [
3290
+ "f",
3291
+ "orm"
3292
+ ],
3293
+ [
3294
+ "i",
3295
+ "x"
3296
+ ],
3297
+ [
3298
+ "v",
3299
+ "ed"
3300
+ ],
3301
+ [
3302
+ "Ġm",
3303
+ "ost"
3304
+ ],
3305
+ [
3306
+ "Ġre",
3307
+ "g"
3308
+ ],
3309
+ [
3310
+ "ation",
3311
+ "al"
3312
+ ],
3313
+ [
3314
+ "er",
3315
+ "n"
3316
+ ],
3317
+ [
3318
+ "ar",
3319
+ "ly"
3320
+ ],
3321
+ [
3322
+ "ĠP",
3323
+ "ol"
3324
+ ],
3325
+ [
3326
+ "Ġa",
3327
+ "ct"
3328
+ ],
3329
+ [
3330
+ "o",
3331
+ "y"
3332
+ ],
3333
+ [
3334
+ "in",
3335
+ "k"
3336
+ ],
3337
+ [
3338
+ "am",
3339
+ "es"
3340
+ ],
3341
+ [
3342
+ "ord",
3343
+ "an"
3344
+ ],
3345
+ [
3346
+ "ĠJ",
3347
+ "ordan"
3348
+ ],
3349
+ [
3350
+ "ĠO",
3351
+ "n"
3352
+ ],
3353
+ [
3354
+ "Ġa",
3355
+ "ir"
3356
+ ],
3357
+ [
3358
+ "ĠA",
3359
+ "s"
3360
+ ],
3361
+ [
3362
+ "Ġd",
3363
+ "uring"
3364
+ ],
3365
+ [
3366
+ "ĠB",
3367
+ "rit"
3368
+ ],
3369
+ [
3370
+ "ion",
3371
+ "s"
3372
+ ],
3373
+ [
3374
+ "a",
3375
+ "w"
3376
+ ],
3377
+ [
3378
+ "Ġc",
3379
+ "o"
3380
+ ],
3381
+ [
3382
+ "Ġf",
3383
+ "l"
3384
+ ],
3385
+ [
3386
+ "e",
3387
+ "e"
3388
+ ],
3389
+ [
3390
+ "ot",
3391
+ "h"
3392
+ ],
3393
+ [
3394
+ "a",
3395
+ "e"
3396
+ ],
3397
+ [
3398
+ "v",
3399
+ "el"
3400
+ ],
3401
+ [
3402
+ "Ġt",
3403
+ "ra"
3404
+ ],
3405
+ [
3406
+ "on",
3407
+ "s"
3408
+ ],
3409
+ [
3410
+ "an",
3411
+ "g"
3412
+ ],
3413
+ [
3414
+ "ic",
3415
+ "k"
3416
+ ],
3417
+ [
3418
+ "Ġas",
3419
+ "s"
3420
+ ],
3421
+ [
3422
+ "Ġat",
3423
+ "t"
3424
+ ],
3425
+ [
3426
+ "Ġ",
3427
+ "ra"
3428
+ ],
3429
+ [
3430
+ "os",
3431
+ "s"
3432
+ ],
3433
+ [
3434
+ "Ġsu",
3435
+ "b"
3436
+ ],
3437
+ [
3438
+ "Ġk",
3439
+ "n"
3440
+ ],
3441
+ [
3442
+ "Ġon",
3443
+ "ly"
3444
+ ],
3445
+ [
3446
+ "Ġag",
3447
+ "ain"
3448
+ ],
3449
+ [
3450
+ "w",
3451
+ "ay"
3452
+ ],
3453
+ [
3454
+ "00",
3455
+ "0"
3456
+ ],
3457
+ [
3458
+ "an",
3459
+ "s"
3460
+ ],
3461
+ [
3462
+ "Ġm",
3463
+ "e"
3464
+ ],
3465
+ [
3466
+ "Ġn",
3467
+ "um"
3468
+ ],
3469
+ [
3470
+ "Ġfor",
3471
+ "m"
3472
+ ],
3473
+ [
3474
+ "is",
3475
+ "s"
3476
+ ],
3477
+ [
3478
+ "Ġp",
3479
+ "ubl"
3480
+ ],
3481
+ [
3482
+ "n",
3483
+ "g"
3484
+ ],
3485
+ [
3486
+ "is",
3487
+ "hed"
3488
+ ],
3489
+ [
3490
+ "ar",
3491
+ "g"
3492
+ ],
3493
+ [
3494
+ "Ġre",
3495
+ "t"
3496
+ ],
3497
+ [
3498
+ "Ġre",
3499
+ "le"
3500
+ ],
3501
+ [
3502
+ "Ġw",
3503
+ "ould"
3504
+ ],
3505
+ [
3506
+ "e",
3507
+ "en"
3508
+ ],
3509
+ [
3510
+ "v",
3511
+ "e"
3512
+ ],
3513
+ [
3514
+ "Ġf",
3515
+ "our"
3516
+ ],
3517
+ [
3518
+ "ic",
3519
+ "t"
3520
+ ],
3521
+ [
3522
+ "Ġth",
3523
+ "ree"
3524
+ ],
3525
+ [
3526
+ "ers",
3527
+ "on"
3528
+ ],
3529
+ [
3530
+ "t",
3531
+ "le"
3532
+ ],
3533
+ [
3534
+ "Ġpro",
3535
+ "du"
3536
+ ],
3537
+ [
3538
+ "Ġm",
3539
+ "on"
3540
+ ],
3541
+ [
3542
+ "Ġte",
3543
+ "am"
3544
+ ],
3545
+ [
3546
+ "o",
3547
+ "ok"
3548
+ ],
3549
+ [
3550
+ "or",
3551
+ "th"
3552
+ ],
3553
+ [
3554
+ "ĠS",
3555
+ "he"
3556
+ ],
3557
+ [
3558
+ "Ġe",
3559
+ "nd"
3560
+ ],
3561
+ [
3562
+ "ar",
3563
+ "s"
3564
+ ],
3565
+ [
3566
+ "Ġbe",
3567
+ "t"
3568
+ ],
3569
+ [
3570
+ "v",
3571
+ "est"
3572
+ ],
3573
+ [
3574
+ "Ġb",
3575
+ "u"
3576
+ ],
3577
+ [
3578
+ "Ġsec",
3579
+ "ond"
3580
+ ],
3581
+ [
3582
+ "Ġth",
3583
+ "an"
3584
+ ],
3585
+ [
3586
+ "st",
3587
+ "e"
3588
+ ],
3589
+ [
3590
+ "ĠI",
3591
+ "s"
3592
+ ],
3593
+ [
3594
+ "ĠI",
3595
+ "nd"
3596
+ ],
3597
+ [
3598
+ "Ġbe",
3599
+ "ing"
3600
+ ],
3601
+ [
3602
+ "Ġde",
3603
+ "c"
3604
+ ],
3605
+ [
3606
+ "o",
3607
+ "od"
3608
+ ],
3609
+ [
3610
+ "Ġc",
3611
+ "an"
3612
+ ],
3613
+ [
3614
+ "en",
3615
+ "er"
3616
+ ],
3617
+ [
3618
+ "Ġth",
3619
+ "rough"
3620
+ ],
3621
+ [
3622
+ "Ġab",
3623
+ "out"
3624
+ ],
3625
+ [
3626
+ "Ġc",
3627
+ "ent"
3628
+ ],
3629
+ [
3630
+ "ct",
3631
+ "ed"
3632
+ ],
3633
+ [
3634
+ "Ġa",
3635
+ "pp"
3636
+ ],
3637
+ [
3638
+ "Ġwhe",
3639
+ "n"
3640
+ ],
3641
+ [
3642
+ "Ġl",
3643
+ "ater"
3644
+ ],
3645
+ [
3646
+ "ow",
3647
+ "er"
3648
+ ],
3649
+ [
3650
+ "ul",
3651
+ "l"
3652
+ ],
3653
+ [
3654
+ "on",
3655
+ "y"
3656
+ ],
3657
+ [
3658
+ "o",
3659
+ "le"
3660
+ ],
3661
+ [
3662
+ "el",
3663
+ "er"
3664
+ ],
3665
+ [
3666
+ "Ġa",
3667
+ "cc"
3668
+ ],
3669
+ [
3670
+ "Ġp",
3671
+ "e"
3672
+ ],
3673
+ [
3674
+ "ak",
3675
+ "e"
3676
+ ],
3677
+ [
3678
+ "i",
3679
+ "ke"
3680
+ ],
3681
+ [
3682
+ "il",
3683
+ "y"
3684
+ ],
3685
+ [
3686
+ "r",
3687
+ "ist"
3688
+ ],
3689
+ [
3690
+ "Ġa",
3691
+ "c"
3692
+ ],
3693
+ [
3694
+ "Ġin",
3695
+ "d"
3696
+ ],
3697
+ [
3698
+ "ĠWhe",
3699
+ "eler"
3700
+ ],
3701
+ [
3702
+ "ĠL",
3703
+ "e"
3704
+ ],
3705
+ [
3706
+ "ou",
3707
+ "th"
3708
+ ],
3709
+ [
3710
+ "ĠC",
3711
+ "om"
3712
+ ],
3713
+ [
3714
+ "us",
3715
+ "ic"
3716
+ ],
3717
+ [
3718
+ "ul",
3719
+ "ar"
3720
+ ],
3721
+ [
3722
+ "i",
3723
+ "ous"
3724
+ ],
3725
+ [
3726
+ "w",
3727
+ "een"
3728
+ ],
3729
+ [
3730
+ "Ġs",
3731
+ "ome"
3732
+ ],
3733
+ [
3734
+ "ur",
3735
+ "ch"
3736
+ ],
3737
+ [
3738
+ "e",
3739
+ "nd"
3740
+ ],
3741
+ [
3742
+ "is",
3743
+ "m"
3744
+ ],
3745
+ [
3746
+ "ch",
3747
+ "ae"
3748
+ ],
3749
+ [
3750
+ "ĠN",
3751
+ "ew"
3752
+ ],
3753
+ [
3754
+ "chae",
3755
+ "olog"
3756
+ ],
3757
+ [
3758
+ "a",
3759
+ "id"
3760
+ ],
3761
+ [
3762
+ "Ġw",
3763
+ "rit"
3764
+ ],
3765
+ [
3766
+ "al",
3767
+ "s"
3768
+ ],
3769
+ [
3770
+ "Ġd",
3771
+ "o"
3772
+ ],
3773
+ [
3774
+ "Ġsu",
3775
+ "ch"
3776
+ ],
3777
+ [
3778
+ "oll",
3779
+ "ow"
3780
+ ],
3781
+ [
3782
+ "al",
3783
+ "ly"
3784
+ ],
3785
+ [
3786
+ "t",
3787
+ "en"
3788
+ ],
3789
+ [
3790
+ "Ġa",
3791
+ "m"
3792
+ ],
3793
+ [
3794
+ "in",
3795
+ "s"
3796
+ ],
3797
+ [
3798
+ "Ġp",
3799
+ "ol"
3800
+ ],
3801
+ [
3802
+ "Ġm",
3803
+ "ade"
3804
+ ],
3805
+ [
3806
+ "if",
3807
+ "ic"
3808
+ ],
3809
+ [
3810
+ "Ġm",
3811
+ "et"
3812
+ ],
3813
+ [
3814
+ "Ġg",
3815
+ "ame"
3816
+ ],
3817
+ [
3818
+ "i",
3819
+ "el"
3820
+ ],
3821
+ [
3822
+ "Ġh",
3823
+ "ist"
3824
+ ],
3825
+ [
3826
+ "ut",
3827
+ "e"
3828
+ ],
3829
+ [
3830
+ "ĠG",
3831
+ "al"
3832
+ ],
3833
+ [
3834
+ "Ġwhe",
3835
+ "re"
3836
+ ],
3837
+ [
3838
+ "f",
3839
+ "ore"
3840
+ ],
3841
+ [
3842
+ "at",
3843
+ "ing"
3844
+ ],
3845
+ [
3846
+ "Ġre",
3847
+ "p"
3848
+ ],
3849
+ [
3850
+ "res",
3851
+ "ent"
3852
+ ],
3853
+ [
3854
+ "j",
3855
+ "ect"
3856
+ ],
3857
+ [
3858
+ "Ġs",
3859
+ "y"
3860
+ ],
3861
+ [
3862
+ "or",
3863
+ "ld"
3864
+ ],
3865
+ [
3866
+ "Ġp",
3867
+ "r"
3868
+ ],
3869
+ [
3870
+ "Ġb",
3871
+ "l"
3872
+ ],
3873
+ [
3874
+ "am",
3875
+ "p"
3876
+ ],
3877
+ [
3878
+ "i",
3879
+ "et"
3880
+ ],
3881
+ [
3882
+ "o",
3883
+ "b"
3884
+ ],
3885
+ [
3886
+ "Ġa",
3887
+ "p"
3888
+ ],
3889
+ [
3890
+ "th",
3891
+ "ough"
3892
+ ],
3893
+ [
3894
+ "ov",
3895
+ "e"
3896
+ ],
3897
+ [
3898
+ "ĠBrit",
3899
+ "ish"
3900
+ ],
3901
+ [
3902
+ "Ġbet",
3903
+ "ween"
3904
+ ],
3905
+ [
3906
+ "vest",
3907
+ "on"
3908
+ ],
3909
+ [
3910
+ "ĠGal",
3911
+ "veston"
3912
+ ],
3913
+ [
3914
+ "er",
3915
+ "man"
3916
+ ],
3917
+ [
3918
+ "ro",
3919
+ "w"
3920
+ ],
3921
+ [
3922
+ "Ġan",
3923
+ "t"
3924
+ ],
3925
+ [
3926
+ "Ġsh",
3927
+ "ip"
3928
+ ],
3929
+ [
3930
+ "ĠCh",
3931
+ "rist"
3932
+ ],
3933
+ [
3934
+ "a",
3935
+ "z"
3936
+ ],
3937
+ [
3938
+ "o",
3939
+ "ol"
3940
+ ],
3941
+ [
3942
+ "Ġthe",
3943
+ "re"
3944
+ ],
3945
+ [
3946
+ "Ġs",
3947
+ "ign"
3948
+ ],
3949
+ [
3950
+ "ĠB",
3951
+ "l"
3952
+ ],
3953
+ [
3954
+ "Ġs",
3955
+ "ur"
3956
+ ],
3957
+ [
3958
+ "is",
3959
+ "ed"
3960
+ ],
3961
+ [
3962
+ "i",
3963
+ "red"
3964
+ ],
3965
+ [
3966
+ "ĠY",
3967
+ "ork"
3968
+ ],
3969
+ [
3970
+ "9",
3971
+ "4"
3972
+ ],
3973
+ [
3974
+ "l",
3975
+ "ed"
3976
+ ],
3977
+ [
3978
+ "Ġc",
3979
+ "ity"
3980
+ ],
3981
+ [
3982
+ "ĠAl",
3983
+ "l"
3984
+ ],
3985
+ [
3986
+ "9",
3987
+ "8"
3988
+ ],
3989
+ [
3990
+ "u",
3991
+ "p"
3992
+ ],
3993
+ [
3994
+ "Ġch",
3995
+ "ar"
3996
+ ],
3997
+ [
3998
+ "Ġs",
3999
+ "ong"
4000
+ ],
4001
+ [
4002
+ "Ġc",
4003
+ "all"
4004
+ ],
4005
+ [
4006
+ "ĠG",
4007
+ "erman"
4008
+ ],
4009
+ [
4010
+ "Ġman",
4011
+ "y"
4012
+ ],
4013
+ [
4014
+ "Ġnum",
4015
+ "ber"
4016
+ ],
4017
+ [
4018
+ "Ġh",
4019
+ "igh"
4020
+ ],
4021
+ [
4022
+ "u",
4023
+ "g"
4024
+ ],
4025
+ [
4026
+ "ic",
4027
+ "s"
4028
+ ],
4029
+ [
4030
+ "ic",
4031
+ "an"
4032
+ ],
4033
+ [
4034
+ "Ġm",
4035
+ "in"
4036
+ ],
4037
+ [
4038
+ "Ġl",
4039
+ "oc"
4040
+ ],
4041
+ [
4042
+ "Ġn",
4043
+ "o"
4044
+ ],
4045
+ [
4046
+ "Ġwh",
4047
+ "ile"
4048
+ ],
4049
+ [
4050
+ "a",
4051
+ "ir"
4052
+ ],
4053
+ [
4054
+ "Ġ",
4055
+ "qu"
4056
+ ],
4057
+ [
4058
+ "Ġb",
4059
+ "oth"
4060
+ ],
4061
+ [
4062
+ "Ġe",
4063
+ "le"
4064
+ ],
4065
+ [
4066
+ "ran",
4067
+ "s"
4068
+ ],
4069
+ [
4070
+ "Ġsu",
4071
+ "pp"
4072
+ ],
4073
+ [
4074
+ "e",
4075
+ "ver"
4076
+ ],
4077
+ [
4078
+ "ĠT",
4079
+ "own"
4080
+ ],
4081
+ [
4082
+ "iv",
4083
+ "ers"
4084
+ ],
4085
+ [
4086
+ "if",
4087
+ "e"
4088
+ ],
4089
+ [
4090
+ "Ġle",
4091
+ "ad"
4092
+ ],
4093
+ [
4094
+ "Ġus",
4095
+ "ed"
4096
+ ],
4097
+ [
4098
+ "he",
4099
+ "s"
4100
+ ],
4101
+ [
4102
+ "iv",
4103
+ "ed"
4104
+ ],
4105
+ [
4106
+ "ver",
4107
+ "al"
4108
+ ],
4109
+ [
4110
+ "Ġthe",
4111
+ "n"
4112
+ ],
4113
+ [
4114
+ "Ġs",
4115
+ "o"
4116
+ ],
4117
+ [
4118
+ "Ġyear",
4119
+ "s"
4120
+ ],
4121
+ [
4122
+ "Ġgod",
4123
+ "s"
4124
+ ],
4125
+ [
4126
+ "g",
4127
+ "y"
4128
+ ],
4129
+ [
4130
+ "re",
4131
+ "n"
4132
+ ],
4133
+ [
4134
+ "Ġl",
4135
+ "ong"
4136
+ ],
4137
+ [
4138
+ "Ġdes",
4139
+ "c"
4140
+ ],
4141
+ [
4142
+ "9",
4143
+ "1"
4144
+ ],
4145
+ [
4146
+ "Ġb",
4147
+ "el"
4148
+ ],
4149
+ [
4150
+ "o",
4151
+ "h"
4152
+ ],
4153
+ [
4154
+ "vi",
4155
+ "ew"
4156
+ ],
4157
+ [
4158
+ "a",
4159
+ "use"
4160
+ ],
4161
+ [
4162
+ "al",
4163
+ "e"
4164
+ ],
4165
+ [
4166
+ "ro",
4167
+ "s"
4168
+ ],
4169
+ [
4170
+ "ot",
4171
+ "her"
4172
+ ],
4173
+ [
4174
+ "el",
4175
+ "f"
4176
+ ],
4177
+ [
4178
+ "n",
4179
+ "ing"
4180
+ ],
4181
+ [
4182
+ "r",
4183
+ "al"
4184
+ ],
4185
+ [
4186
+ "Ġf",
4187
+ "ollow"
4188
+ ],
4189
+ [
4190
+ "ĠUn",
4191
+ "ited"
4192
+ ],
4193
+ [
4194
+ "Ġd",
4195
+ "if"
4196
+ ],
4197
+ [
4198
+ "ĠA",
4199
+ "mer"
4200
+ ],
4201
+ [
4202
+ "ver",
4203
+ "y"
4204
+ ],
4205
+ [
4206
+ "u",
4207
+ "res"
4208
+ ],
4209
+ [
4210
+ "Ġs",
4211
+ "ch"
4212
+ ],
4213
+ [
4214
+ "Ġd",
4215
+ "ay"
4216
+ ],
4217
+ [
4218
+ "Ġ",
4219
+ "ent"
4220
+ ],
4221
+ [
4222
+ "Ġw",
4223
+ "ell"
4224
+ ],
4225
+ [
4226
+ "Ġm",
4227
+ "ain"
4228
+ ],
4229
+ [
4230
+ "ĠTh",
4231
+ "is"
4232
+ ],
4233
+ [
4234
+ "Ġt",
4235
+ "r"
4236
+ ],
4237
+ [
4238
+ "Ġde",
4239
+ "f"
4240
+ ],
4241
+ [
4242
+ "2",
4243
+ "0"
4244
+ ],
4245
+ [
4246
+ "Ġo",
4247
+ "b"
4248
+ ],
4249
+ [
4250
+ "Ġc",
4251
+ "re"
4252
+ ],
4253
+ [
4254
+ "ter",
4255
+ "n"
4256
+ ],
4257
+ [
4258
+ "t",
4259
+ "y"
4260
+ ],
4261
+ [
4262
+ "ĠC",
4263
+ "l"
4264
+ ],
4265
+ [
4266
+ "Ġe",
4267
+ "m"
4268
+ ],
4269
+ [
4270
+ "Ġbe",
4271
+ "fore"
4272
+ ],
4273
+ [
4274
+ "ist",
4275
+ "s"
4276
+ ],
4277
+ [
4278
+ "ĠM",
4279
+ "ar"
4280
+ ],
4281
+ [
4282
+ "ra",
4283
+ "ft"
4284
+ ],
4285
+ [
4286
+ "Ġbec",
4287
+ "ame"
4288
+ ],
4289
+ [
4290
+ "Ġthe",
4291
+ "se"
4292
+ ],
4293
+ [
4294
+ "em",
4295
+ "b"
4296
+ ],
4297
+ [
4298
+ "Ġper",
4299
+ "form"
4300
+ ],
4301
+ [
4302
+ "Ġagain",
4303
+ "st"
4304
+ ],
4305
+ [
4306
+ "a",
4307
+ "h"
4308
+ ],
4309
+ [
4310
+ "op",
4311
+ "le"
4312
+ ],
4313
+ [
4314
+ "iz",
4315
+ "ed"
4316
+ ],
4317
+ [
4318
+ "iel",
4319
+ "d"
4320
+ ],
4321
+ [
4322
+ "Ġap",
4323
+ "pe"
4324
+ ],
4325
+ [
4326
+ "st",
4327
+ "ru"
4328
+ ],
4329
+ [
4330
+ "Ġde",
4331
+ "p"
4332
+ ],
4333
+ [
4334
+ "3",
4335
+ "0"
4336
+ ],
4337
+ [
4338
+ "Ġo",
4339
+ "per"
4340
+ ],
4341
+ [
4342
+ "Ġp",
4343
+ "op"
4344
+ ],
4345
+ [
4346
+ "Ġkn",
4347
+ "own"
4348
+ ],
4349
+ [
4350
+ "ste",
4351
+ "in"
4352
+ ],
4353
+ [
4354
+ "i",
4355
+ "o"
4356
+ ],
4357
+ [
4358
+ "y",
4359
+ "s"
4360
+ ],
4361
+ [
4362
+ "Ġ",
4363
+ "Z"
4364
+ ],
4365
+ [
4366
+ "Ġc",
4367
+ "ar"
4368
+ ],
4369
+ [
4370
+ "Ġc",
4371
+ "ol"
4372
+ ],
4373
+ [
4374
+ "id",
4375
+ "ent"
4376
+ ],
4377
+ [
4378
+ "ow",
4379
+ "ever"
4380
+ ],
4381
+ [
4382
+ "ce",
4383
+ "pt"
4384
+ ],
4385
+ [
4386
+ "Ġrem",
4387
+ "ain"
4388
+ ],
4389
+ [
4390
+ "s",
4391
+ "on"
4392
+ ],
4393
+ [
4394
+ "Ġst",
4395
+ "ud"
4396
+ ],
4397
+ [
4398
+ "Ġinclud",
4399
+ "ing"
4400
+ ],
4401
+ [
4402
+ "Ġ",
4403
+ "%"
4404
+ ],
4405
+ [
4406
+ "ĠA",
4407
+ "nd"
4408
+ ],
4409
+ [
4410
+ "Ġor",
4411
+ "ig"
4412
+ ]
4413
+ ]
4414
+ }
4415
+ }
afmoe/AfmoeForCausalLM/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|begin_of_text|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 128,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
afmoe/AfmoeModel/chat_template.jinja ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {%- if '</think>' in content %}
27
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
28
+ {%- endif %}
29
+ {{- '<|im_start|>' + message.role + '\n' }}
30
+ {% generation %}
31
+ {{- content }}
32
+ {%- if message.tool_calls %}
33
+ {%- for tool_call in message.tool_calls %}
34
+ {%- if (loop.first and content) or (not loop.first) %}
35
+ {{- '\n' }}
36
+ {%- endif %}
37
+ {%- if tool_call.function %}
38
+ {%- set tool_call = tool_call.function %}
39
+ {%- endif %}
40
+ {{- '<tool_call>\n{"name": "' }}
41
+ {{- tool_call.name }}
42
+ {{- '", "arguments": ' }}
43
+ {%- if tool_call.arguments is string %}
44
+ {{- tool_call.arguments }}
45
+ {%- else %}
46
+ {{- tool_call.arguments | tojson }}
47
+ {%- endif %}
48
+ {{- '}\n</tool_call>' }}
49
+ {%- endfor %}
50
+ {%- endif %}
51
+ {{- '<|im_end|>' }}
52
+ {% endgeneration %}
53
+ {{- '\n' }}
54
+ {%- elif message.role == "tool" %}
55
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
56
+ {{- '<|im_start|>user' }}
57
+ {%- endif %}
58
+ {{- '\n<tool_response>\n' }}
59
+ {{- content }}
60
+ {{- '\n</tool_response>' }}
61
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
62
+ {{- '<|im_end|>\n' }}
63
+ {%- endif %}
64
+ {%- endif %}
65
+ {%- endfor %}
66
+ {%- if add_generation_prompt %}
67
+ {{- '<|im_start|>assistant\n<think>\n' }}
68
+ {%- endif %}
afmoe/AfmoeModel/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AfmoeModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "global_attn_every_n_layers": 2,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 16,
16
+ "layer_types": [
17
+ "sliding_attention",
18
+ "full_attention"
19
+ ],
20
+ "max_position_embeddings": 128,
21
+ "model_type": "afmoe",
22
+ "moe_intermediate_size": 16,
23
+ "mup_enabled": false,
24
+ "num_attention_heads": 16,
25
+ "num_dense_layers": 1,
26
+ "num_experts": 4,
27
+ "num_experts_per_tok": 2,
28
+ "num_hidden_layers": 2,
29
+ "num_key_value_heads": 16,
30
+ "num_shared_experts": 2,
31
+ "output_router_logits": false,
32
+ "pad_token_id": 0,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_parameters": {
35
+ "rope_theta": 10000.0,
36
+ "rope_type": "default"
37
+ },
38
+ "route_scale": 1.0,
39
+ "sliding_window": 128,
40
+ "tie_word_embeddings": false,
41
+ "transformers_version": "5.15.0.dev0",
42
+ "use_cache": false,
43
+ "vocab_size": 1026
44
+ }
afmoe/AfmoeModel/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3387ff456ac38f6dc9a3df4dc0a5427f69494d0e34559c0b595113fe58bf8575
3
+ size 2803976
afmoe/AfmoeModel/tokenizer.json ADDED
@@ -0,0 +1,4415 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|begin_of_text|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|end_of_text|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<|im_end|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<|eot_id|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "<|start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 6,
62
+ "content": "<|channel|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 7,
71
+ "content": "<|message|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 8,
80
+ "content": "<|end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 9,
89
+ "content": "<|fitm_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 10,
98
+ "content": "<|fitm_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 11,
107
+ "content": "<|fitm_hole|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 12,
116
+ "content": "<|pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 13,
125
+ "content": "<|reserved_special_2|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 14,
134
+ "content": "<|reserved_special_3|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 15,
143
+ "content": "<|reserved_special_4|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 16,
152
+ "content": "<|reserved_special_5|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 17,
161
+ "content": "<|reserved_special_6|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 18,
170
+ "content": "<|reserved_special_7|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 19,
179
+ "content": "<|reserved_special_8|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 20,
188
+ "content": "<|reserved_special_9|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 21,
197
+ "content": "<|reserved_special_10|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 22,
206
+ "content": "<|reserved_special_11|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 23,
215
+ "content": "<|reserved_special_12|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 24,
224
+ "content": "<|reserved_special_13|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 25,
233
+ "content": "<|reserved_special_14|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 26,
242
+ "content": "<|reserved_special_15|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 27,
251
+ "content": "<|reserved_special_16|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 28,
260
+ "content": "<|reserved_special_17|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 29,
269
+ "content": "<|reserved_special_18|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 1024,
278
+ "content": "<think>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": false
284
+ },
285
+ {
286
+ "id": 1025,
287
+ "content": "</think>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": false
293
+ }
294
+ ],
295
+ "normalizer": {
296
+ "type": "Sequence",
297
+ "normalizers": []
298
+ },
299
+ "pre_tokenizer": {
300
+ "type": "Sequence",
301
+ "pretokenizers": [
302
+ {
303
+ "type": "Digits",
304
+ "individual_digits": false
305
+ },
306
+ {
307
+ "type": "Split",
308
+ "pattern": {
309
+ "Regex": "\\p{Nd}{1,510}(?=(?>\\p{Nd}{510})*(?:\\P{Nd}|$))|\\G\\p{Nd}{510}"
310
+ },
311
+ "behavior": "Isolated",
312
+ "invert": false
313
+ },
314
+ {
315
+ "type": "Split",
316
+ "pattern": {
317
+ "Regex": "\\A\\p{Nd}{1,2}(?=\\p{Nd}{3}+\\z)"
318
+ },
319
+ "behavior": "Isolated",
320
+ "invert": false
321
+ },
322
+ {
323
+ "type": "Split",
324
+ "pattern": {
325
+ "Regex": "\\A\\p{Nd}{3}|\\G\\p{Nd}{3}"
326
+ },
327
+ "behavior": "Isolated",
328
+ "invert": false
329
+ },
330
+ {
331
+ "type": "Split",
332
+ "pattern": {
333
+ "Regex": "(?:[\\u4E00-\\u9FFF\\u3040-\\u309F\\u30A0-\\u30FF\\u3400-\\u4DBF\\uf900-\\uFAFF\\uFF65-\\uFF9F\\u2F00-\\u2FDF]+|[\\u0E00-\\u0E7F]+|[\\u0E80-\\u0EFF]+|[\\u1780-\\u17FF]+|[\\u1000-\\u109F\\uAA60-\\uAA7F\\uA9E0-\\uA9FF]+|[\\uAC00-\\uD7AF\\u1100-\\u11FF]+)"
334
+ },
335
+ "behavior": "Isolated",
336
+ "invert": false
337
+ },
338
+ {
339
+ "type": "Split",
340
+ "pattern": {
341
+ "Regex": "[!\"#$%&'()*+,\\-./:;<=>?@\\[\\\\\\]^_`{|}~][A-Za-z]+|[^\r\n\\p{L}\\p{P}\\p{S}]?[\\p{L}\\p{M}]+| ?[\\p{P}\\p{S}]+[\r\n]*|\\s*[\r\n]+|\\s+(?!\\S)|\\s+"
342
+ },
343
+ "behavior": "Isolated",
344
+ "invert": false
345
+ },
346
+ {
347
+ "type": "ByteLevel",
348
+ "add_prefix_space": false,
349
+ "trim_offsets": true,
350
+ "use_regex": false
351
+ }
352
+ ]
353
+ },
354
+ "post_processor": {
355
+ "type": "Sequence",
356
+ "processors": [
357
+ {
358
+ "type": "ByteLevel",
359
+ "add_prefix_space": true,
360
+ "trim_offsets": false,
361
+ "use_regex": true
362
+ },
363
+ {
364
+ "type": "TemplateProcessing",
365
+ "single": [
366
+ {
367
+ "SpecialToken": {
368
+ "id": "<|begin_of_text|>",
369
+ "type_id": 0
370
+ }
371
+ },
372
+ {
373
+ "Sequence": {
374
+ "id": "A",
375
+ "type_id": 0
376
+ }
377
+ }
378
+ ],
379
+ "pair": [
380
+ {
381
+ "SpecialToken": {
382
+ "id": "<|begin_of_text|>",
383
+ "type_id": 0
384
+ }
385
+ },
386
+ {
387
+ "Sequence": {
388
+ "id": "A",
389
+ "type_id": 0
390
+ }
391
+ },
392
+ {
393
+ "SpecialToken": {
394
+ "id": "<|begin_of_text|>",
395
+ "type_id": 0
396
+ }
397
+ },
398
+ {
399
+ "Sequence": {
400
+ "id": "B",
401
+ "type_id": 0
402
+ }
403
+ }
404
+ ],
405
+ "special_tokens": {
406
+ "<|begin_of_text|>": {
407
+ "id": "<|begin_of_text|>",
408
+ "ids": [
409
+ 0
410
+ ],
411
+ "tokens": [
412
+ "<|begin_of_text|>"
413
+ ]
414
+ }
415
+ }
416
+ }
417
+ ]
418
+ },
419
+ "decoder": {
420
+ "type": "ByteLevel",
421
+ "add_prefix_space": true,
422
+ "trim_offsets": true,
423
+ "use_regex": true
424
+ },
425
+ "model": {
426
+ "type": "BPE",
427
+ "dropout": null,
428
+ "unk_token": null,
429
+ "continuing_subword_prefix": null,
430
+ "end_of_word_suffix": null,
431
+ "fuse_unk": false,
432
+ "byte_fallback": false,
433
+ "ignore_merges": false,
434
+ "vocab": {
435
+ "<|begin_of_text|>": 0,
436
+ "<|end_of_text|>": 1,
437
+ "<|im_start|>": 2,
438
+ "<|im_end|>": 3,
439
+ "<|eot_id|>": 4,
440
+ "<|start|>": 5,
441
+ "<|channel|>": 6,
442
+ "<|message|>": 7,
443
+ "<|end|>": 8,
444
+ "<|fitm_start|>": 9,
445
+ "<|fitm_end|>": 10,
446
+ "<|fitm_hole|>": 11,
447
+ "<|pad|>": 12,
448
+ "<|reserved_special_2|>": 13,
449
+ "<|reserved_special_3|>": 14,
450
+ "<|reserved_special_4|>": 15,
451
+ "<|reserved_special_5|>": 16,
452
+ "<|reserved_special_6|>": 17,
453
+ "<|reserved_special_7|>": 18,
454
+ "<|reserved_special_8|>": 19,
455
+ "<|reserved_special_9|>": 20,
456
+ "<|reserved_special_10|>": 21,
457
+ "<|reserved_special_11|>": 22,
458
+ "<|reserved_special_12|>": 23,
459
+ "<|reserved_special_13|>": 24,
460
+ "<|reserved_special_14|>": 25,
461
+ "<|reserved_special_15|>": 26,
462
+ "<|reserved_special_16|>": 27,
463
+ "<|reserved_special_17|>": 28,
464
+ "<|reserved_special_18|>": 29,
465
+ "!": 30,
466
+ "\"": 31,
467
+ "#": 32,
468
+ "$": 33,
469
+ "%": 34,
470
+ "&": 35,
471
+ "'": 36,
472
+ "(": 37,
473
+ ")": 38,
474
+ "*": 39,
475
+ "+": 40,
476
+ ",": 41,
477
+ "-": 42,
478
+ ".": 43,
479
+ "/": 44,
480
+ "0": 45,
481
+ "1": 46,
482
+ "2": 47,
483
+ "3": 48,
484
+ "4": 49,
485
+ "5": 50,
486
+ "6": 51,
487
+ "7": 52,
488
+ "8": 53,
489
+ "9": 54,
490
+ ":": 55,
491
+ ";": 56,
492
+ "<": 57,
493
+ "=": 58,
494
+ ">": 59,
495
+ "?": 60,
496
+ "@": 61,
497
+ "A": 62,
498
+ "B": 63,
499
+ "C": 64,
500
+ "D": 65,
501
+ "E": 66,
502
+ "F": 67,
503
+ "G": 68,
504
+ "H": 69,
505
+ "I": 70,
506
+ "J": 71,
507
+ "K": 72,
508
+ "L": 73,
509
+ "M": 74,
510
+ "N": 75,
511
+ "O": 76,
512
+ "P": 77,
513
+ "Q": 78,
514
+ "R": 79,
515
+ "S": 80,
516
+ "T": 81,
517
+ "U": 82,
518
+ "V": 83,
519
+ "W": 84,
520
+ "X": 85,
521
+ "Y": 86,
522
+ "Z": 87,
523
+ "[": 88,
524
+ "\\": 89,
525
+ "]": 90,
526
+ "^": 91,
527
+ "_": 92,
528
+ "`": 93,
529
+ "a": 94,
530
+ "b": 95,
531
+ "c": 96,
532
+ "d": 97,
533
+ "e": 98,
534
+ "f": 99,
535
+ "g": 100,
536
+ "h": 101,
537
+ "i": 102,
538
+ "j": 103,
539
+ "k": 104,
540
+ "l": 105,
541
+ "m": 106,
542
+ "n": 107,
543
+ "o": 108,
544
+ "p": 109,
545
+ "q": 110,
546
+ "r": 111,
547
+ "s": 112,
548
+ "t": 113,
549
+ "u": 114,
550
+ "v": 115,
551
+ "w": 116,
552
+ "x": 117,
553
+ "y": 118,
554
+ "z": 119,
555
+ "{": 120,
556
+ "|": 121,
557
+ "}": 122,
558
+ "~": 123,
559
+ "¡": 124,
560
+ "¢": 125,
561
+ "£": 126,
562
+ "¤": 127,
563
+ "¥": 128,
564
+ "¦": 129,
565
+ "§": 130,
566
+ "¨": 131,
567
+ "©": 132,
568
+ "ª": 133,
569
+ "«": 134,
570
+ "¬": 135,
571
+ "®": 136,
572
+ "¯": 137,
573
+ "°": 138,
574
+ "±": 139,
575
+ "²": 140,
576
+ "³": 141,
577
+ "´": 142,
578
+ "µ": 143,
579
+ "¶": 144,
580
+ "·": 145,
581
+ "¸": 146,
582
+ "¹": 147,
583
+ "º": 148,
584
+ "»": 149,
585
+ "¼": 150,
586
+ "½": 151,
587
+ "¾": 152,
588
+ "¿": 153,
589
+ "À": 154,
590
+ "Á": 155,
591
+ "Â": 156,
592
+ "Ã": 157,
593
+ "Ä": 158,
594
+ "Å": 159,
595
+ "Æ": 160,
596
+ "Ç": 161,
597
+ "È": 162,
598
+ "É": 163,
599
+ "Ê": 164,
600
+ "Ë": 165,
601
+ "Ì": 166,
602
+ "Í": 167,
603
+ "Î": 168,
604
+ "Ï": 169,
605
+ "Ð": 170,
606
+ "Ñ": 171,
607
+ "Ò": 172,
608
+ "Ó": 173,
609
+ "Ô": 174,
610
+ "Õ": 175,
611
+ "Ö": 176,
612
+ "×": 177,
613
+ "Ø": 178,
614
+ "Ù": 179,
615
+ "Ú": 180,
616
+ "Û": 181,
617
+ "Ü": 182,
618
+ "Ý": 183,
619
+ "Þ": 184,
620
+ "ß": 185,
621
+ "à": 186,
622
+ "á": 187,
623
+ "â": 188,
624
+ "ã": 189,
625
+ "ä": 190,
626
+ "å": 191,
627
+ "æ": 192,
628
+ "ç": 193,
629
+ "è": 194,
630
+ "é": 195,
631
+ "ê": 196,
632
+ "ë": 197,
633
+ "ì": 198,
634
+ "í": 199,
635
+ "î": 200,
636
+ "ï": 201,
637
+ "ð": 202,
638
+ "ñ": 203,
639
+ "ò": 204,
640
+ "ó": 205,
641
+ "ô": 206,
642
+ "õ": 207,
643
+ "ö": 208,
644
+ "÷": 209,
645
+ "ø": 210,
646
+ "ù": 211,
647
+ "ú": 212,
648
+ "û": 213,
649
+ "ü": 214,
650
+ "ý": 215,
651
+ "þ": 216,
652
+ "ÿ": 217,
653
+ "Ā": 218,
654
+ "ā": 219,
655
+ "Ă": 220,
656
+ "ă": 221,
657
+ "Ą": 222,
658
+ "ą": 223,
659
+ "Ć": 224,
660
+ "ć": 225,
661
+ "Ĉ": 226,
662
+ "ĉ": 227,
663
+ "Ċ": 228,
664
+ "ċ": 229,
665
+ "Č": 230,
666
+ "č": 231,
667
+ "Ď": 232,
668
+ "ď": 233,
669
+ "Đ": 234,
670
+ "đ": 235,
671
+ "Ē": 236,
672
+ "ē": 237,
673
+ "Ĕ": 238,
674
+ "ĕ": 239,
675
+ "Ė": 240,
676
+ "ė": 241,
677
+ "Ę": 242,
678
+ "ę": 243,
679
+ "Ě": 244,
680
+ "ě": 245,
681
+ "Ĝ": 246,
682
+ "ĝ": 247,
683
+ "Ğ": 248,
684
+ "ğ": 249,
685
+ "Ġ": 250,
686
+ "ġ": 251,
687
+ "Ģ": 252,
688
+ "ģ": 253,
689
+ "Ĥ": 254,
690
+ "ĥ": 255,
691
+ "Ħ": 256,
692
+ "ħ": 257,
693
+ "Ĩ": 258,
694
+ "ĩ": 259,
695
+ "Ī": 260,
696
+ "ī": 261,
697
+ "Ĭ": 262,
698
+ "ĭ": 263,
699
+ "Į": 264,
700
+ "į": 265,
701
+ "İ": 266,
702
+ "ı": 267,
703
+ "IJ": 268,
704
+ "ij": 269,
705
+ "Ĵ": 270,
706
+ "ĵ": 271,
707
+ "Ķ": 272,
708
+ "ķ": 273,
709
+ "ĸ": 274,
710
+ "Ĺ": 275,
711
+ "ĺ": 276,
712
+ "Ļ": 277,
713
+ "ļ": 278,
714
+ "Ľ": 279,
715
+ "ľ": 280,
716
+ "Ŀ": 281,
717
+ "ŀ": 282,
718
+ "Ł": 283,
719
+ "ł": 284,
720
+ "Ń": 285,
721
+ "Ġt": 286,
722
+ "he": 287,
723
+ "Ġa": 288,
724
+ "in": 289,
725
+ "Ġthe": 290,
726
+ "er": 291,
727
+ "on": 292,
728
+ "Ġ,": 293,
729
+ "re": 294,
730
+ "Ġs": 295,
731
+ "ed": 296,
732
+ "Ġo": 297,
733
+ "nd": 298,
734
+ "Ġw": 299,
735
+ "at": 300,
736
+ "Ġ.": 301,
737
+ "or": 302,
738
+ "it": 303,
739
+ "is": 304,
740
+ "Ġc": 305,
741
+ "es": 306,
742
+ "Ġf": 307,
743
+ "en": 308,
744
+ "Ġof": 309,
745
+ "ar": 310,
746
+ "al": 311,
747
+ "Ġin": 312,
748
+ "Ġb": 313,
749
+ "an": 314,
750
+ "Ġp": 315,
751
+ "ing": 316,
752
+ "as": 317,
753
+ "Ġand": 318,
754
+ "ic": 319,
755
+ "Ġto": 320,
756
+ "Ġm": 321,
757
+ "ro": 322,
758
+ "Ġd": 323,
759
+ "Ġh": 324,
760
+ "ion": 325,
761
+ "le": 326,
762
+ "ĠT": 327,
763
+ "ou": 328,
764
+ "Ġre": 329,
765
+ "Ġ=": 330,
766
+ "ĠA": 331,
767
+ "Ġ\"": 332,
768
+ "ĠS": 333,
769
+ "Ġth": 334,
770
+ "ent": 335,
771
+ "il": 336,
772
+ "st": 337,
773
+ "Ġ@": 338,
774
+ "el": 339,
775
+ "ĠC": 340,
776
+ "ĠĊ": 341,
777
+ "ol": 342,
778
+ "Ġl": 343,
779
+ "Ġn": 344,
780
+ "om": 345,
781
+ "Ġe": 346,
782
+ "ct": 347,
783
+ "am": 348,
784
+ "ad": 349,
785
+ "Ġg": 350,
786
+ "Ġwas": 351,
787
+ "ur": 352,
788
+ "Ġon": 353,
789
+ "ĠThe": 354,
790
+ "ĠI": 355,
791
+ "im": 356,
792
+ "-@": 357,
793
+ "Ġ@-@": 358,
794
+ "Ġbe": 359,
795
+ "ly": 360,
796
+ "ĠM": 361,
797
+ "id": 362,
798
+ "Ġfor": 363,
799
+ "ir": 364,
800
+ "ch": 365,
801
+ "ĠB": 366,
802
+ "iv": 367,
803
+ "ot": 368,
804
+ "Ġ'": 369,
805
+ "ith": 370,
806
+ "ation": 371,
807
+ "ra": 372,
808
+ "ig": 373,
809
+ "Ġas": 374,
810
+ "et": 375,
811
+ "ow": 376,
812
+ "us": 377,
813
+ "ut": 378,
814
+ "Ġst": 379,
815
+ "ce": 380,
816
+ "Ġwith": 381,
817
+ "ĠP": 382,
818
+ "ers": 383,
819
+ "Ġhe": 384,
820
+ "Ġthat": 385,
821
+ "ay": 386,
822
+ "Ġis": 387,
823
+ "ĠH": 388,
824
+ "ul": 389,
825
+ "ĠG": 390,
826
+ "ĠF": 391,
827
+ "Ġal": 392,
828
+ "ĠR": 393,
829
+ "ĠN": 394,
830
+ "ist": 395,
831
+ "um": 396,
832
+ "em": 397,
833
+ "Ġwh": 398,
834
+ "ĠW": 399,
835
+ "est": 400,
836
+ "Ġby": 401,
837
+ "un": 402,
838
+ "Ġan": 403,
839
+ "ver": 404,
840
+ "os": 405,
841
+ "th": 406,
842
+ "Ġ)": 407,
843
+ "Ġ(": 408,
844
+ "ter": 409,
845
+ "Ġcon": 410,
846
+ "ĠJ": 411,
847
+ "rom": 412,
848
+ "ĠD": 413,
849
+ "Ġat": 414,
850
+ "Ġse": 415,
851
+ "and": 416,
852
+ "od": 417,
853
+ "ĠL": 418,
854
+ "av": 419,
855
+ "Ġit": 420,
856
+ "00": 421,
857
+ "Ġde": 422,
858
+ "ag": 423,
859
+ "her": 424,
860
+ "ies": 425,
861
+ "pe": 426,
862
+ "ĠE": 427,
863
+ "ain": 428,
864
+ "ck": 429,
865
+ "Ġhis": 430,
866
+ "ri": 431,
867
+ "Ġfrom": 432,
868
+ "ere": 433,
869
+ "res": 434,
870
+ "ort": 435,
871
+ "Ġpro": 436,
872
+ "if": 437,
873
+ "Ġcom": 438,
874
+ "ew": 439,
875
+ "ity": 440,
876
+ "Ġwere": 441,
877
+ "Ġv": 442,
878
+ "ate": 443,
879
+ "ĠIn": 444,
880
+ "Ġsu": 445,
881
+ "ĠO": 446,
882
+ "op": 447,
883
+ "Ġor": 448,
884
+ "ich": 449,
885
+ "ore": 450,
886
+ "all": 451,
887
+ "igh": 452,
888
+ "ated": 453,
889
+ "ord": 454,
890
+ "se": 455,
891
+ "ill": 456,
892
+ "art": 457,
893
+ "Ġex": 458,
894
+ "ab": 459,
895
+ "pt": 460,
896
+ "Ġch": 461,
897
+ "Ġsh": 462,
898
+ "ld": 463,
899
+ "Ġpl": 464,
900
+ "pp": 465,
901
+ "ak": 466,
902
+ "Ġare": 467,
903
+ "ber": 468,
904
+ "gh": 469,
905
+ "ess": 470,
906
+ "ud": 471,
907
+ "Ġâ": 472,
908
+ "ant": 473,
909
+ "ard": 474,
910
+ "rou": 475,
911
+ "ong": 476,
912
+ "ĠU": 477,
913
+ "ru": 478,
914
+ "ia": 479,
915
+ "qu": 480,
916
+ "Ġwhich": 481,
917
+ "ĠâĢ": 482,
918
+ "ame": 483,
919
+ "ment": 484,
920
+ "ĠCh": 485,
921
+ "Ġle": 486,
922
+ "rit": 487,
923
+ "Ġhad": 488,
924
+ "ial": 489,
925
+ "ian": 490,
926
+ "og": 491,
927
+ "red": 492,
928
+ "ĠK": 493,
929
+ "ĠSt": 494,
930
+ "ive": 495,
931
+ "oc": 496,
932
+ "ip": 497,
933
+ "ov": 498,
934
+ "Ġ;": 499,
935
+ "Ġr": 500,
936
+ "ish": 501,
937
+ "ost": 502,
938
+ "our": 503,
939
+ "Ġar": 504,
940
+ "Ġu": 505,
941
+ "Ġnot": 506,
942
+ "ear": 507,
943
+ "ight": 508,
944
+ "ast": 509,
945
+ "ac": 510,
946
+ "Ġy": 511,
947
+ "Ġk": 512,
948
+ "ave": 513,
949
+ "ary": 514,
950
+ "ell": 515,
951
+ "ther": 516,
952
+ "ction": 517,
953
+ "ical": 518,
954
+ "nt": 519,
955
+ "own": 520,
956
+ "cc": 521,
957
+ "Ġinc": 522,
958
+ "ine": 523,
959
+ "ge": 524,
960
+ "ide": 525,
961
+ "ust": 526,
962
+ "ĠâĢĵ": 527,
963
+ "Ġher": 528,
964
+ "so": 529,
965
+ "ap": 530,
966
+ "ue": 531,
967
+ "ure": 532,
968
+ "ork": 533,
969
+ "ran": 534,
970
+ "out": 535,
971
+ "Ġalso": 536,
972
+ "Ġtheir": 537,
973
+ "Ġhas": 538,
974
+ "wo": 539,
975
+ "Ġun": 540,
976
+ "ous": 541,
977
+ "ff": 542,
978
+ "ign": 543,
979
+ "fter": 544,
980
+ "ĠV": 545,
981
+ "ub": 546,
982
+ "Ġrec": 547,
983
+ "ome": 548,
984
+ "01": 549,
985
+ "Ġcl": 550,
986
+ ".@": 551,
987
+ "Ġ@.@": 552,
988
+ "Ġcont": 553,
989
+ "irst": 554,
990
+ "ĠHe": 555,
991
+ "Ġte": 556,
992
+ "ition": 557,
993
+ "ater": 558,
994
+ "Ġper": 559,
995
+ "ass": 560,
996
+ "ack": 561,
997
+ "ations": 562,
998
+ "ie": 563,
999
+ "Ġits": 564,
1000
+ "Ġab": 565,
1001
+ "pl": 566,
1002
+ "Ġone": 567,
1003
+ "Ġint": 568,
1004
+ "Ġsc": 569,
1005
+ "Ġfirst": 570,
1006
+ "ond": 571,
1007
+ "ime": 572,
1008
+ "hed": 573,
1009
+ "Ġ:": 574,
1010
+ "orm": 575,
1011
+ "ult": 576,
1012
+ "ould": 577,
1013
+ "ory": 578,
1014
+ "Ġwho": 579,
1015
+ "Ġwhe": 580,
1016
+ "ĠTh": 581,
1017
+ "per": 582,
1018
+ "Ġbut": 583,
1019
+ "Ġhave": 584,
1020
+ "Ġtwo": 585,
1021
+ "nder": 586,
1022
+ "ĠAl": 587,
1023
+ "ect": 588,
1024
+ "Ġthis": 589,
1025
+ "ok": 590,
1026
+ "ark": 591,
1027
+ "uring": 592,
1028
+ "du": 593,
1029
+ "ire": 594,
1030
+ "ough": 595,
1031
+ "ual": 596,
1032
+ "Ġall": 597,
1033
+ "ĠY": 598,
1034
+ "iz": 599,
1035
+ "mer": 600,
1036
+ "Ġus": 601,
1037
+ "ach": 602,
1038
+ "oll": 603,
1039
+ "Ġbeen": 604,
1040
+ "Ġplay": 605,
1041
+ "Ġres": 606,
1042
+ "ree": 607,
1043
+ "Ġshe": 608,
1044
+ ",@": 609,
1045
+ "Ġ@,@": 610,
1046
+ "age": 611,
1047
+ "Ġoff": 612,
1048
+ "ey": 613,
1049
+ "Ġcomp": 614,
1050
+ "Ġag": 615,
1051
+ "ason": 616,
1052
+ "port": 617,
1053
+ "oin": 618,
1054
+ "Ġad": 619,
1055
+ "Ġyear": 620,
1056
+ "Ġim": 621,
1057
+ "ĠIt": 622,
1058
+ "ence": 623,
1059
+ "Ġpart": 624,
1060
+ "Ġdes": 625,
1061
+ "ke": 626,
1062
+ "ric": 627,
1063
+ "are": 628,
1064
+ "ry": 629,
1065
+ "lud": 630,
1066
+ "Ġbec": 631,
1067
+ "te": 632,
1068
+ "Ġj": 633,
1069
+ "Ġother": 634,
1070
+ "ely": 635,
1071
+ "Ġdis": 636,
1072
+ "ph": 637,
1073
+ "Ġman": 638,
1074
+ "ound": 639,
1075
+ "old": 640,
1076
+ "Ġspe": 641,
1077
+ "act": 642,
1078
+ "Ġro": 643,
1079
+ "Ġafter": 644,
1080
+ "ance": 645,
1081
+ "ath": 646,
1082
+ "Ġen": 647,
1083
+ "ited": 648,
1084
+ "ĠUn": 649,
1085
+ "Ġgo": 650,
1086
+ "ib": 651,
1087
+ "ile": 652,
1088
+ "Ġthey": 653,
1089
+ "ite": 654,
1090
+ "man": 655,
1091
+ "ities": 656,
1092
+ "Ġover": 657,
1093
+ "ced": 658,
1094
+ "ents": 659,
1095
+ "ors": 660,
1096
+ "round": 661,
1097
+ "ilm": 662,
1098
+ "Ġinclud": 663,
1099
+ "Ġpre": 664,
1100
+ "ĠRe": 665,
1101
+ "vi": 666,
1102
+ "olog": 667,
1103
+ "ted": 668,
1104
+ "ade": 669,
1105
+ "ied": 670,
1106
+ "ose": 671,
1107
+ "ase": 672,
1108
+ "Ġcomm": 673,
1109
+ "Ġtime": 674,
1110
+ "Ġser": 675,
1111
+ "inal": 676,
1112
+ "Ġseason": 677,
1113
+ "99": 678,
1114
+ "ased": 679,
1115
+ "Ġout": 680,
1116
+ "ice": 681,
1117
+ "ĠAr": 682,
1118
+ "ates": 683,
1119
+ "ress": 684,
1120
+ "Ġup": 685,
1121
+ "ĠSe": 686,
1122
+ "ft": 687,
1123
+ "Ġthem": 688,
1124
+ "ubl": 689,
1125
+ "les": 690,
1126
+ "ild": 691,
1127
+ "Ġsp": 692,
1128
+ "Ġev": 693,
1129
+ "Ġmore": 694,
1130
+ "land": 695,
1131
+ "bum": 696,
1132
+ "fer": 697,
1133
+ "ces": 698,
1134
+ "Ġnew": 699,
1135
+ "gan": 700,
1136
+ "rough": 701,
1137
+ "able": 702,
1138
+ "ron": 703,
1139
+ "ts": 704,
1140
+ "ĠDe": 705,
1141
+ "ace": 706,
1142
+ "Ġne": 707,
1143
+ "Ġgod": 708,
1144
+ "ock": 709,
1145
+ "Ġalbum": 710,
1146
+ "rib": 711,
1147
+ "ward": 712,
1148
+ "Ġrem": 713,
1149
+ "Ġsec": 714,
1150
+ "Ġunder": 715,
1151
+ "wn": 716,
1152
+ "Ġwork": 717,
1153
+ "ered": 718,
1154
+ "ĠSh": 719,
1155
+ "ind": 720,
1156
+ "ens": 721,
1157
+ "Ġrel": 722,
1158
+ "Ġfilm": 723,
1159
+ "use": 724,
1160
+ "Ġhim": 725,
1161
+ "ings": 726,
1162
+ "ount": 727,
1163
+ "Ġrecord": 728,
1164
+ "Ġspec": 729,
1165
+ "ĠWhe": 730,
1166
+ "Ġinto": 731,
1167
+ "arn": 732,
1168
+ "reat": 733,
1169
+ "hip": 734,
1170
+ "one": 735,
1171
+ "orn": 736,
1172
+ "Ġinter": 737,
1173
+ "urn": 738,
1174
+ "ail": 739,
1175
+ "Ġfe": 740,
1176
+ "ember": 741,
1177
+ "Ġcons": 742,
1178
+ "form": 743,
1179
+ "ix": 744,
1180
+ "ved": 745,
1181
+ "Ġmost": 746,
1182
+ "Ġreg": 747,
1183
+ "ational": 748,
1184
+ "ern": 749,
1185
+ "arly": 750,
1186
+ "ĠPol": 751,
1187
+ "Ġact": 752,
1188
+ "oy": 753,
1189
+ "ink": 754,
1190
+ "ames": 755,
1191
+ "ordan": 756,
1192
+ "ĠJordan": 757,
1193
+ "ĠOn": 758,
1194
+ "Ġair": 759,
1195
+ "ĠAs": 760,
1196
+ "Ġduring": 761,
1197
+ "ĠBrit": 762,
1198
+ "ions": 763,
1199
+ "aw": 764,
1200
+ "Ġco": 765,
1201
+ "Ġfl": 766,
1202
+ "ee": 767,
1203
+ "oth": 768,
1204
+ "ae": 769,
1205
+ "vel": 770,
1206
+ "Ġtra": 771,
1207
+ "ons": 772,
1208
+ "ang": 773,
1209
+ "ick": 774,
1210
+ "Ġass": 775,
1211
+ "Ġatt": 776,
1212
+ "Ġra": 777,
1213
+ "oss": 778,
1214
+ "Ġsub": 779,
1215
+ "Ġkn": 780,
1216
+ "Ġonly": 781,
1217
+ "Ġagain": 782,
1218
+ "way": 783,
1219
+ "000": 784,
1220
+ "ans": 785,
1221
+ "Ġme": 786,
1222
+ "Ġnum": 787,
1223
+ "Ġform": 788,
1224
+ "iss": 789,
1225
+ "Ġpubl": 790,
1226
+ "ng": 791,
1227
+ "ished": 792,
1228
+ "arg": 793,
1229
+ "Ġret": 794,
1230
+ "Ġrele": 795,
1231
+ "Ġwould": 796,
1232
+ "een": 797,
1233
+ "ve": 798,
1234
+ "Ġfour": 799,
1235
+ "ict": 800,
1236
+ "Ġthree": 801,
1237
+ "erson": 802,
1238
+ "tle": 803,
1239
+ "Ġprodu": 804,
1240
+ "Ġmon": 805,
1241
+ "Ġteam": 806,
1242
+ "ook": 807,
1243
+ "orth": 808,
1244
+ "ĠShe": 809,
1245
+ "Ġend": 810,
1246
+ "ars": 811,
1247
+ "Ġbet": 812,
1248
+ "vest": 813,
1249
+ "Ġbu": 814,
1250
+ "Ġsecond": 815,
1251
+ "Ġthan": 816,
1252
+ "ste": 817,
1253
+ "ĠIs": 818,
1254
+ "ĠInd": 819,
1255
+ "Ġbeing": 820,
1256
+ "Ġdec": 821,
1257
+ "ood": 822,
1258
+ "Ġcan": 823,
1259
+ "ener": 824,
1260
+ "Ġthrough": 825,
1261
+ "Ġabout": 826,
1262
+ "Ġcent": 827,
1263
+ "cted": 828,
1264
+ "Ġapp": 829,
1265
+ "Ġwhen": 830,
1266
+ "Ġlater": 831,
1267
+ "ower": 832,
1268
+ "ull": 833,
1269
+ "ony": 834,
1270
+ "ole": 835,
1271
+ "eler": 836,
1272
+ "Ġacc": 837,
1273
+ "Ġpe": 838,
1274
+ "ake": 839,
1275
+ "ike": 840,
1276
+ "ily": 841,
1277
+ "rist": 842,
1278
+ "Ġac": 843,
1279
+ "Ġind": 844,
1280
+ "ĠWheeler": 845,
1281
+ "ĠLe": 846,
1282
+ "outh": 847,
1283
+ "ĠCom": 848,
1284
+ "usic": 849,
1285
+ "ular": 850,
1286
+ "ious": 851,
1287
+ "ween": 852,
1288
+ "Ġsome": 853,
1289
+ "urch": 854,
1290
+ "end": 855,
1291
+ "ism": 856,
1292
+ "chae": 857,
1293
+ "ĠNew": 858,
1294
+ "chaeolog": 859,
1295
+ "aid": 860,
1296
+ "Ġwrit": 861,
1297
+ "als": 862,
1298
+ "Ġdo": 863,
1299
+ "Ġsuch": 864,
1300
+ "ollow": 865,
1301
+ "ally": 866,
1302
+ "ten": 867,
1303
+ "Ġam": 868,
1304
+ "ins": 869,
1305
+ "Ġpol": 870,
1306
+ "Ġmade": 871,
1307
+ "ific": 872,
1308
+ "Ġmet": 873,
1309
+ "Ġgame": 874,
1310
+ "iel": 875,
1311
+ "Ġhist": 876,
1312
+ "ute": 877,
1313
+ "ĠGal": 878,
1314
+ "Ġwhere": 879,
1315
+ "fore": 880,
1316
+ "ating": 881,
1317
+ "Ġrep": 882,
1318
+ "resent": 883,
1319
+ "ject": 884,
1320
+ "Ġsy": 885,
1321
+ "orld": 886,
1322
+ "Ġpr": 887,
1323
+ "Ġbl": 888,
1324
+ "amp": 889,
1325
+ "iet": 890,
1326
+ "ob": 891,
1327
+ "Ġap": 892,
1328
+ "though": 893,
1329
+ "ove": 894,
1330
+ "ĠBritish": 895,
1331
+ "Ġbetween": 896,
1332
+ "veston": 897,
1333
+ "ĠGalveston": 898,
1334
+ "erman": 899,
1335
+ "row": 900,
1336
+ "Ġant": 901,
1337
+ "Ġship": 902,
1338
+ "ĠChrist": 903,
1339
+ "az": 904,
1340
+ "ool": 905,
1341
+ "Ġthere": 906,
1342
+ "Ġsign": 907,
1343
+ "ĠBl": 908,
1344
+ "Ġsur": 909,
1345
+ "ised": 910,
1346
+ "ired": 911,
1347
+ "ĠYork": 912,
1348
+ "94": 913,
1349
+ "led": 914,
1350
+ "Ġcity": 915,
1351
+ "ĠAll": 916,
1352
+ "98": 917,
1353
+ "up": 918,
1354
+ "Ġchar": 919,
1355
+ "Ġsong": 920,
1356
+ "Ġcall": 921,
1357
+ "ĠGerman": 922,
1358
+ "Ġmany": 923,
1359
+ "Ġnumber": 924,
1360
+ "Ġhigh": 925,
1361
+ "ug": 926,
1362
+ "ics": 927,
1363
+ "ican": 928,
1364
+ "Ġmin": 929,
1365
+ "Ġloc": 930,
1366
+ "Ġno": 931,
1367
+ "Ġwhile": 932,
1368
+ "air": 933,
1369
+ "Ġqu": 934,
1370
+ "Ġboth": 935,
1371
+ "Ġele": 936,
1372
+ "rans": 937,
1373
+ "Ġsupp": 938,
1374
+ "ever": 939,
1375
+ "ĠTown": 940,
1376
+ "ivers": 941,
1377
+ "ife": 942,
1378
+ "Ġlead": 943,
1379
+ "Ġused": 944,
1380
+ "hes": 945,
1381
+ "ived": 946,
1382
+ "veral": 947,
1383
+ "Ġthen": 948,
1384
+ "Ġso": 949,
1385
+ "Ġyears": 950,
1386
+ "Ġgods": 951,
1387
+ "gy": 952,
1388
+ "ren": 953,
1389
+ "Ġlong": 954,
1390
+ "Ġdesc": 955,
1391
+ "91": 956,
1392
+ "Ġbel": 957,
1393
+ "oh": 958,
1394
+ "view": 959,
1395
+ "ause": 960,
1396
+ "ale": 961,
1397
+ "ros": 962,
1398
+ "other": 963,
1399
+ "elf": 964,
1400
+ "ning": 965,
1401
+ "ral": 966,
1402
+ "Ġfollow": 967,
1403
+ "ĠUnited": 968,
1404
+ "Ġdif": 969,
1405
+ "ĠAmer": 970,
1406
+ "very": 971,
1407
+ "ures": 972,
1408
+ "Ġsch": 973,
1409
+ "Ġday": 974,
1410
+ "Ġent": 975,
1411
+ "Ġwell": 976,
1412
+ "Ġmain": 977,
1413
+ "ĠThis": 978,
1414
+ "Ġtr": 979,
1415
+ "Ġdef": 980,
1416
+ "20": 981,
1417
+ "Ġob": 982,
1418
+ "Ġcre": 983,
1419
+ "tern": 984,
1420
+ "ty": 985,
1421
+ "ĠCl": 986,
1422
+ "Ġem": 987,
1423
+ "Ġbefore": 988,
1424
+ "ists": 989,
1425
+ "ĠMar": 990,
1426
+ "raft": 991,
1427
+ "Ġbecame": 992,
1428
+ "Ġthese": 993,
1429
+ "emb": 994,
1430
+ "Ġperform": 995,
1431
+ "Ġagainst": 996,
1432
+ "ah": 997,
1433
+ "ople": 998,
1434
+ "ized": 999,
1435
+ "ield": 1000,
1436
+ "Ġappe": 1001,
1437
+ "stru": 1002,
1438
+ "Ġdep": 1003,
1439
+ "30": 1004,
1440
+ "Ġoper": 1005,
1441
+ "Ġpop": 1006,
1442
+ "Ġknown": 1007,
1443
+ "stein": 1008,
1444
+ "io": 1009,
1445
+ "ys": 1010,
1446
+ "ĠZ": 1011,
1447
+ "Ġcar": 1012,
1448
+ "Ġcol": 1013,
1449
+ "ident": 1014,
1450
+ "owever": 1015,
1451
+ "cept": 1016,
1452
+ "Ġremain": 1017,
1453
+ "son": 1018,
1454
+ "Ġstud": 1019,
1455
+ "Ġincluding": 1020,
1456
+ "Ġ%": 1021,
1457
+ "ĠAnd": 1022,
1458
+ "Ġorig": 1023
1459
+ },
1460
+ "merges": [
1461
+ [
1462
+ "Ġ",
1463
+ "t"
1464
+ ],
1465
+ [
1466
+ "h",
1467
+ "e"
1468
+ ],
1469
+ [
1470
+ "Ġ",
1471
+ "a"
1472
+ ],
1473
+ [
1474
+ "i",
1475
+ "n"
1476
+ ],
1477
+ [
1478
+ "Ġt",
1479
+ "he"
1480
+ ],
1481
+ [
1482
+ "e",
1483
+ "r"
1484
+ ],
1485
+ [
1486
+ "o",
1487
+ "n"
1488
+ ],
1489
+ [
1490
+ "Ġ",
1491
+ ","
1492
+ ],
1493
+ [
1494
+ "r",
1495
+ "e"
1496
+ ],
1497
+ [
1498
+ "Ġ",
1499
+ "s"
1500
+ ],
1501
+ [
1502
+ "e",
1503
+ "d"
1504
+ ],
1505
+ [
1506
+ "Ġ",
1507
+ "o"
1508
+ ],
1509
+ [
1510
+ "n",
1511
+ "d"
1512
+ ],
1513
+ [
1514
+ "Ġ",
1515
+ "w"
1516
+ ],
1517
+ [
1518
+ "a",
1519
+ "t"
1520
+ ],
1521
+ [
1522
+ "Ġ",
1523
+ "."
1524
+ ],
1525
+ [
1526
+ "o",
1527
+ "r"
1528
+ ],
1529
+ [
1530
+ "i",
1531
+ "t"
1532
+ ],
1533
+ [
1534
+ "i",
1535
+ "s"
1536
+ ],
1537
+ [
1538
+ "Ġ",
1539
+ "c"
1540
+ ],
1541
+ [
1542
+ "e",
1543
+ "s"
1544
+ ],
1545
+ [
1546
+ "Ġ",
1547
+ "f"
1548
+ ],
1549
+ [
1550
+ "e",
1551
+ "n"
1552
+ ],
1553
+ [
1554
+ "Ġo",
1555
+ "f"
1556
+ ],
1557
+ [
1558
+ "a",
1559
+ "r"
1560
+ ],
1561
+ [
1562
+ "a",
1563
+ "l"
1564
+ ],
1565
+ [
1566
+ "Ġ",
1567
+ "in"
1568
+ ],
1569
+ [
1570
+ "Ġ",
1571
+ "b"
1572
+ ],
1573
+ [
1574
+ "a",
1575
+ "n"
1576
+ ],
1577
+ [
1578
+ "Ġ",
1579
+ "p"
1580
+ ],
1581
+ [
1582
+ "in",
1583
+ "g"
1584
+ ],
1585
+ [
1586
+ "a",
1587
+ "s"
1588
+ ],
1589
+ [
1590
+ "Ġa",
1591
+ "nd"
1592
+ ],
1593
+ [
1594
+ "i",
1595
+ "c"
1596
+ ],
1597
+ [
1598
+ "Ġt",
1599
+ "o"
1600
+ ],
1601
+ [
1602
+ "Ġ",
1603
+ "m"
1604
+ ],
1605
+ [
1606
+ "r",
1607
+ "o"
1608
+ ],
1609
+ [
1610
+ "Ġ",
1611
+ "d"
1612
+ ],
1613
+ [
1614
+ "Ġ",
1615
+ "h"
1616
+ ],
1617
+ [
1618
+ "i",
1619
+ "on"
1620
+ ],
1621
+ [
1622
+ "l",
1623
+ "e"
1624
+ ],
1625
+ [
1626
+ "Ġ",
1627
+ "T"
1628
+ ],
1629
+ [
1630
+ "o",
1631
+ "u"
1632
+ ],
1633
+ [
1634
+ "Ġ",
1635
+ "re"
1636
+ ],
1637
+ [
1638
+ "Ġ",
1639
+ "="
1640
+ ],
1641
+ [
1642
+ "Ġ",
1643
+ "A"
1644
+ ],
1645
+ [
1646
+ "Ġ",
1647
+ "\""
1648
+ ],
1649
+ [
1650
+ "Ġ",
1651
+ "S"
1652
+ ],
1653
+ [
1654
+ "Ġt",
1655
+ "h"
1656
+ ],
1657
+ [
1658
+ "en",
1659
+ "t"
1660
+ ],
1661
+ [
1662
+ "i",
1663
+ "l"
1664
+ ],
1665
+ [
1666
+ "s",
1667
+ "t"
1668
+ ],
1669
+ [
1670
+ "Ġ",
1671
+ "@"
1672
+ ],
1673
+ [
1674
+ "e",
1675
+ "l"
1676
+ ],
1677
+ [
1678
+ "Ġ",
1679
+ "C"
1680
+ ],
1681
+ [
1682
+ "Ġ",
1683
+ "Ċ"
1684
+ ],
1685
+ [
1686
+ "o",
1687
+ "l"
1688
+ ],
1689
+ [
1690
+ "Ġ",
1691
+ "l"
1692
+ ],
1693
+ [
1694
+ "Ġ",
1695
+ "n"
1696
+ ],
1697
+ [
1698
+ "o",
1699
+ "m"
1700
+ ],
1701
+ [
1702
+ "Ġ",
1703
+ "e"
1704
+ ],
1705
+ [
1706
+ "c",
1707
+ "t"
1708
+ ],
1709
+ [
1710
+ "a",
1711
+ "m"
1712
+ ],
1713
+ [
1714
+ "a",
1715
+ "d"
1716
+ ],
1717
+ [
1718
+ "Ġ",
1719
+ "g"
1720
+ ],
1721
+ [
1722
+ "Ġw",
1723
+ "as"
1724
+ ],
1725
+ [
1726
+ "u",
1727
+ "r"
1728
+ ],
1729
+ [
1730
+ "Ġ",
1731
+ "on"
1732
+ ],
1733
+ [
1734
+ "ĠT",
1735
+ "he"
1736
+ ],
1737
+ [
1738
+ "Ġ",
1739
+ "I"
1740
+ ],
1741
+ [
1742
+ "i",
1743
+ "m"
1744
+ ],
1745
+ [
1746
+ "-",
1747
+ "@"
1748
+ ],
1749
+ [
1750
+ "Ġ@",
1751
+ "-@"
1752
+ ],
1753
+ [
1754
+ "Ġb",
1755
+ "e"
1756
+ ],
1757
+ [
1758
+ "l",
1759
+ "y"
1760
+ ],
1761
+ [
1762
+ "Ġ",
1763
+ "M"
1764
+ ],
1765
+ [
1766
+ "i",
1767
+ "d"
1768
+ ],
1769
+ [
1770
+ "Ġf",
1771
+ "or"
1772
+ ],
1773
+ [
1774
+ "i",
1775
+ "r"
1776
+ ],
1777
+ [
1778
+ "c",
1779
+ "h"
1780
+ ],
1781
+ [
1782
+ "Ġ",
1783
+ "B"
1784
+ ],
1785
+ [
1786
+ "i",
1787
+ "v"
1788
+ ],
1789
+ [
1790
+ "o",
1791
+ "t"
1792
+ ],
1793
+ [
1794
+ "Ġ",
1795
+ "'"
1796
+ ],
1797
+ [
1798
+ "it",
1799
+ "h"
1800
+ ],
1801
+ [
1802
+ "at",
1803
+ "ion"
1804
+ ],
1805
+ [
1806
+ "r",
1807
+ "a"
1808
+ ],
1809
+ [
1810
+ "i",
1811
+ "g"
1812
+ ],
1813
+ [
1814
+ "Ġa",
1815
+ "s"
1816
+ ],
1817
+ [
1818
+ "e",
1819
+ "t"
1820
+ ],
1821
+ [
1822
+ "o",
1823
+ "w"
1824
+ ],
1825
+ [
1826
+ "u",
1827
+ "s"
1828
+ ],
1829
+ [
1830
+ "u",
1831
+ "t"
1832
+ ],
1833
+ [
1834
+ "Ġs",
1835
+ "t"
1836
+ ],
1837
+ [
1838
+ "c",
1839
+ "e"
1840
+ ],
1841
+ [
1842
+ "Ġw",
1843
+ "ith"
1844
+ ],
1845
+ [
1846
+ "Ġ",
1847
+ "P"
1848
+ ],
1849
+ [
1850
+ "er",
1851
+ "s"
1852
+ ],
1853
+ [
1854
+ "Ġ",
1855
+ "he"
1856
+ ],
1857
+ [
1858
+ "Ġth",
1859
+ "at"
1860
+ ],
1861
+ [
1862
+ "a",
1863
+ "y"
1864
+ ],
1865
+ [
1866
+ "Ġ",
1867
+ "is"
1868
+ ],
1869
+ [
1870
+ "Ġ",
1871
+ "H"
1872
+ ],
1873
+ [
1874
+ "u",
1875
+ "l"
1876
+ ],
1877
+ [
1878
+ "Ġ",
1879
+ "G"
1880
+ ],
1881
+ [
1882
+ "Ġ",
1883
+ "F"
1884
+ ],
1885
+ [
1886
+ "Ġa",
1887
+ "l"
1888
+ ],
1889
+ [
1890
+ "Ġ",
1891
+ "R"
1892
+ ],
1893
+ [
1894
+ "Ġ",
1895
+ "N"
1896
+ ],
1897
+ [
1898
+ "is",
1899
+ "t"
1900
+ ],
1901
+ [
1902
+ "u",
1903
+ "m"
1904
+ ],
1905
+ [
1906
+ "e",
1907
+ "m"
1908
+ ],
1909
+ [
1910
+ "Ġw",
1911
+ "h"
1912
+ ],
1913
+ [
1914
+ "Ġ",
1915
+ "W"
1916
+ ],
1917
+ [
1918
+ "es",
1919
+ "t"
1920
+ ],
1921
+ [
1922
+ "Ġb",
1923
+ "y"
1924
+ ],
1925
+ [
1926
+ "u",
1927
+ "n"
1928
+ ],
1929
+ [
1930
+ "Ġa",
1931
+ "n"
1932
+ ],
1933
+ [
1934
+ "v",
1935
+ "er"
1936
+ ],
1937
+ [
1938
+ "o",
1939
+ "s"
1940
+ ],
1941
+ [
1942
+ "t",
1943
+ "h"
1944
+ ],
1945
+ [
1946
+ "Ġ",
1947
+ ")"
1948
+ ],
1949
+ [
1950
+ "Ġ",
1951
+ "("
1952
+ ],
1953
+ [
1954
+ "t",
1955
+ "er"
1956
+ ],
1957
+ [
1958
+ "Ġc",
1959
+ "on"
1960
+ ],
1961
+ [
1962
+ "Ġ",
1963
+ "J"
1964
+ ],
1965
+ [
1966
+ "ro",
1967
+ "m"
1968
+ ],
1969
+ [
1970
+ "Ġ",
1971
+ "D"
1972
+ ],
1973
+ [
1974
+ "Ġa",
1975
+ "t"
1976
+ ],
1977
+ [
1978
+ "Ġs",
1979
+ "e"
1980
+ ],
1981
+ [
1982
+ "a",
1983
+ "nd"
1984
+ ],
1985
+ [
1986
+ "o",
1987
+ "d"
1988
+ ],
1989
+ [
1990
+ "Ġ",
1991
+ "L"
1992
+ ],
1993
+ [
1994
+ "a",
1995
+ "v"
1996
+ ],
1997
+ [
1998
+ "Ġ",
1999
+ "it"
2000
+ ],
2001
+ [
2002
+ "0",
2003
+ "0"
2004
+ ],
2005
+ [
2006
+ "Ġd",
2007
+ "e"
2008
+ ],
2009
+ [
2010
+ "a",
2011
+ "g"
2012
+ ],
2013
+ [
2014
+ "he",
2015
+ "r"
2016
+ ],
2017
+ [
2018
+ "i",
2019
+ "es"
2020
+ ],
2021
+ [
2022
+ "p",
2023
+ "e"
2024
+ ],
2025
+ [
2026
+ "Ġ",
2027
+ "E"
2028
+ ],
2029
+ [
2030
+ "a",
2031
+ "in"
2032
+ ],
2033
+ [
2034
+ "c",
2035
+ "k"
2036
+ ],
2037
+ [
2038
+ "Ġh",
2039
+ "is"
2040
+ ],
2041
+ [
2042
+ "r",
2043
+ "i"
2044
+ ],
2045
+ [
2046
+ "Ġf",
2047
+ "rom"
2048
+ ],
2049
+ [
2050
+ "er",
2051
+ "e"
2052
+ ],
2053
+ [
2054
+ "re",
2055
+ "s"
2056
+ ],
2057
+ [
2058
+ "or",
2059
+ "t"
2060
+ ],
2061
+ [
2062
+ "Ġp",
2063
+ "ro"
2064
+ ],
2065
+ [
2066
+ "i",
2067
+ "f"
2068
+ ],
2069
+ [
2070
+ "Ġc",
2071
+ "om"
2072
+ ],
2073
+ [
2074
+ "e",
2075
+ "w"
2076
+ ],
2077
+ [
2078
+ "it",
2079
+ "y"
2080
+ ],
2081
+ [
2082
+ "Ġw",
2083
+ "ere"
2084
+ ],
2085
+ [
2086
+ "Ġ",
2087
+ "v"
2088
+ ],
2089
+ [
2090
+ "at",
2091
+ "e"
2092
+ ],
2093
+ [
2094
+ "ĠI",
2095
+ "n"
2096
+ ],
2097
+ [
2098
+ "Ġs",
2099
+ "u"
2100
+ ],
2101
+ [
2102
+ "Ġ",
2103
+ "O"
2104
+ ],
2105
+ [
2106
+ "o",
2107
+ "p"
2108
+ ],
2109
+ [
2110
+ "Ġo",
2111
+ "r"
2112
+ ],
2113
+ [
2114
+ "ic",
2115
+ "h"
2116
+ ],
2117
+ [
2118
+ "o",
2119
+ "re"
2120
+ ],
2121
+ [
2122
+ "al",
2123
+ "l"
2124
+ ],
2125
+ [
2126
+ "ig",
2127
+ "h"
2128
+ ],
2129
+ [
2130
+ "at",
2131
+ "ed"
2132
+ ],
2133
+ [
2134
+ "or",
2135
+ "d"
2136
+ ],
2137
+ [
2138
+ "s",
2139
+ "e"
2140
+ ],
2141
+ [
2142
+ "il",
2143
+ "l"
2144
+ ],
2145
+ [
2146
+ "ar",
2147
+ "t"
2148
+ ],
2149
+ [
2150
+ "Ġe",
2151
+ "x"
2152
+ ],
2153
+ [
2154
+ "a",
2155
+ "b"
2156
+ ],
2157
+ [
2158
+ "p",
2159
+ "t"
2160
+ ],
2161
+ [
2162
+ "Ġc",
2163
+ "h"
2164
+ ],
2165
+ [
2166
+ "Ġs",
2167
+ "h"
2168
+ ],
2169
+ [
2170
+ "l",
2171
+ "d"
2172
+ ],
2173
+ [
2174
+ "Ġp",
2175
+ "l"
2176
+ ],
2177
+ [
2178
+ "p",
2179
+ "p"
2180
+ ],
2181
+ [
2182
+ "a",
2183
+ "k"
2184
+ ],
2185
+ [
2186
+ "Ġa",
2187
+ "re"
2188
+ ],
2189
+ [
2190
+ "b",
2191
+ "er"
2192
+ ],
2193
+ [
2194
+ "g",
2195
+ "h"
2196
+ ],
2197
+ [
2198
+ "es",
2199
+ "s"
2200
+ ],
2201
+ [
2202
+ "u",
2203
+ "d"
2204
+ ],
2205
+ [
2206
+ "Ġ",
2207
+ "â"
2208
+ ],
2209
+ [
2210
+ "an",
2211
+ "t"
2212
+ ],
2213
+ [
2214
+ "ar",
2215
+ "d"
2216
+ ],
2217
+ [
2218
+ "ro",
2219
+ "u"
2220
+ ],
2221
+ [
2222
+ "on",
2223
+ "g"
2224
+ ],
2225
+ [
2226
+ "Ġ",
2227
+ "U"
2228
+ ],
2229
+ [
2230
+ "r",
2231
+ "u"
2232
+ ],
2233
+ [
2234
+ "i",
2235
+ "a"
2236
+ ],
2237
+ [
2238
+ "q",
2239
+ "u"
2240
+ ],
2241
+ [
2242
+ "Ġwh",
2243
+ "ich"
2244
+ ],
2245
+ [
2246
+ "Ġâ",
2247
+ "Ģ"
2248
+ ],
2249
+ [
2250
+ "am",
2251
+ "e"
2252
+ ],
2253
+ [
2254
+ "m",
2255
+ "ent"
2256
+ ],
2257
+ [
2258
+ "ĠC",
2259
+ "h"
2260
+ ],
2261
+ [
2262
+ "Ġ",
2263
+ "le"
2264
+ ],
2265
+ [
2266
+ "r",
2267
+ "it"
2268
+ ],
2269
+ [
2270
+ "Ġh",
2271
+ "ad"
2272
+ ],
2273
+ [
2274
+ "i",
2275
+ "al"
2276
+ ],
2277
+ [
2278
+ "i",
2279
+ "an"
2280
+ ],
2281
+ [
2282
+ "o",
2283
+ "g"
2284
+ ],
2285
+ [
2286
+ "re",
2287
+ "d"
2288
+ ],
2289
+ [
2290
+ "Ġ",
2291
+ "K"
2292
+ ],
2293
+ [
2294
+ "ĠS",
2295
+ "t"
2296
+ ],
2297
+ [
2298
+ "iv",
2299
+ "e"
2300
+ ],
2301
+ [
2302
+ "o",
2303
+ "c"
2304
+ ],
2305
+ [
2306
+ "i",
2307
+ "p"
2308
+ ],
2309
+ [
2310
+ "o",
2311
+ "v"
2312
+ ],
2313
+ [
2314
+ "Ġ",
2315
+ ";"
2316
+ ],
2317
+ [
2318
+ "Ġ",
2319
+ "r"
2320
+ ],
2321
+ [
2322
+ "is",
2323
+ "h"
2324
+ ],
2325
+ [
2326
+ "o",
2327
+ "st"
2328
+ ],
2329
+ [
2330
+ "ou",
2331
+ "r"
2332
+ ],
2333
+ [
2334
+ "Ġa",
2335
+ "r"
2336
+ ],
2337
+ [
2338
+ "Ġ",
2339
+ "u"
2340
+ ],
2341
+ [
2342
+ "Ġn",
2343
+ "ot"
2344
+ ],
2345
+ [
2346
+ "e",
2347
+ "ar"
2348
+ ],
2349
+ [
2350
+ "igh",
2351
+ "t"
2352
+ ],
2353
+ [
2354
+ "as",
2355
+ "t"
2356
+ ],
2357
+ [
2358
+ "a",
2359
+ "c"
2360
+ ],
2361
+ [
2362
+ "Ġ",
2363
+ "y"
2364
+ ],
2365
+ [
2366
+ "Ġ",
2367
+ "k"
2368
+ ],
2369
+ [
2370
+ "av",
2371
+ "e"
2372
+ ],
2373
+ [
2374
+ "ar",
2375
+ "y"
2376
+ ],
2377
+ [
2378
+ "el",
2379
+ "l"
2380
+ ],
2381
+ [
2382
+ "t",
2383
+ "her"
2384
+ ],
2385
+ [
2386
+ "ct",
2387
+ "ion"
2388
+ ],
2389
+ [
2390
+ "ic",
2391
+ "al"
2392
+ ],
2393
+ [
2394
+ "n",
2395
+ "t"
2396
+ ],
2397
+ [
2398
+ "ow",
2399
+ "n"
2400
+ ],
2401
+ [
2402
+ "c",
2403
+ "c"
2404
+ ],
2405
+ [
2406
+ "Ġin",
2407
+ "c"
2408
+ ],
2409
+ [
2410
+ "in",
2411
+ "e"
2412
+ ],
2413
+ [
2414
+ "g",
2415
+ "e"
2416
+ ],
2417
+ [
2418
+ "id",
2419
+ "e"
2420
+ ],
2421
+ [
2422
+ "u",
2423
+ "st"
2424
+ ],
2425
+ [
2426
+ "ĠâĢ",
2427
+ "ĵ"
2428
+ ],
2429
+ [
2430
+ "Ġhe",
2431
+ "r"
2432
+ ],
2433
+ [
2434
+ "s",
2435
+ "o"
2436
+ ],
2437
+ [
2438
+ "a",
2439
+ "p"
2440
+ ],
2441
+ [
2442
+ "u",
2443
+ "e"
2444
+ ],
2445
+ [
2446
+ "u",
2447
+ "re"
2448
+ ],
2449
+ [
2450
+ "or",
2451
+ "k"
2452
+ ],
2453
+ [
2454
+ "r",
2455
+ "an"
2456
+ ],
2457
+ [
2458
+ "ou",
2459
+ "t"
2460
+ ],
2461
+ [
2462
+ "Ġal",
2463
+ "so"
2464
+ ],
2465
+ [
2466
+ "Ġthe",
2467
+ "ir"
2468
+ ],
2469
+ [
2470
+ "Ġh",
2471
+ "as"
2472
+ ],
2473
+ [
2474
+ "w",
2475
+ "o"
2476
+ ],
2477
+ [
2478
+ "Ġ",
2479
+ "un"
2480
+ ],
2481
+ [
2482
+ "ou",
2483
+ "s"
2484
+ ],
2485
+ [
2486
+ "f",
2487
+ "f"
2488
+ ],
2489
+ [
2490
+ "ig",
2491
+ "n"
2492
+ ],
2493
+ [
2494
+ "f",
2495
+ "ter"
2496
+ ],
2497
+ [
2498
+ "Ġ",
2499
+ "V"
2500
+ ],
2501
+ [
2502
+ "u",
2503
+ "b"
2504
+ ],
2505
+ [
2506
+ "Ġre",
2507
+ "c"
2508
+ ],
2509
+ [
2510
+ "om",
2511
+ "e"
2512
+ ],
2513
+ [
2514
+ "0",
2515
+ "1"
2516
+ ],
2517
+ [
2518
+ "Ġc",
2519
+ "l"
2520
+ ],
2521
+ [
2522
+ ".",
2523
+ "@"
2524
+ ],
2525
+ [
2526
+ "Ġ@",
2527
+ ".@"
2528
+ ],
2529
+ [
2530
+ "Ġcon",
2531
+ "t"
2532
+ ],
2533
+ [
2534
+ "ir",
2535
+ "st"
2536
+ ],
2537
+ [
2538
+ "ĠH",
2539
+ "e"
2540
+ ],
2541
+ [
2542
+ "Ġt",
2543
+ "e"
2544
+ ],
2545
+ [
2546
+ "it",
2547
+ "ion"
2548
+ ],
2549
+ [
2550
+ "at",
2551
+ "er"
2552
+ ],
2553
+ [
2554
+ "Ġp",
2555
+ "er"
2556
+ ],
2557
+ [
2558
+ "as",
2559
+ "s"
2560
+ ],
2561
+ [
2562
+ "a",
2563
+ "ck"
2564
+ ],
2565
+ [
2566
+ "ation",
2567
+ "s"
2568
+ ],
2569
+ [
2570
+ "i",
2571
+ "e"
2572
+ ],
2573
+ [
2574
+ "Ġit",
2575
+ "s"
2576
+ ],
2577
+ [
2578
+ "Ġa",
2579
+ "b"
2580
+ ],
2581
+ [
2582
+ "p",
2583
+ "l"
2584
+ ],
2585
+ [
2586
+ "Ġon",
2587
+ "e"
2588
+ ],
2589
+ [
2590
+ "Ġin",
2591
+ "t"
2592
+ ],
2593
+ [
2594
+ "Ġs",
2595
+ "c"
2596
+ ],
2597
+ [
2598
+ "Ġf",
2599
+ "irst"
2600
+ ],
2601
+ [
2602
+ "on",
2603
+ "d"
2604
+ ],
2605
+ [
2606
+ "im",
2607
+ "e"
2608
+ ],
2609
+ [
2610
+ "he",
2611
+ "d"
2612
+ ],
2613
+ [
2614
+ "Ġ",
2615
+ ":"
2616
+ ],
2617
+ [
2618
+ "or",
2619
+ "m"
2620
+ ],
2621
+ [
2622
+ "ul",
2623
+ "t"
2624
+ ],
2625
+ [
2626
+ "ou",
2627
+ "ld"
2628
+ ],
2629
+ [
2630
+ "or",
2631
+ "y"
2632
+ ],
2633
+ [
2634
+ "Ġwh",
2635
+ "o"
2636
+ ],
2637
+ [
2638
+ "Ġw",
2639
+ "he"
2640
+ ],
2641
+ [
2642
+ "ĠT",
2643
+ "h"
2644
+ ],
2645
+ [
2646
+ "p",
2647
+ "er"
2648
+ ],
2649
+ [
2650
+ "Ġb",
2651
+ "ut"
2652
+ ],
2653
+ [
2654
+ "Ġh",
2655
+ "ave"
2656
+ ],
2657
+ [
2658
+ "Ġt",
2659
+ "wo"
2660
+ ],
2661
+ [
2662
+ "nd",
2663
+ "er"
2664
+ ],
2665
+ [
2666
+ "ĠA",
2667
+ "l"
2668
+ ],
2669
+ [
2670
+ "e",
2671
+ "ct"
2672
+ ],
2673
+ [
2674
+ "Ġth",
2675
+ "is"
2676
+ ],
2677
+ [
2678
+ "o",
2679
+ "k"
2680
+ ],
2681
+ [
2682
+ "ar",
2683
+ "k"
2684
+ ],
2685
+ [
2686
+ "ur",
2687
+ "ing"
2688
+ ],
2689
+ [
2690
+ "d",
2691
+ "u"
2692
+ ],
2693
+ [
2694
+ "i",
2695
+ "re"
2696
+ ],
2697
+ [
2698
+ "ou",
2699
+ "gh"
2700
+ ],
2701
+ [
2702
+ "u",
2703
+ "al"
2704
+ ],
2705
+ [
2706
+ "Ġal",
2707
+ "l"
2708
+ ],
2709
+ [
2710
+ "Ġ",
2711
+ "Y"
2712
+ ],
2713
+ [
2714
+ "i",
2715
+ "z"
2716
+ ],
2717
+ [
2718
+ "m",
2719
+ "er"
2720
+ ],
2721
+ [
2722
+ "Ġ",
2723
+ "us"
2724
+ ],
2725
+ [
2726
+ "a",
2727
+ "ch"
2728
+ ],
2729
+ [
2730
+ "ol",
2731
+ "l"
2732
+ ],
2733
+ [
2734
+ "Ġbe",
2735
+ "en"
2736
+ ],
2737
+ [
2738
+ "Ġpl",
2739
+ "ay"
2740
+ ],
2741
+ [
2742
+ "Ġre",
2743
+ "s"
2744
+ ],
2745
+ [
2746
+ "re",
2747
+ "e"
2748
+ ],
2749
+ [
2750
+ "Ġs",
2751
+ "he"
2752
+ ],
2753
+ [
2754
+ ",",
2755
+ "@"
2756
+ ],
2757
+ [
2758
+ "Ġ@",
2759
+ ",@"
2760
+ ],
2761
+ [
2762
+ "ag",
2763
+ "e"
2764
+ ],
2765
+ [
2766
+ "Ġof",
2767
+ "f"
2768
+ ],
2769
+ [
2770
+ "e",
2771
+ "y"
2772
+ ],
2773
+ [
2774
+ "Ġcom",
2775
+ "p"
2776
+ ],
2777
+ [
2778
+ "Ġa",
2779
+ "g"
2780
+ ],
2781
+ [
2782
+ "as",
2783
+ "on"
2784
+ ],
2785
+ [
2786
+ "p",
2787
+ "ort"
2788
+ ],
2789
+ [
2790
+ "o",
2791
+ "in"
2792
+ ],
2793
+ [
2794
+ "Ġa",
2795
+ "d"
2796
+ ],
2797
+ [
2798
+ "Ġy",
2799
+ "ear"
2800
+ ],
2801
+ [
2802
+ "Ġ",
2803
+ "im"
2804
+ ],
2805
+ [
2806
+ "ĠI",
2807
+ "t"
2808
+ ],
2809
+ [
2810
+ "en",
2811
+ "ce"
2812
+ ],
2813
+ [
2814
+ "Ġp",
2815
+ "art"
2816
+ ],
2817
+ [
2818
+ "Ġd",
2819
+ "es"
2820
+ ],
2821
+ [
2822
+ "k",
2823
+ "e"
2824
+ ],
2825
+ [
2826
+ "r",
2827
+ "ic"
2828
+ ],
2829
+ [
2830
+ "a",
2831
+ "re"
2832
+ ],
2833
+ [
2834
+ "r",
2835
+ "y"
2836
+ ],
2837
+ [
2838
+ "l",
2839
+ "ud"
2840
+ ],
2841
+ [
2842
+ "Ġbe",
2843
+ "c"
2844
+ ],
2845
+ [
2846
+ "t",
2847
+ "e"
2848
+ ],
2849
+ [
2850
+ "Ġ",
2851
+ "j"
2852
+ ],
2853
+ [
2854
+ "Ġo",
2855
+ "ther"
2856
+ ],
2857
+ [
2858
+ "el",
2859
+ "y"
2860
+ ],
2861
+ [
2862
+ "Ġd",
2863
+ "is"
2864
+ ],
2865
+ [
2866
+ "p",
2867
+ "h"
2868
+ ],
2869
+ [
2870
+ "Ġm",
2871
+ "an"
2872
+ ],
2873
+ [
2874
+ "ou",
2875
+ "nd"
2876
+ ],
2877
+ [
2878
+ "ol",
2879
+ "d"
2880
+ ],
2881
+ [
2882
+ "Ġs",
2883
+ "pe"
2884
+ ],
2885
+ [
2886
+ "a",
2887
+ "ct"
2888
+ ],
2889
+ [
2890
+ "Ġ",
2891
+ "ro"
2892
+ ],
2893
+ [
2894
+ "Ġa",
2895
+ "fter"
2896
+ ],
2897
+ [
2898
+ "an",
2899
+ "ce"
2900
+ ],
2901
+ [
2902
+ "at",
2903
+ "h"
2904
+ ],
2905
+ [
2906
+ "Ġ",
2907
+ "en"
2908
+ ],
2909
+ [
2910
+ "it",
2911
+ "ed"
2912
+ ],
2913
+ [
2914
+ "ĠU",
2915
+ "n"
2916
+ ],
2917
+ [
2918
+ "Ġg",
2919
+ "o"
2920
+ ],
2921
+ [
2922
+ "i",
2923
+ "b"
2924
+ ],
2925
+ [
2926
+ "i",
2927
+ "le"
2928
+ ],
2929
+ [
2930
+ "Ġthe",
2931
+ "y"
2932
+ ],
2933
+ [
2934
+ "it",
2935
+ "e"
2936
+ ],
2937
+ [
2938
+ "m",
2939
+ "an"
2940
+ ],
2941
+ [
2942
+ "it",
2943
+ "ies"
2944
+ ],
2945
+ [
2946
+ "Ġo",
2947
+ "ver"
2948
+ ],
2949
+ [
2950
+ "c",
2951
+ "ed"
2952
+ ],
2953
+ [
2954
+ "ent",
2955
+ "s"
2956
+ ],
2957
+ [
2958
+ "or",
2959
+ "s"
2960
+ ],
2961
+ [
2962
+ "rou",
2963
+ "nd"
2964
+ ],
2965
+ [
2966
+ "il",
2967
+ "m"
2968
+ ],
2969
+ [
2970
+ "Ġinc",
2971
+ "lud"
2972
+ ],
2973
+ [
2974
+ "Ġp",
2975
+ "re"
2976
+ ],
2977
+ [
2978
+ "ĠR",
2979
+ "e"
2980
+ ],
2981
+ [
2982
+ "v",
2983
+ "i"
2984
+ ],
2985
+ [
2986
+ "ol",
2987
+ "og"
2988
+ ],
2989
+ [
2990
+ "t",
2991
+ "ed"
2992
+ ],
2993
+ [
2994
+ "ad",
2995
+ "e"
2996
+ ],
2997
+ [
2998
+ "i",
2999
+ "ed"
3000
+ ],
3001
+ [
3002
+ "os",
3003
+ "e"
3004
+ ],
3005
+ [
3006
+ "as",
3007
+ "e"
3008
+ ],
3009
+ [
3010
+ "Ġcom",
3011
+ "m"
3012
+ ],
3013
+ [
3014
+ "Ġt",
3015
+ "ime"
3016
+ ],
3017
+ [
3018
+ "Ġs",
3019
+ "er"
3020
+ ],
3021
+ [
3022
+ "in",
3023
+ "al"
3024
+ ],
3025
+ [
3026
+ "Ġse",
3027
+ "ason"
3028
+ ],
3029
+ [
3030
+ "9",
3031
+ "9"
3032
+ ],
3033
+ [
3034
+ "as",
3035
+ "ed"
3036
+ ],
3037
+ [
3038
+ "Ġo",
3039
+ "ut"
3040
+ ],
3041
+ [
3042
+ "ic",
3043
+ "e"
3044
+ ],
3045
+ [
3046
+ "ĠA",
3047
+ "r"
3048
+ ],
3049
+ [
3050
+ "at",
3051
+ "es"
3052
+ ],
3053
+ [
3054
+ "res",
3055
+ "s"
3056
+ ],
3057
+ [
3058
+ "Ġu",
3059
+ "p"
3060
+ ],
3061
+ [
3062
+ "ĠS",
3063
+ "e"
3064
+ ],
3065
+ [
3066
+ "f",
3067
+ "t"
3068
+ ],
3069
+ [
3070
+ "Ġthe",
3071
+ "m"
3072
+ ],
3073
+ [
3074
+ "ub",
3075
+ "l"
3076
+ ],
3077
+ [
3078
+ "l",
3079
+ "es"
3080
+ ],
3081
+ [
3082
+ "il",
3083
+ "d"
3084
+ ],
3085
+ [
3086
+ "Ġs",
3087
+ "p"
3088
+ ],
3089
+ [
3090
+ "Ġe",
3091
+ "v"
3092
+ ],
3093
+ [
3094
+ "Ġm",
3095
+ "ore"
3096
+ ],
3097
+ [
3098
+ "l",
3099
+ "and"
3100
+ ],
3101
+ [
3102
+ "b",
3103
+ "um"
3104
+ ],
3105
+ [
3106
+ "f",
3107
+ "er"
3108
+ ],
3109
+ [
3110
+ "c",
3111
+ "es"
3112
+ ],
3113
+ [
3114
+ "Ġn",
3115
+ "ew"
3116
+ ],
3117
+ [
3118
+ "g",
3119
+ "an"
3120
+ ],
3121
+ [
3122
+ "rou",
3123
+ "gh"
3124
+ ],
3125
+ [
3126
+ "ab",
3127
+ "le"
3128
+ ],
3129
+ [
3130
+ "r",
3131
+ "on"
3132
+ ],
3133
+ [
3134
+ "t",
3135
+ "s"
3136
+ ],
3137
+ [
3138
+ "ĠD",
3139
+ "e"
3140
+ ],
3141
+ [
3142
+ "a",
3143
+ "ce"
3144
+ ],
3145
+ [
3146
+ "Ġn",
3147
+ "e"
3148
+ ],
3149
+ [
3150
+ "Ġg",
3151
+ "od"
3152
+ ],
3153
+ [
3154
+ "o",
3155
+ "ck"
3156
+ ],
3157
+ [
3158
+ "Ġal",
3159
+ "bum"
3160
+ ],
3161
+ [
3162
+ "ri",
3163
+ "b"
3164
+ ],
3165
+ [
3166
+ "w",
3167
+ "ard"
3168
+ ],
3169
+ [
3170
+ "Ġre",
3171
+ "m"
3172
+ ],
3173
+ [
3174
+ "Ġse",
3175
+ "c"
3176
+ ],
3177
+ [
3178
+ "Ġu",
3179
+ "nder"
3180
+ ],
3181
+ [
3182
+ "w",
3183
+ "n"
3184
+ ],
3185
+ [
3186
+ "Ġw",
3187
+ "ork"
3188
+ ],
3189
+ [
3190
+ "er",
3191
+ "ed"
3192
+ ],
3193
+ [
3194
+ "ĠS",
3195
+ "h"
3196
+ ],
3197
+ [
3198
+ "in",
3199
+ "d"
3200
+ ],
3201
+ [
3202
+ "en",
3203
+ "s"
3204
+ ],
3205
+ [
3206
+ "Ġre",
3207
+ "l"
3208
+ ],
3209
+ [
3210
+ "Ġf",
3211
+ "ilm"
3212
+ ],
3213
+ [
3214
+ "us",
3215
+ "e"
3216
+ ],
3217
+ [
3218
+ "Ġh",
3219
+ "im"
3220
+ ],
3221
+ [
3222
+ "ing",
3223
+ "s"
3224
+ ],
3225
+ [
3226
+ "ou",
3227
+ "nt"
3228
+ ],
3229
+ [
3230
+ "Ġrec",
3231
+ "ord"
3232
+ ],
3233
+ [
3234
+ "Ġspe",
3235
+ "c"
3236
+ ],
3237
+ [
3238
+ "ĠW",
3239
+ "he"
3240
+ ],
3241
+ [
3242
+ "Ġint",
3243
+ "o"
3244
+ ],
3245
+ [
3246
+ "ar",
3247
+ "n"
3248
+ ],
3249
+ [
3250
+ "re",
3251
+ "at"
3252
+ ],
3253
+ [
3254
+ "h",
3255
+ "ip"
3256
+ ],
3257
+ [
3258
+ "on",
3259
+ "e"
3260
+ ],
3261
+ [
3262
+ "or",
3263
+ "n"
3264
+ ],
3265
+ [
3266
+ "Ġin",
3267
+ "ter"
3268
+ ],
3269
+ [
3270
+ "ur",
3271
+ "n"
3272
+ ],
3273
+ [
3274
+ "a",
3275
+ "il"
3276
+ ],
3277
+ [
3278
+ "Ġf",
3279
+ "e"
3280
+ ],
3281
+ [
3282
+ "em",
3283
+ "ber"
3284
+ ],
3285
+ [
3286
+ "Ġcon",
3287
+ "s"
3288
+ ],
3289
+ [
3290
+ "f",
3291
+ "orm"
3292
+ ],
3293
+ [
3294
+ "i",
3295
+ "x"
3296
+ ],
3297
+ [
3298
+ "v",
3299
+ "ed"
3300
+ ],
3301
+ [
3302
+ "Ġm",
3303
+ "ost"
3304
+ ],
3305
+ [
3306
+ "Ġre",
3307
+ "g"
3308
+ ],
3309
+ [
3310
+ "ation",
3311
+ "al"
3312
+ ],
3313
+ [
3314
+ "er",
3315
+ "n"
3316
+ ],
3317
+ [
3318
+ "ar",
3319
+ "ly"
3320
+ ],
3321
+ [
3322
+ "ĠP",
3323
+ "ol"
3324
+ ],
3325
+ [
3326
+ "Ġa",
3327
+ "ct"
3328
+ ],
3329
+ [
3330
+ "o",
3331
+ "y"
3332
+ ],
3333
+ [
3334
+ "in",
3335
+ "k"
3336
+ ],
3337
+ [
3338
+ "am",
3339
+ "es"
3340
+ ],
3341
+ [
3342
+ "ord",
3343
+ "an"
3344
+ ],
3345
+ [
3346
+ "ĠJ",
3347
+ "ordan"
3348
+ ],
3349
+ [
3350
+ "ĠO",
3351
+ "n"
3352
+ ],
3353
+ [
3354
+ "Ġa",
3355
+ "ir"
3356
+ ],
3357
+ [
3358
+ "ĠA",
3359
+ "s"
3360
+ ],
3361
+ [
3362
+ "Ġd",
3363
+ "uring"
3364
+ ],
3365
+ [
3366
+ "ĠB",
3367
+ "rit"
3368
+ ],
3369
+ [
3370
+ "ion",
3371
+ "s"
3372
+ ],
3373
+ [
3374
+ "a",
3375
+ "w"
3376
+ ],
3377
+ [
3378
+ "Ġc",
3379
+ "o"
3380
+ ],
3381
+ [
3382
+ "Ġf",
3383
+ "l"
3384
+ ],
3385
+ [
3386
+ "e",
3387
+ "e"
3388
+ ],
3389
+ [
3390
+ "ot",
3391
+ "h"
3392
+ ],
3393
+ [
3394
+ "a",
3395
+ "e"
3396
+ ],
3397
+ [
3398
+ "v",
3399
+ "el"
3400
+ ],
3401
+ [
3402
+ "Ġt",
3403
+ "ra"
3404
+ ],
3405
+ [
3406
+ "on",
3407
+ "s"
3408
+ ],
3409
+ [
3410
+ "an",
3411
+ "g"
3412
+ ],
3413
+ [
3414
+ "ic",
3415
+ "k"
3416
+ ],
3417
+ [
3418
+ "Ġas",
3419
+ "s"
3420
+ ],
3421
+ [
3422
+ "Ġat",
3423
+ "t"
3424
+ ],
3425
+ [
3426
+ "Ġ",
3427
+ "ra"
3428
+ ],
3429
+ [
3430
+ "os",
3431
+ "s"
3432
+ ],
3433
+ [
3434
+ "Ġsu",
3435
+ "b"
3436
+ ],
3437
+ [
3438
+ "Ġk",
3439
+ "n"
3440
+ ],
3441
+ [
3442
+ "Ġon",
3443
+ "ly"
3444
+ ],
3445
+ [
3446
+ "Ġag",
3447
+ "ain"
3448
+ ],
3449
+ [
3450
+ "w",
3451
+ "ay"
3452
+ ],
3453
+ [
3454
+ "00",
3455
+ "0"
3456
+ ],
3457
+ [
3458
+ "an",
3459
+ "s"
3460
+ ],
3461
+ [
3462
+ "Ġm",
3463
+ "e"
3464
+ ],
3465
+ [
3466
+ "Ġn",
3467
+ "um"
3468
+ ],
3469
+ [
3470
+ "Ġfor",
3471
+ "m"
3472
+ ],
3473
+ [
3474
+ "is",
3475
+ "s"
3476
+ ],
3477
+ [
3478
+ "Ġp",
3479
+ "ubl"
3480
+ ],
3481
+ [
3482
+ "n",
3483
+ "g"
3484
+ ],
3485
+ [
3486
+ "is",
3487
+ "hed"
3488
+ ],
3489
+ [
3490
+ "ar",
3491
+ "g"
3492
+ ],
3493
+ [
3494
+ "Ġre",
3495
+ "t"
3496
+ ],
3497
+ [
3498
+ "Ġre",
3499
+ "le"
3500
+ ],
3501
+ [
3502
+ "Ġw",
3503
+ "ould"
3504
+ ],
3505
+ [
3506
+ "e",
3507
+ "en"
3508
+ ],
3509
+ [
3510
+ "v",
3511
+ "e"
3512
+ ],
3513
+ [
3514
+ "Ġf",
3515
+ "our"
3516
+ ],
3517
+ [
3518
+ "ic",
3519
+ "t"
3520
+ ],
3521
+ [
3522
+ "Ġth",
3523
+ "ree"
3524
+ ],
3525
+ [
3526
+ "ers",
3527
+ "on"
3528
+ ],
3529
+ [
3530
+ "t",
3531
+ "le"
3532
+ ],
3533
+ [
3534
+ "Ġpro",
3535
+ "du"
3536
+ ],
3537
+ [
3538
+ "Ġm",
3539
+ "on"
3540
+ ],
3541
+ [
3542
+ "Ġte",
3543
+ "am"
3544
+ ],
3545
+ [
3546
+ "o",
3547
+ "ok"
3548
+ ],
3549
+ [
3550
+ "or",
3551
+ "th"
3552
+ ],
3553
+ [
3554
+ "ĠS",
3555
+ "he"
3556
+ ],
3557
+ [
3558
+ "Ġe",
3559
+ "nd"
3560
+ ],
3561
+ [
3562
+ "ar",
3563
+ "s"
3564
+ ],
3565
+ [
3566
+ "Ġbe",
3567
+ "t"
3568
+ ],
3569
+ [
3570
+ "v",
3571
+ "est"
3572
+ ],
3573
+ [
3574
+ "Ġb",
3575
+ "u"
3576
+ ],
3577
+ [
3578
+ "Ġsec",
3579
+ "ond"
3580
+ ],
3581
+ [
3582
+ "Ġth",
3583
+ "an"
3584
+ ],
3585
+ [
3586
+ "st",
3587
+ "e"
3588
+ ],
3589
+ [
3590
+ "ĠI",
3591
+ "s"
3592
+ ],
3593
+ [
3594
+ "ĠI",
3595
+ "nd"
3596
+ ],
3597
+ [
3598
+ "Ġbe",
3599
+ "ing"
3600
+ ],
3601
+ [
3602
+ "Ġde",
3603
+ "c"
3604
+ ],
3605
+ [
3606
+ "o",
3607
+ "od"
3608
+ ],
3609
+ [
3610
+ "Ġc",
3611
+ "an"
3612
+ ],
3613
+ [
3614
+ "en",
3615
+ "er"
3616
+ ],
3617
+ [
3618
+ "Ġth",
3619
+ "rough"
3620
+ ],
3621
+ [
3622
+ "Ġab",
3623
+ "out"
3624
+ ],
3625
+ [
3626
+ "Ġc",
3627
+ "ent"
3628
+ ],
3629
+ [
3630
+ "ct",
3631
+ "ed"
3632
+ ],
3633
+ [
3634
+ "Ġa",
3635
+ "pp"
3636
+ ],
3637
+ [
3638
+ "Ġwhe",
3639
+ "n"
3640
+ ],
3641
+ [
3642
+ "Ġl",
3643
+ "ater"
3644
+ ],
3645
+ [
3646
+ "ow",
3647
+ "er"
3648
+ ],
3649
+ [
3650
+ "ul",
3651
+ "l"
3652
+ ],
3653
+ [
3654
+ "on",
3655
+ "y"
3656
+ ],
3657
+ [
3658
+ "o",
3659
+ "le"
3660
+ ],
3661
+ [
3662
+ "el",
3663
+ "er"
3664
+ ],
3665
+ [
3666
+ "Ġa",
3667
+ "cc"
3668
+ ],
3669
+ [
3670
+ "Ġp",
3671
+ "e"
3672
+ ],
3673
+ [
3674
+ "ak",
3675
+ "e"
3676
+ ],
3677
+ [
3678
+ "i",
3679
+ "ke"
3680
+ ],
3681
+ [
3682
+ "il",
3683
+ "y"
3684
+ ],
3685
+ [
3686
+ "r",
3687
+ "ist"
3688
+ ],
3689
+ [
3690
+ "Ġa",
3691
+ "c"
3692
+ ],
3693
+ [
3694
+ "Ġin",
3695
+ "d"
3696
+ ],
3697
+ [
3698
+ "ĠWhe",
3699
+ "eler"
3700
+ ],
3701
+ [
3702
+ "ĠL",
3703
+ "e"
3704
+ ],
3705
+ [
3706
+ "ou",
3707
+ "th"
3708
+ ],
3709
+ [
3710
+ "ĠC",
3711
+ "om"
3712
+ ],
3713
+ [
3714
+ "us",
3715
+ "ic"
3716
+ ],
3717
+ [
3718
+ "ul",
3719
+ "ar"
3720
+ ],
3721
+ [
3722
+ "i",
3723
+ "ous"
3724
+ ],
3725
+ [
3726
+ "w",
3727
+ "een"
3728
+ ],
3729
+ [
3730
+ "Ġs",
3731
+ "ome"
3732
+ ],
3733
+ [
3734
+ "ur",
3735
+ "ch"
3736
+ ],
3737
+ [
3738
+ "e",
3739
+ "nd"
3740
+ ],
3741
+ [
3742
+ "is",
3743
+ "m"
3744
+ ],
3745
+ [
3746
+ "ch",
3747
+ "ae"
3748
+ ],
3749
+ [
3750
+ "ĠN",
3751
+ "ew"
3752
+ ],
3753
+ [
3754
+ "chae",
3755
+ "olog"
3756
+ ],
3757
+ [
3758
+ "a",
3759
+ "id"
3760
+ ],
3761
+ [
3762
+ "Ġw",
3763
+ "rit"
3764
+ ],
3765
+ [
3766
+ "al",
3767
+ "s"
3768
+ ],
3769
+ [
3770
+ "Ġd",
3771
+ "o"
3772
+ ],
3773
+ [
3774
+ "Ġsu",
3775
+ "ch"
3776
+ ],
3777
+ [
3778
+ "oll",
3779
+ "ow"
3780
+ ],
3781
+ [
3782
+ "al",
3783
+ "ly"
3784
+ ],
3785
+ [
3786
+ "t",
3787
+ "en"
3788
+ ],
3789
+ [
3790
+ "Ġa",
3791
+ "m"
3792
+ ],
3793
+ [
3794
+ "in",
3795
+ "s"
3796
+ ],
3797
+ [
3798
+ "Ġp",
3799
+ "ol"
3800
+ ],
3801
+ [
3802
+ "Ġm",
3803
+ "ade"
3804
+ ],
3805
+ [
3806
+ "if",
3807
+ "ic"
3808
+ ],
3809
+ [
3810
+ "Ġm",
3811
+ "et"
3812
+ ],
3813
+ [
3814
+ "Ġg",
3815
+ "ame"
3816
+ ],
3817
+ [
3818
+ "i",
3819
+ "el"
3820
+ ],
3821
+ [
3822
+ "Ġh",
3823
+ "ist"
3824
+ ],
3825
+ [
3826
+ "ut",
3827
+ "e"
3828
+ ],
3829
+ [
3830
+ "ĠG",
3831
+ "al"
3832
+ ],
3833
+ [
3834
+ "Ġwhe",
3835
+ "re"
3836
+ ],
3837
+ [
3838
+ "f",
3839
+ "ore"
3840
+ ],
3841
+ [
3842
+ "at",
3843
+ "ing"
3844
+ ],
3845
+ [
3846
+ "Ġre",
3847
+ "p"
3848
+ ],
3849
+ [
3850
+ "res",
3851
+ "ent"
3852
+ ],
3853
+ [
3854
+ "j",
3855
+ "ect"
3856
+ ],
3857
+ [
3858
+ "Ġs",
3859
+ "y"
3860
+ ],
3861
+ [
3862
+ "or",
3863
+ "ld"
3864
+ ],
3865
+ [
3866
+ "Ġp",
3867
+ "r"
3868
+ ],
3869
+ [
3870
+ "Ġb",
3871
+ "l"
3872
+ ],
3873
+ [
3874
+ "am",
3875
+ "p"
3876
+ ],
3877
+ [
3878
+ "i",
3879
+ "et"
3880
+ ],
3881
+ [
3882
+ "o",
3883
+ "b"
3884
+ ],
3885
+ [
3886
+ "Ġa",
3887
+ "p"
3888
+ ],
3889
+ [
3890
+ "th",
3891
+ "ough"
3892
+ ],
3893
+ [
3894
+ "ov",
3895
+ "e"
3896
+ ],
3897
+ [
3898
+ "ĠBrit",
3899
+ "ish"
3900
+ ],
3901
+ [
3902
+ "Ġbet",
3903
+ "ween"
3904
+ ],
3905
+ [
3906
+ "vest",
3907
+ "on"
3908
+ ],
3909
+ [
3910
+ "ĠGal",
3911
+ "veston"
3912
+ ],
3913
+ [
3914
+ "er",
3915
+ "man"
3916
+ ],
3917
+ [
3918
+ "ro",
3919
+ "w"
3920
+ ],
3921
+ [
3922
+ "Ġan",
3923
+ "t"
3924
+ ],
3925
+ [
3926
+ "Ġsh",
3927
+ "ip"
3928
+ ],
3929
+ [
3930
+ "ĠCh",
3931
+ "rist"
3932
+ ],
3933
+ [
3934
+ "a",
3935
+ "z"
3936
+ ],
3937
+ [
3938
+ "o",
3939
+ "ol"
3940
+ ],
3941
+ [
3942
+ "Ġthe",
3943
+ "re"
3944
+ ],
3945
+ [
3946
+ "Ġs",
3947
+ "ign"
3948
+ ],
3949
+ [
3950
+ "ĠB",
3951
+ "l"
3952
+ ],
3953
+ [
3954
+ "Ġs",
3955
+ "ur"
3956
+ ],
3957
+ [
3958
+ "is",
3959
+ "ed"
3960
+ ],
3961
+ [
3962
+ "i",
3963
+ "red"
3964
+ ],
3965
+ [
3966
+ "ĠY",
3967
+ "ork"
3968
+ ],
3969
+ [
3970
+ "9",
3971
+ "4"
3972
+ ],
3973
+ [
3974
+ "l",
3975
+ "ed"
3976
+ ],
3977
+ [
3978
+ "Ġc",
3979
+ "ity"
3980
+ ],
3981
+ [
3982
+ "ĠAl",
3983
+ "l"
3984
+ ],
3985
+ [
3986
+ "9",
3987
+ "8"
3988
+ ],
3989
+ [
3990
+ "u",
3991
+ "p"
3992
+ ],
3993
+ [
3994
+ "Ġch",
3995
+ "ar"
3996
+ ],
3997
+ [
3998
+ "Ġs",
3999
+ "ong"
4000
+ ],
4001
+ [
4002
+ "Ġc",
4003
+ "all"
4004
+ ],
4005
+ [
4006
+ "ĠG",
4007
+ "erman"
4008
+ ],
4009
+ [
4010
+ "Ġman",
4011
+ "y"
4012
+ ],
4013
+ [
4014
+ "Ġnum",
4015
+ "ber"
4016
+ ],
4017
+ [
4018
+ "Ġh",
4019
+ "igh"
4020
+ ],
4021
+ [
4022
+ "u",
4023
+ "g"
4024
+ ],
4025
+ [
4026
+ "ic",
4027
+ "s"
4028
+ ],
4029
+ [
4030
+ "ic",
4031
+ "an"
4032
+ ],
4033
+ [
4034
+ "Ġm",
4035
+ "in"
4036
+ ],
4037
+ [
4038
+ "Ġl",
4039
+ "oc"
4040
+ ],
4041
+ [
4042
+ "Ġn",
4043
+ "o"
4044
+ ],
4045
+ [
4046
+ "Ġwh",
4047
+ "ile"
4048
+ ],
4049
+ [
4050
+ "a",
4051
+ "ir"
4052
+ ],
4053
+ [
4054
+ "Ġ",
4055
+ "qu"
4056
+ ],
4057
+ [
4058
+ "Ġb",
4059
+ "oth"
4060
+ ],
4061
+ [
4062
+ "Ġe",
4063
+ "le"
4064
+ ],
4065
+ [
4066
+ "ran",
4067
+ "s"
4068
+ ],
4069
+ [
4070
+ "Ġsu",
4071
+ "pp"
4072
+ ],
4073
+ [
4074
+ "e",
4075
+ "ver"
4076
+ ],
4077
+ [
4078
+ "ĠT",
4079
+ "own"
4080
+ ],
4081
+ [
4082
+ "iv",
4083
+ "ers"
4084
+ ],
4085
+ [
4086
+ "if",
4087
+ "e"
4088
+ ],
4089
+ [
4090
+ "Ġle",
4091
+ "ad"
4092
+ ],
4093
+ [
4094
+ "Ġus",
4095
+ "ed"
4096
+ ],
4097
+ [
4098
+ "he",
4099
+ "s"
4100
+ ],
4101
+ [
4102
+ "iv",
4103
+ "ed"
4104
+ ],
4105
+ [
4106
+ "ver",
4107
+ "al"
4108
+ ],
4109
+ [
4110
+ "Ġthe",
4111
+ "n"
4112
+ ],
4113
+ [
4114
+ "Ġs",
4115
+ "o"
4116
+ ],
4117
+ [
4118
+ "Ġyear",
4119
+ "s"
4120
+ ],
4121
+ [
4122
+ "Ġgod",
4123
+ "s"
4124
+ ],
4125
+ [
4126
+ "g",
4127
+ "y"
4128
+ ],
4129
+ [
4130
+ "re",
4131
+ "n"
4132
+ ],
4133
+ [
4134
+ "Ġl",
4135
+ "ong"
4136
+ ],
4137
+ [
4138
+ "Ġdes",
4139
+ "c"
4140
+ ],
4141
+ [
4142
+ "9",
4143
+ "1"
4144
+ ],
4145
+ [
4146
+ "Ġb",
4147
+ "el"
4148
+ ],
4149
+ [
4150
+ "o",
4151
+ "h"
4152
+ ],
4153
+ [
4154
+ "vi",
4155
+ "ew"
4156
+ ],
4157
+ [
4158
+ "a",
4159
+ "use"
4160
+ ],
4161
+ [
4162
+ "al",
4163
+ "e"
4164
+ ],
4165
+ [
4166
+ "ro",
4167
+ "s"
4168
+ ],
4169
+ [
4170
+ "ot",
4171
+ "her"
4172
+ ],
4173
+ [
4174
+ "el",
4175
+ "f"
4176
+ ],
4177
+ [
4178
+ "n",
4179
+ "ing"
4180
+ ],
4181
+ [
4182
+ "r",
4183
+ "al"
4184
+ ],
4185
+ [
4186
+ "Ġf",
4187
+ "ollow"
4188
+ ],
4189
+ [
4190
+ "ĠUn",
4191
+ "ited"
4192
+ ],
4193
+ [
4194
+ "Ġd",
4195
+ "if"
4196
+ ],
4197
+ [
4198
+ "ĠA",
4199
+ "mer"
4200
+ ],
4201
+ [
4202
+ "ver",
4203
+ "y"
4204
+ ],
4205
+ [
4206
+ "u",
4207
+ "res"
4208
+ ],
4209
+ [
4210
+ "Ġs",
4211
+ "ch"
4212
+ ],
4213
+ [
4214
+ "Ġd",
4215
+ "ay"
4216
+ ],
4217
+ [
4218
+ "Ġ",
4219
+ "ent"
4220
+ ],
4221
+ [
4222
+ "Ġw",
4223
+ "ell"
4224
+ ],
4225
+ [
4226
+ "Ġm",
4227
+ "ain"
4228
+ ],
4229
+ [
4230
+ "ĠTh",
4231
+ "is"
4232
+ ],
4233
+ [
4234
+ "Ġt",
4235
+ "r"
4236
+ ],
4237
+ [
4238
+ "Ġde",
4239
+ "f"
4240
+ ],
4241
+ [
4242
+ "2",
4243
+ "0"
4244
+ ],
4245
+ [
4246
+ "Ġo",
4247
+ "b"
4248
+ ],
4249
+ [
4250
+ "Ġc",
4251
+ "re"
4252
+ ],
4253
+ [
4254
+ "ter",
4255
+ "n"
4256
+ ],
4257
+ [
4258
+ "t",
4259
+ "y"
4260
+ ],
4261
+ [
4262
+ "ĠC",
4263
+ "l"
4264
+ ],
4265
+ [
4266
+ "Ġe",
4267
+ "m"
4268
+ ],
4269
+ [
4270
+ "Ġbe",
4271
+ "fore"
4272
+ ],
4273
+ [
4274
+ "ist",
4275
+ "s"
4276
+ ],
4277
+ [
4278
+ "ĠM",
4279
+ "ar"
4280
+ ],
4281
+ [
4282
+ "ra",
4283
+ "ft"
4284
+ ],
4285
+ [
4286
+ "Ġbec",
4287
+ "ame"
4288
+ ],
4289
+ [
4290
+ "Ġthe",
4291
+ "se"
4292
+ ],
4293
+ [
4294
+ "em",
4295
+ "b"
4296
+ ],
4297
+ [
4298
+ "Ġper",
4299
+ "form"
4300
+ ],
4301
+ [
4302
+ "Ġagain",
4303
+ "st"
4304
+ ],
4305
+ [
4306
+ "a",
4307
+ "h"
4308
+ ],
4309
+ [
4310
+ "op",
4311
+ "le"
4312
+ ],
4313
+ [
4314
+ "iz",
4315
+ "ed"
4316
+ ],
4317
+ [
4318
+ "iel",
4319
+ "d"
4320
+ ],
4321
+ [
4322
+ "Ġap",
4323
+ "pe"
4324
+ ],
4325
+ [
4326
+ "st",
4327
+ "ru"
4328
+ ],
4329
+ [
4330
+ "Ġde",
4331
+ "p"
4332
+ ],
4333
+ [
4334
+ "3",
4335
+ "0"
4336
+ ],
4337
+ [
4338
+ "Ġo",
4339
+ "per"
4340
+ ],
4341
+ [
4342
+ "Ġp",
4343
+ "op"
4344
+ ],
4345
+ [
4346
+ "Ġkn",
4347
+ "own"
4348
+ ],
4349
+ [
4350
+ "ste",
4351
+ "in"
4352
+ ],
4353
+ [
4354
+ "i",
4355
+ "o"
4356
+ ],
4357
+ [
4358
+ "y",
4359
+ "s"
4360
+ ],
4361
+ [
4362
+ "Ġ",
4363
+ "Z"
4364
+ ],
4365
+ [
4366
+ "Ġc",
4367
+ "ar"
4368
+ ],
4369
+ [
4370
+ "Ġc",
4371
+ "ol"
4372
+ ],
4373
+ [
4374
+ "id",
4375
+ "ent"
4376
+ ],
4377
+ [
4378
+ "ow",
4379
+ "ever"
4380
+ ],
4381
+ [
4382
+ "ce",
4383
+ "pt"
4384
+ ],
4385
+ [
4386
+ "Ġrem",
4387
+ "ain"
4388
+ ],
4389
+ [
4390
+ "s",
4391
+ "on"
4392
+ ],
4393
+ [
4394
+ "Ġst",
4395
+ "ud"
4396
+ ],
4397
+ [
4398
+ "Ġinclud",
4399
+ "ing"
4400
+ ],
4401
+ [
4402
+ "Ġ",
4403
+ "%"
4404
+ ],
4405
+ [
4406
+ "ĠA",
4407
+ "nd"
4408
+ ],
4409
+ [
4410
+ "Ġor",
4411
+ "ig"
4412
+ ]
4413
+ ]
4414
+ }
4415
+ }
afmoe/AfmoeModel/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|begin_of_text|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 128,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
aimv2/Aimv2Model/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Aimv2Model"
4
+ ],
5
+ "dtype": "float32",
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "max_logit_scale": 100.0,
9
+ "model_type": "aimv2",
10
+ "projection_dim": 64,
11
+ "text_config": {
12
+ "attention_dropout": 0.1,
13
+ "dropout": 0.1,
14
+ "eos_token_id": 1023,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 32,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 37,
19
+ "max_position_embeddings": 25,
20
+ "mlp_bias": false,
21
+ "model_type": "aimv2_text_model",
22
+ "num_attention_heads": 4,
23
+ "num_hidden_layers": 2,
24
+ "projection_dim": 32,
25
+ "qkv_bias": false,
26
+ "rms_norm_eps": 1e-05,
27
+ "vocab_size": 1024
28
+ },
29
+ "transformers_version": "5.15.0.dev0",
30
+ "vision_config": {
31
+ "attention_dropout": 0.1,
32
+ "dropout": 0.1,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 32,
35
+ "image_size": 30,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 37,
38
+ "is_native": false,
39
+ "mlp_bias": false,
40
+ "model_type": "aimv2_vision_model",
41
+ "num_attention_heads": 4,
42
+ "num_channels": 3,
43
+ "num_hidden_layers": 2,
44
+ "patch_size": 2,
45
+ "projection_dim": 32,
46
+ "qkv_bias": false,
47
+ "rms_norm_eps": 1e-05,
48
+ "use_head": true
49
+ }
50
+ }
aimv2/Aimv2Model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278ecd0f717d2c8f924a7037e888209ff06482dfe897acc15a234fe1922a1442
3
+ size 323172
aimv2/Aimv2Model/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 30,
4
+ "width": 30
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 30
26
+ }
27
+ }
aimv2/Aimv2Model/tokenizer.json ADDED
@@ -0,0 +1,3735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<start_of_text>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<end_of_text>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": {
26
+ "type": "Sequence",
27
+ "normalizers": [
28
+ {
29
+ "type": "NFC"
30
+ },
31
+ {
32
+ "type": "Replace",
33
+ "pattern": {
34
+ "Regex": "\\s+"
35
+ },
36
+ "content": " "
37
+ },
38
+ {
39
+ "type": "Lowercase"
40
+ }
41
+ ]
42
+ },
43
+ "pre_tokenizer": {
44
+ "type": "Sequence",
45
+ "pretokenizers": [
46
+ {
47
+ "type": "Split",
48
+ "pattern": {
49
+ "Regex": "<\\|startoftext\\|>|<\\|endoftext\\|>|'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
50
+ },
51
+ "behavior": "Removed",
52
+ "invert": true
53
+ },
54
+ {
55
+ "type": "ByteLevel",
56
+ "add_prefix_space": false,
57
+ "trim_offsets": true,
58
+ "use_regex": true
59
+ }
60
+ ]
61
+ },
62
+ "post_processor": {
63
+ "type": "RobertaProcessing",
64
+ "sep": [
65
+ "<end_of_text>",
66
+ 1
67
+ ],
68
+ "cls": [
69
+ "<start_of_text>",
70
+ 0
71
+ ],
72
+ "trim_offsets": false,
73
+ "add_prefix_space": false
74
+ },
75
+ "decoder": {
76
+ "type": "ByteLevel",
77
+ "add_prefix_space": true,
78
+ "trim_offsets": true,
79
+ "use_regex": true
80
+ },
81
+ "model": {
82
+ "type": "BPE",
83
+ "dropout": null,
84
+ "unk_token": "<end_of_text>",
85
+ "continuing_subword_prefix": "",
86
+ "end_of_word_suffix": "</w>",
87
+ "fuse_unk": false,
88
+ "byte_fallback": false,
89
+ "ignore_merges": false,
90
+ "vocab": {
91
+ "<start_of_text>": 0,
92
+ "<end_of_text>": 1,
93
+ "!": 2,
94
+ "\"": 3,
95
+ "#": 4,
96
+ "$": 5,
97
+ "%": 6,
98
+ "&": 7,
99
+ "'": 8,
100
+ "(": 9,
101
+ ")": 10,
102
+ "*": 11,
103
+ "+": 12,
104
+ ",": 13,
105
+ "-": 14,
106
+ ".": 15,
107
+ "/": 16,
108
+ "0": 17,
109
+ "1": 18,
110
+ "2": 19,
111
+ "3": 20,
112
+ "4": 21,
113
+ "5": 22,
114
+ "6": 23,
115
+ "7": 24,
116
+ "8": 25,
117
+ "9": 26,
118
+ ":": 27,
119
+ ";": 28,
120
+ "<": 29,
121
+ "=": 30,
122
+ ">": 31,
123
+ "?": 32,
124
+ "@": 33,
125
+ "A": 34,
126
+ "B": 35,
127
+ "C": 36,
128
+ "D": 37,
129
+ "E": 38,
130
+ "F": 39,
131
+ "G": 40,
132
+ "H": 41,
133
+ "I": 42,
134
+ "J": 43,
135
+ "K": 44,
136
+ "L": 45,
137
+ "M": 46,
138
+ "N": 47,
139
+ "O": 48,
140
+ "P": 49,
141
+ "Q": 50,
142
+ "R": 51,
143
+ "S": 52,
144
+ "T": 53,
145
+ "U": 54,
146
+ "V": 55,
147
+ "W": 56,
148
+ "X": 57,
149
+ "Y": 58,
150
+ "Z": 59,
151
+ "[": 60,
152
+ "\\": 61,
153
+ "]": 62,
154
+ "^": 63,
155
+ "_": 64,
156
+ "`": 65,
157
+ "a": 66,
158
+ "b": 67,
159
+ "c": 68,
160
+ "d": 69,
161
+ "e": 70,
162
+ "f": 71,
163
+ "g": 72,
164
+ "h": 73,
165
+ "i": 74,
166
+ "j": 75,
167
+ "k": 76,
168
+ "l": 77,
169
+ "m": 78,
170
+ "n": 79,
171
+ "o": 80,
172
+ "p": 81,
173
+ "q": 82,
174
+ "r": 83,
175
+ "s": 84,
176
+ "t": 85,
177
+ "u": 86,
178
+ "v": 87,
179
+ "w": 88,
180
+ "x": 89,
181
+ "y": 90,
182
+ "z": 91,
183
+ "{": 92,
184
+ "|": 93,
185
+ "}": 94,
186
+ "~": 95,
187
+ "¡": 96,
188
+ "¢": 97,
189
+ "£": 98,
190
+ "¤": 99,
191
+ "¥": 100,
192
+ "¦": 101,
193
+ "§": 102,
194
+ "¨": 103,
195
+ "©": 104,
196
+ "ª": 105,
197
+ "«": 106,
198
+ "¬": 107,
199
+ "®": 108,
200
+ "¯": 109,
201
+ "°": 110,
202
+ "±": 111,
203
+ "²": 112,
204
+ "³": 113,
205
+ "´": 114,
206
+ "µ": 115,
207
+ "¶": 116,
208
+ "·": 117,
209
+ "¸": 118,
210
+ "¹": 119,
211
+ "º": 120,
212
+ "»": 121,
213
+ "¼": 122,
214
+ "½": 123,
215
+ "¾": 124,
216
+ "¿": 125,
217
+ "À": 126,
218
+ "Á": 127,
219
+ "Â": 128,
220
+ "Ã": 129,
221
+ "Ä": 130,
222
+ "Å": 131,
223
+ "Æ": 132,
224
+ "Ç": 133,
225
+ "È": 134,
226
+ "É": 135,
227
+ "Ê": 136,
228
+ "Ë": 137,
229
+ "Ì": 138,
230
+ "Í": 139,
231
+ "Î": 140,
232
+ "Ï": 141,
233
+ "Ð": 142,
234
+ "Ñ": 143,
235
+ "Ò": 144,
236
+ "Ó": 145,
237
+ "Ô": 146,
238
+ "Õ": 147,
239
+ "Ö": 148,
240
+ "×": 149,
241
+ "Ø": 150,
242
+ "Ù": 151,
243
+ "Ú": 152,
244
+ "Û": 153,
245
+ "Ü": 154,
246
+ "Ý": 155,
247
+ "Þ": 156,
248
+ "ß": 157,
249
+ "à": 158,
250
+ "á": 159,
251
+ "â": 160,
252
+ "ã": 161,
253
+ "ä": 162,
254
+ "å": 163,
255
+ "æ": 164,
256
+ "ç": 165,
257
+ "è": 166,
258
+ "é": 167,
259
+ "ê": 168,
260
+ "ë": 169,
261
+ "ì": 170,
262
+ "í": 171,
263
+ "î": 172,
264
+ "ï": 173,
265
+ "ð": 174,
266
+ "ñ": 175,
267
+ "ò": 176,
268
+ "ó": 177,
269
+ "ô": 178,
270
+ "õ": 179,
271
+ "ö": 180,
272
+ "÷": 181,
273
+ "ø": 182,
274
+ "ù": 183,
275
+ "ú": 184,
276
+ "û": 185,
277
+ "ü": 186,
278
+ "ý": 187,
279
+ "þ": 188,
280
+ "ÿ": 189,
281
+ "Ā": 190,
282
+ "ā": 191,
283
+ "Ă": 192,
284
+ "ă": 193,
285
+ "Ą": 194,
286
+ "ą": 195,
287
+ "Ć": 196,
288
+ "ć": 197,
289
+ "Ĉ": 198,
290
+ "ĉ": 199,
291
+ "Ċ": 200,
292
+ "ċ": 201,
293
+ "Č": 202,
294
+ "č": 203,
295
+ "Ď": 204,
296
+ "ď": 205,
297
+ "Đ": 206,
298
+ "đ": 207,
299
+ "Ē": 208,
300
+ "ē": 209,
301
+ "Ĕ": 210,
302
+ "ĕ": 211,
303
+ "Ė": 212,
304
+ "ė": 213,
305
+ "Ę": 214,
306
+ "ę": 215,
307
+ "Ě": 216,
308
+ "ě": 217,
309
+ "Ĝ": 218,
310
+ "ĝ": 219,
311
+ "Ğ": 220,
312
+ "ğ": 221,
313
+ "Ġ": 222,
314
+ "ġ": 223,
315
+ "Ģ": 224,
316
+ "ģ": 225,
317
+ "Ĥ": 226,
318
+ "ĥ": 227,
319
+ "Ħ": 228,
320
+ "ħ": 229,
321
+ "Ĩ": 230,
322
+ "ĩ": 231,
323
+ "Ī": 232,
324
+ "ī": 233,
325
+ "Ĭ": 234,
326
+ "ĭ": 235,
327
+ "Į": 236,
328
+ "į": 237,
329
+ "İ": 238,
330
+ "ı": 239,
331
+ "IJ": 240,
332
+ "ij": 241,
333
+ "Ĵ": 242,
334
+ "ĵ": 243,
335
+ "Ķ": 244,
336
+ "ķ": 245,
337
+ "ĸ": 246,
338
+ "Ĺ": 247,
339
+ "ĺ": 248,
340
+ "Ļ": 249,
341
+ "ļ": 250,
342
+ "Ľ": 251,
343
+ "ľ": 252,
344
+ "Ŀ": 253,
345
+ "ŀ": 254,
346
+ "Ł": 255,
347
+ "ł": 256,
348
+ "Ń": 257,
349
+ "l</w>": 258,
350
+ "e</w>": 259,
351
+ "s</w>": 260,
352
+ "d</w>": 261,
353
+ "y</w>": 262,
354
+ "h</w>": 263,
355
+ "n</w>": 264,
356
+ "a</w>": 265,
357
+ "t</w>": 266,
358
+ "p</w>": 267,
359
+ "r</w>": 268,
360
+ "x</w>": 269,
361
+ "c</w>": 270,
362
+ "i</w>": 271,
363
+ "g</w>": 272,
364
+ "m</w>": 273,
365
+ "u</w>": 274,
366
+ "o</w>": 275,
367
+ "k</w>": 276,
368
+ "z</w>": 277,
369
+ "ĭ</w>": 278,
370
+ "v</w>": 279,
371
+ "f</w>": 280,
372
+ "Ĺ</w>": 281,
373
+ "Ħ</w>": 282,
374
+ "w</w>": 283,
375
+ "¯</w>": 284,
376
+ "b</w>": 285,
377
+ "9</w>": 286,
378
+ "į</w>": 287,
379
+ "\"</w>": 288,
380
+ "!</w>": 289,
381
+ "ĵ</w>": 290,
382
+ "´</w>": 291,
383
+ "1</w>": 292,
384
+ "º</w>": 293,
385
+ "j</w>": 294,
386
+ "ĩ</w>": 295,
387
+ "/</w>": 296,
388
+ "ļ</w>": 297,
389
+ "£</w>": 298,
390
+ "%</w>": 299,
391
+ "ł</w>": 300,
392
+ "Ĥ</w>": 301,
393
+ "#</w>": 302,
394
+ "`</w>": 303,
395
+ "ª</w>": 304,
396
+ "©</w>": 305,
397
+ "ħ</w>": 306,
398
+ "Ń</w>": 307,
399
+ "@</w>": 308,
400
+ "-</w>": 309,
401
+ ".</w>": 310,
402
+ "?</w>": 311,
403
+ "Ĵ</w>": 312,
404
+ "¹</w>": 313,
405
+ "İ</w>": 314,
406
+ "(</w>": 315,
407
+ "$</w>": 316,
408
+ "¢</w>": 317,
409
+ "±</w>": 318,
410
+ "·</w>": 319,
411
+ "q</w>": 320,
412
+ "¤</w>": 321,
413
+ "'</w>": 322,
414
+ "³</w>": 323,
415
+ "ĺ</w>": 324,
416
+ "Ĭ</w>": 325,
417
+ "4</w>": 326,
418
+ "½</w>": 327,
419
+ "ķ</w>": 328,
420
+ ",</w>": 329,
421
+ "]</w>": 330,
422
+ "ŀ</w>": 331,
423
+ "°</w>": 332,
424
+ "=</w>": 333,
425
+ "ģ</w>": 334,
426
+ "5</w>": 335,
427
+ "§</w>": 336,
428
+ "Į</w>": 337,
429
+ "&</w>": 338,
430
+ "^</w>": 339,
431
+ "¶</w>": 340,
432
+ "²</w>": 341,
433
+ "ľ</w>": 342,
434
+ "3</w>": 343,
435
+ "2</w>": 344,
436
+ "Ľ</w>": 345,
437
+ "Ķ</w>": 346,
438
+ "¾</w>": 347,
439
+ "ī</w>": 348,
440
+ ")</w>": 349,
441
+ "0</w>": 350,
442
+ "8</w>": 351,
443
+ "¡</w>": 352,
444
+ "IJ</w>": 353,
445
+ "[</w>": 354,
446
+ "¨</w>": 355,
447
+ "¦</w>": 356,
448
+ "+</w>": 357,
449
+ "></w>": 358,
450
+ "~</w>": 359,
451
+ "<</w>": 360,
452
+ "*</w>": 361,
453
+ "6</w>": 362,
454
+ ":</w>": 363,
455
+ "7</w>": 364,
456
+ "Ŀ</w>": 365,
457
+ "Ī</w>": 366,
458
+ ";</w>": 367,
459
+ "µ</w>": 368,
460
+ "Ļ</w>": 369,
461
+ "th": 370,
462
+ "the</w>": 371,
463
+ "in": 372,
464
+ "an": 373,
465
+ "ed</w>": 374,
466
+ "er": 375,
467
+ "re": 376,
468
+ "ti": 377,
469
+ "ar": 378,
470
+ "or": 379,
471
+ "on": 380,
472
+ "of</w>": 381,
473
+ "en": 382,
474
+ "and</w>": 383,
475
+ "er</w>": 384,
476
+ "on</w>": 385,
477
+ "in</w>": 386,
478
+ "st": 387,
479
+ "al": 388,
480
+ "ing</w>": 389,
481
+ "it": 390,
482
+ "ro": 391,
483
+ "as</w>": 392,
484
+ "to</w>": 393,
485
+ "at": 394,
486
+ "es</w>": 395,
487
+ "hi": 396,
488
+ "ou": 397,
489
+ "al</w>": 398,
490
+ "an</w>": 399,
491
+ "ac": 400,
492
+ "at</w>": 401,
493
+ "li": 402,
494
+ "si": 403,
495
+ "ri": 404,
496
+ "el": 405,
497
+ "or</w>": 406,
498
+ "as": 407,
499
+ "de": 408,
500
+ "ur": 409,
501
+ "co": 410,
502
+ "am": 411,
503
+ "di": 412,
504
+ "ch": 413,
505
+ "was</w>": 414,
506
+ "tion</w>": 415,
507
+ "le": 416,
508
+ "st</w>": 417,
509
+ "ly</w>": 418,
510
+ "se": 419,
511
+ "lo": 420,
512
+ "un": 421,
513
+ "-@</w>": 422,
514
+ "@-@</w>": 423,
515
+ "is</w>": 424,
516
+ "be": 425,
517
+ "fi": 426,
518
+ "en</w>": 427,
519
+ "la": 428,
520
+ "ra": 429,
521
+ "le</w>": 430,
522
+ "con": 431,
523
+ "sh": 432,
524
+ "po": 433,
525
+ "that</w>": 434,
526
+ "wit": 435,
527
+ "vi": 436,
528
+ "for</w>": 437,
529
+ "with</w>": 438,
530
+ "ch</w>": 439,
531
+ "em": 440,
532
+ "ma": 441,
533
+ "'s</w>": 442,
534
+ "su": 443,
535
+ "ts</w>": 444,
536
+ "ve</w>": 445,
537
+ "by</w>": 446,
538
+ "ent</w>": 447,
539
+ "the": 448,
540
+ "ha": 449,
541
+ "ci": 450,
542
+ "pro": 451,
543
+ "ere</w>": 452,
544
+ "com": 453,
545
+ "ag": 454,
546
+ "ce</w>": 455,
547
+ "bu": 456,
548
+ "il": 457,
549
+ "no": 458,
550
+ "wh": 459,
551
+ "is": 460,
552
+ "sp": 461,
553
+ "ne": 462,
554
+ "ol": 463,
555
+ "ca": 464,
556
+ "ted</w>": 465,
557
+ "it</w>": 466,
558
+ "ers</w>": 467,
559
+ "tion": 468,
560
+ "he</w>": 469,
561
+ "se</w>": 470,
562
+ "gh": 471,
563
+ "for": 472,
564
+ "his</w>": 473,
565
+ "ru": 474,
566
+ "th</w>": 475,
567
+ "ver": 476,
568
+ "ad": 477,
569
+ "to": 478,
570
+ "mo": 479,
571
+ "ex": 480,
572
+ "fro": 481,
573
+ "from</w>": 482,
574
+ "ab": 483,
575
+ "whi": 484,
576
+ "per": 485,
577
+ "cu": 486,
578
+ "ea": 487,
579
+ "ds</w>": 488,
580
+ "were</w>": 489,
581
+ "ic": 490,
582
+ "om": 491,
583
+ "ap": 492,
584
+ "ity</w>": 493,
585
+ "ation</w>": 494,
586
+ "ter</w>": 495,
587
+ "pre": 496,
588
+ "oun": 497,
589
+ "ai": 498,
590
+ "fe": 499,
591
+ "lu": 500,
592
+ "ter": 501,
593
+ "ated</w>": 502,
594
+ "de</w>": 503,
595
+ "du": 504,
596
+ "go": 505,
597
+ "bo": 506,
598
+ "all</w>": 507,
599
+ "we": 508,
600
+ "ate</w>": 509,
601
+ "tim": 510,
602
+ "rec": 511,
603
+ "are</w>": 512,
604
+ "qu": 513,
605
+ "ther</w>": 514,
606
+ "man": 515,
607
+ "ding</w>": 516,
608
+ "me": 517,
609
+ "op": 518,
610
+ "gu": 519,
611
+ "par": 520,
612
+ "tr": 521,
613
+ "one</w>": 522,
614
+ "which</w>": 523,
615
+ "gi": 524,
616
+ "ec": 525,
617
+ "âĢ": 526,
618
+ "ded</w>": 527,
619
+ "ss</w>": 528,
620
+ "por": 529,
621
+ "ame</w>": 530,
622
+ "had</w>": 531,
623
+ "wor": 532,
624
+ "af": 533,
625
+ "der": 534,
626
+ "ver</w>": 535,
627
+ "ing": 536,
628
+ "sc": 537,
629
+ "ear": 538,
630
+ "be</w>": 539,
631
+ "ho": 540,
632
+ "so</w>": 541,
633
+ "tions</w>": 542,
634
+ "ta": 543,
635
+ "ber</w>": 544,
636
+ "ld</w>": 545,
637
+ "wa": 546,
638
+ "mu": 547,
639
+ "ni": 548,
640
+ "sed</w>": 549,
641
+ "mar": 550,
642
+ "tur": 551,
643
+ "ally</w>": 552,
644
+ "of": 553,
645
+ "pu": 554,
646
+ "ght</w>": 555,
647
+ "shi": 556,
648
+ "mi": 557,
649
+ "tw": 558,
650
+ "est": 559,
651
+ "out</w>": 560,
652
+ "its</w>": 561,
653
+ "gh</w>": 562,
654
+ "fir": 563,
655
+ "her</w>": 564,
656
+ "ir</w>": 565,
657
+ "um": 566,
658
+ "ce": 567,
659
+ "pla": 568,
660
+ "this</w>": 569,
661
+ "wn</w>": 570,
662
+ "au": 571,
663
+ "rou": 572,
664
+ "pl": 573,
665
+ "she</w>": 574,
666
+ "âĢĵ</w>": 575,
667
+ "ke</w>": 576,
668
+ "inc": 577,
669
+ "im": 578,
670
+ "also</w>": 579,
671
+ "der</w>": 580,
672
+ "ge</w>": 581,
673
+ "na": 582,
674
+ "ine</w>": 583,
675
+ "their</w>": 584,
676
+ "ong</w>": 585,
677
+ "pe": 586,
678
+ "ser": 587,
679
+ "ved</w>": 588,
680
+ "ary</w>": 589,
681
+ "sen": 590,
682
+ "ment</w>": 591,
683
+ "fin": 592,
684
+ "has</w>": 593,
685
+ "ting</w>": 594,
686
+ "do": 595,
687
+ "sh</w>": 596,
688
+ "not</w>": 597,
689
+ "te</w>": 598,
690
+ "ran": 599,
691
+ "sa": 600,
692
+ "mor": 601,
693
+ "ori": 602,
694
+ "min": 603,
695
+ "led</w>": 604,
696
+ ".@</w>": 605,
697
+ "@.@</w>": 606,
698
+ "but</w>": 607,
699
+ "after</w>": 608,
700
+ "two</w>": 609,
701
+ "first</w>": 610,
702
+ "sti": 611,
703
+ "so": 612,
704
+ "ir": 613,
705
+ "fer": 614,
706
+ "other</w>": 615,
707
+ "ty</w>": 616,
708
+ "ents</w>": 617,
709
+ "they</w>": 618,
710
+ "comm": 619,
711
+ "tu": 620,
712
+ "wi": 621,
713
+ "ge": 622,
714
+ "te": 623,
715
+ "have</w>": 624,
716
+ "ned</w>": 625,
717
+ "ten": 626,
718
+ "ss": 627,
719
+ "ould</w>": 628,
720
+ "who</w>": 629,
721
+ "pi": 630,
722
+ "da": 631,
723
+ "ast</w>": 632,
724
+ "ties</w>": 633,
725
+ "lar": 634,
726
+ "son</w>": 635,
727
+ "war": 636,
728
+ "sho": 637,
729
+ "ke": 638,
730
+ "char": 639,
731
+ "been</w>": 640,
732
+ "our": 641,
733
+ ",@</w>": 642,
734
+ "@,@</w>": 643,
735
+ "man</w>": 644,
736
+ "new</w>": 645,
737
+ "ks</w>": 646,
738
+ "mon": 647,
739
+ "sion</w>": 648,
740
+ "gen": 649,
741
+ "ory</w>": 650,
742
+ "uring</w>": 651,
743
+ "ar</w>": 652,
744
+ "gre": 653,
745
+ "ater</w>": 654,
746
+ "low": 655,
747
+ "ant</w>": 656,
748
+ "sig": 657,
749
+ "ely</w>": 658,
750
+ "ft</w>": 659,
751
+ "cont": 660,
752
+ "fu": 661,
753
+ "rit": 662,
754
+ "age</w>": 663,
755
+ "ous</w>": 664,
756
+ "cre": 665,
757
+ "cen": 666,
758
+ "ste": 667,
759
+ "el</w>": 668,
760
+ "duc": 669,
761
+ "us</w>": 670,
762
+ "poli": 671,
763
+ "tional</w>": 672,
764
+ "ome</w>": 673,
765
+ "time</w>": 674,
766
+ "tra": 675,
767
+ "ali": 676,
768
+ "play": 677,
769
+ "king</w>": 678,
770
+ "spe": 679,
771
+ "our</w>": 680,
772
+ "oc": 681,
773
+ "ited</w>": 682,
774
+ "fil": 683,
775
+ "air": 684,
776
+ "bri": 685,
777
+ "als</w>": 686,
778
+ "ev": 687,
779
+ "oo": 688,
780
+ "ari": 689,
781
+ "inter": 690,
782
+ "tic": 691,
783
+ "uni": 692,
784
+ "gra": 693,
785
+ "lar</w>": 694,
786
+ "seas": 695,
787
+ "during</w>": 696,
788
+ "stru": 697,
789
+ "res</w>": 698,
790
+ "nor": 699,
791
+ "pp": 700,
792
+ "jo": 701,
793
+ "thou": 702,
794
+ "ember</w>": 703,
795
+ "land</w>": 704,
796
+ "ord": 705,
797
+ "ck</w>": 706,
798
+ "ite</w>": 707,
799
+ "inclu": 708,
800
+ "ance</w>": 709,
801
+ "str": 710,
802
+ "pri": 711,
803
+ "ure</w>": 712,
804
+ "tive</w>": 713,
805
+ "att": 714,
806
+ "ree</w>": 715,
807
+ "ack</w>": 716,
808
+ "col": 717,
809
+ "cul": 718,
810
+ "more</w>": 719,
811
+ "bli": 720,
812
+ "gro": 721,
813
+ "ased</w>": 722,
814
+ "ps</w>": 723,
815
+ "than</w>": 724,
816
+ "form": 725,
817
+ "yp": 726,
818
+ "comp": 727,
819
+ "recor": 728,
820
+ "cor": 729,
821
+ "ell</w>": 730,
822
+ "most</w>": 731,
823
+ "ates</w>": 732,
824
+ "ins</w>": 733,
825
+ "ined</w>": 734,
826
+ "chi": 735,
827
+ "publi": 736,
828
+ "way</w>": 737,
829
+ "et</w>": 738,
830
+ "car": 739,
831
+ "les</w>": 740,
832
+ "ad</w>": 741,
833
+ "ces</w>": 742,
834
+ "sch": 743,
835
+ "speci": 744,
836
+ "ons</w>": 745,
837
+ "ence</w>": 746,
838
+ "albu": 747,
839
+ "ves</w>": 748,
840
+ "ear</w>": 749,
841
+ "ren": 750,
842
+ "cha": 751,
843
+ "ship</w>": 752,
844
+ "ju": 753,
845
+ "ound</w>": 754,
846
+ "old</w>": 755,
847
+ "ked</w>": 756,
848
+ "and": 757,
849
+ "ace</w>": 758,
850
+ "season</w>": 759,
851
+ "sel": 760,
852
+ "able</w>": 761,
853
+ "indi": 762,
854
+ "ph": 763,
855
+ "tri": 764,
856
+ "ei": 765,
857
+ "city</w>": 766,
858
+ "cau": 767,
859
+ "mil": 768,
860
+ "bi": 769,
861
+ "tly</w>": 770,
862
+ "into</w>": 771,
863
+ "cl": 772,
864
+ "red</w>": 773,
865
+ "ls</w>": 774,
866
+ "sou": 775,
867
+ "ase</w>": 776,
868
+ "ings</w>": 777,
869
+ "ving</w>": 778,
870
+ "ach": 779,
871
+ "sy": 780,
872
+ "when</w>": 781,
873
+ "olo": 782,
874
+ "over</w>": 783,
875
+ "hist": 784,
876
+ "though</w>": 785,
877
+ "end</w>": 786,
878
+ "tic</w>": 787,
879
+ "dis": 788,
880
+ "secon": 789,
881
+ "can": 790,
882
+ "sur": 791,
883
+ "only</w>": 792,
884
+ "may</w>": 793,
885
+ "ordan</w>": 794,
886
+ "coun": 795,
887
+ "jordan</w>": 796,
888
+ "ms</w>": 797,
889
+ "ans</w>": 798,
890
+ "album</w>": 799,
891
+ "ern</w>": 800,
892
+ "ble</w>": 801,
893
+ "re</w>": 802,
894
+ "wn": 803,
895
+ "ach</w>": 804,
896
+ "ames</w>": 805,
897
+ "ok</w>": 806,
898
+ "ys</w>": 807,
899
+ "up</w>": 808,
900
+ "there</w>": 809,
901
+ "sub": 810,
902
+ "eg": 811,
903
+ "num": 812,
904
+ "many</w>": 813,
905
+ "three</w>": 814,
906
+ "gin": 815,
907
+ "rele": 816,
908
+ "shed</w>": 817,
909
+ "aga": 818,
910
+ "gal": 819,
911
+ "kno": 820,
912
+ "od</w>": 821,
913
+ "while</w>": 822,
914
+ "year</w>": 823,
915
+ "ors</w>": 824,
916
+ "ning</w>": 825,
917
+ "pa": 826,
918
+ "later</w>": 827,
919
+ "ve": 828,
920
+ "no</w>": 829,
921
+ "throu": 830,
922
+ "ying</w>": 831,
923
+ "emp": 832,
924
+ "ations</w>": 833,
925
+ "ic</w>": 834,
926
+ "vie": 835,
927
+ "whe": 836,
928
+ "ssi": 837,
929
+ "came</w>": 838,
930
+ "sic</w>": 839,
931
+ "fa": 840,
932
+ "bet": 841,
933
+ "war</w>": 842,
934
+ "bro": 843,
935
+ "would</w>": 844,
936
+ "some</w>": 845,
937
+ "ll</w>": 846,
938
+ "dev": 847,
939
+ "ical</w>": 848,
940
+ "sk": 849,
941
+ "produc": 850,
942
+ "port</w>": 851,
943
+ "scri": 852,
944
+ "buil": 853,
945
+ "bar": 854,
946
+ "game</w>": 855,
947
+ "film</w>": 856,
948
+ "ba": 857,
949
+ "tho": 858,
950
+ "loc": 859,
951
+ "being</w>": 860,
952
+ "these</w>": 861,
953
+ "about</w>": 862,
954
+ "soci": 863,
955
+ "sing</w>": 864,
956
+ "lan": 865,
957
+ "tre": 866,
958
+ "ten</w>": 867,
959
+ "writ": 868,
960
+ "fol": 869,
961
+ "ard</w>": 870,
962
+ "ue</w>": 871,
963
+ "eam</w>": 872,
964
+ "sts</w>": 873,
965
+ "him</w>": 874,
966
+ "app": 875,
967
+ "ger": 876,
968
+ "them</w>": 877,
969
+ "struc": 878,
970
+ "offi": 879,
971
+ "my</w>": 880,
972
+ "ani": 881,
973
+ "day</w>": 882,
974
+ "dy</w>": 883,
975
+ "he": 884,
976
+ "um</w>": 885,
977
+ "stri": 886,
978
+ "stu": 887,
979
+ "ele": 888,
980
+ "wheel": 889,
981
+ "cra": 890,
982
+ "second</w>": 891,
983
+ "ong": 892,
984
+ "side</w>": 893,
985
+ "such</w>": 894,
986
+ "team</w>": 895,
987
+ "ating</w>": 896,
988
+ "can</w>": 897,
989
+ "fac": 898,
990
+ "mis": 899,
991
+ "wheeler</w>": 900,
992
+ "den": 901,
993
+ "me</w>": 902,
994
+ "cri": 903,
995
+ "chri": 904,
996
+ "ween</w>": 905,
997
+ "chae": 906,
998
+ "ga": 907,
999
+ "ling</w>": 908,
1000
+ "ses</w>": 909,
1001
+ "between</w>": 910,
1002
+ "mat": 911,
1003
+ "vest": 912,
1004
+ "poin": 913,
1005
+ "gener": 914,
1006
+ "cal": 915,
1007
+ "wil": 916,
1008
+ "tish</w>": 917,
1009
+ "archae": 918,
1010
+ "ears</w>": 919,
1011
+ "archaeolo": 920,
1012
+ "jec": 921,
1013
+ "tal</w>": 922,
1014
+ "und</w>": 923,
1015
+ "sin": 924,
1016
+ "ven": 925,
1017
+ "made</w>": 926,
1018
+ "sul": 927,
1019
+ "ture</w>": 928,
1020
+ "oper": 929,
1021
+ "ven</w>": 930,
1022
+ "ws</w>": 931,
1023
+ "where</w>": 932,
1024
+ "ron": 933,
1025
+ "consi": 934,
1026
+ "four</w>": 935,
1027
+ "ton</w>": 936,
1028
+ "ob": 937,
1029
+ "wer</w>": 938,
1030
+ "sever": 939,
1031
+ "under</w>": 940,
1032
+ "work</w>": 941,
1033
+ "amer": 942,
1034
+ "cap": 943,
1035
+ "national</w>": 944,
1036
+ "with": 945,
1037
+ "fore</w>": 946,
1038
+ "then</w>": 947,
1039
+ "although</w>": 948,
1040
+ "sm": 949,
1041
+ "ony</w>": 950,
1042
+ "eld</w>": 951,
1043
+ "chur": 952,
1044
+ "british</w>": 953,
1045
+ "galvest": 954,
1046
+ "both</w>": 955,
1047
+ "ber": 956,
1048
+ "sted</w>": 957,
1049
+ "direc": 958,
1050
+ "galveston</w>": 959,
1051
+ "fe</w>": 960,
1052
+ "well</w>": 961,
1053
+ "dre": 962,
1054
+ "yor": 963,
1055
+ "nov": 964,
1056
+ "lit": 965,
1057
+ "tro": 966,
1058
+ "descri": 967,
1059
+ "cation</w>": 968,
1060
+ "aid</w>": 969,
1061
+ "tran": 970,
1062
+ "ini": 971,
1063
+ "state</w>": 972,
1064
+ "peri": 973,
1065
+ "des</w>": 974,
1066
+ "est</w>": 975,
1067
+ "hea": 976,
1068
+ "pen": 977,
1069
+ "years</w>": 978,
1070
+ "world</w>": 979,
1071
+ "ies</w>": 980,
1072
+ "used</w>": 981,
1073
+ "gods</w>": 982,
1074
+ "ters</w>": 983,
1075
+ "dif": 984,
1076
+ "follow": 985,
1077
+ "are": 986,
1078
+ "es": 987,
1079
+ "gan</w>": 988,
1080
+ "star": 989,
1081
+ "like</w>": 990,
1082
+ "early</w>": 991,
1083
+ "men": 992,
1084
+ "sing": 993,
1085
+ "bor": 994,
1086
+ "tor</w>": 995,
1087
+ "music</w>": 996,
1088
+ "clas": 997,
1089
+ "several</w>": 998,
1090
+ "united</w>": 999,
1091
+ "number</w>": 1000,
1092
+ "church</w>": 1001,
1093
+ "york</w>": 1002,
1094
+ "cur": 1003,
1095
+ "clo": 1004,
1096
+ "ang": 1005,
1097
+ "resp": 1006,
1098
+ "ami": 1007,
1099
+ "mem": 1008,
1100
+ "clu": 1009,
1101
+ "part</w>": 1010,
1102
+ "ced</w>": 1011,
1103
+ "cer": 1012,
1104
+ "je": 1013,
1105
+ "tru": 1014,
1106
+ "eng": 1015,
1107
+ "before</w>": 1016,
1108
+ "known</w>": 1017,
1109
+ "americ": 1018,
1110
+ "long</w>": 1019,
1111
+ "nam": 1020,
1112
+ "stan": 1021,
1113
+ "ster</w>": 1022,
1114
+ "ale</w>": 1023
1115
+ },
1116
+ "merges": [
1117
+ [
1118
+ "t",
1119
+ "h"
1120
+ ],
1121
+ [
1122
+ "th",
1123
+ "e</w>"
1124
+ ],
1125
+ [
1126
+ "i",
1127
+ "n"
1128
+ ],
1129
+ [
1130
+ "a",
1131
+ "n"
1132
+ ],
1133
+ [
1134
+ "e",
1135
+ "d</w>"
1136
+ ],
1137
+ [
1138
+ "e",
1139
+ "r"
1140
+ ],
1141
+ [
1142
+ "r",
1143
+ "e"
1144
+ ],
1145
+ [
1146
+ "t",
1147
+ "i"
1148
+ ],
1149
+ [
1150
+ "a",
1151
+ "r"
1152
+ ],
1153
+ [
1154
+ "o",
1155
+ "r"
1156
+ ],
1157
+ [
1158
+ "o",
1159
+ "n"
1160
+ ],
1161
+ [
1162
+ "o",
1163
+ "f</w>"
1164
+ ],
1165
+ [
1166
+ "e",
1167
+ "n"
1168
+ ],
1169
+ [
1170
+ "an",
1171
+ "d</w>"
1172
+ ],
1173
+ [
1174
+ "e",
1175
+ "r</w>"
1176
+ ],
1177
+ [
1178
+ "o",
1179
+ "n</w>"
1180
+ ],
1181
+ [
1182
+ "i",
1183
+ "n</w>"
1184
+ ],
1185
+ [
1186
+ "s",
1187
+ "t"
1188
+ ],
1189
+ [
1190
+ "a",
1191
+ "l"
1192
+ ],
1193
+ [
1194
+ "in",
1195
+ "g</w>"
1196
+ ],
1197
+ [
1198
+ "i",
1199
+ "t"
1200
+ ],
1201
+ [
1202
+ "r",
1203
+ "o"
1204
+ ],
1205
+ [
1206
+ "a",
1207
+ "s</w>"
1208
+ ],
1209
+ [
1210
+ "t",
1211
+ "o</w>"
1212
+ ],
1213
+ [
1214
+ "a",
1215
+ "t"
1216
+ ],
1217
+ [
1218
+ "e",
1219
+ "s</w>"
1220
+ ],
1221
+ [
1222
+ "h",
1223
+ "i"
1224
+ ],
1225
+ [
1226
+ "o",
1227
+ "u"
1228
+ ],
1229
+ [
1230
+ "a",
1231
+ "l</w>"
1232
+ ],
1233
+ [
1234
+ "a",
1235
+ "n</w>"
1236
+ ],
1237
+ [
1238
+ "a",
1239
+ "c"
1240
+ ],
1241
+ [
1242
+ "a",
1243
+ "t</w>"
1244
+ ],
1245
+ [
1246
+ "l",
1247
+ "i"
1248
+ ],
1249
+ [
1250
+ "s",
1251
+ "i"
1252
+ ],
1253
+ [
1254
+ "r",
1255
+ "i"
1256
+ ],
1257
+ [
1258
+ "e",
1259
+ "l"
1260
+ ],
1261
+ [
1262
+ "o",
1263
+ "r</w>"
1264
+ ],
1265
+ [
1266
+ "a",
1267
+ "s"
1268
+ ],
1269
+ [
1270
+ "d",
1271
+ "e"
1272
+ ],
1273
+ [
1274
+ "u",
1275
+ "r"
1276
+ ],
1277
+ [
1278
+ "c",
1279
+ "o"
1280
+ ],
1281
+ [
1282
+ "a",
1283
+ "m"
1284
+ ],
1285
+ [
1286
+ "d",
1287
+ "i"
1288
+ ],
1289
+ [
1290
+ "c",
1291
+ "h"
1292
+ ],
1293
+ [
1294
+ "w",
1295
+ "as</w>"
1296
+ ],
1297
+ [
1298
+ "ti",
1299
+ "on</w>"
1300
+ ],
1301
+ [
1302
+ "l",
1303
+ "e"
1304
+ ],
1305
+ [
1306
+ "s",
1307
+ "t</w>"
1308
+ ],
1309
+ [
1310
+ "l",
1311
+ "y</w>"
1312
+ ],
1313
+ [
1314
+ "s",
1315
+ "e"
1316
+ ],
1317
+ [
1318
+ "l",
1319
+ "o"
1320
+ ],
1321
+ [
1322
+ "u",
1323
+ "n"
1324
+ ],
1325
+ [
1326
+ "-",
1327
+ "@</w>"
1328
+ ],
1329
+ [
1330
+ "@",
1331
+ "-@</w>"
1332
+ ],
1333
+ [
1334
+ "i",
1335
+ "s</w>"
1336
+ ],
1337
+ [
1338
+ "b",
1339
+ "e"
1340
+ ],
1341
+ [
1342
+ "f",
1343
+ "i"
1344
+ ],
1345
+ [
1346
+ "e",
1347
+ "n</w>"
1348
+ ],
1349
+ [
1350
+ "l",
1351
+ "a"
1352
+ ],
1353
+ [
1354
+ "r",
1355
+ "a"
1356
+ ],
1357
+ [
1358
+ "l",
1359
+ "e</w>"
1360
+ ],
1361
+ [
1362
+ "c",
1363
+ "on"
1364
+ ],
1365
+ [
1366
+ "s",
1367
+ "h"
1368
+ ],
1369
+ [
1370
+ "p",
1371
+ "o"
1372
+ ],
1373
+ [
1374
+ "th",
1375
+ "at</w>"
1376
+ ],
1377
+ [
1378
+ "w",
1379
+ "it"
1380
+ ],
1381
+ [
1382
+ "v",
1383
+ "i"
1384
+ ],
1385
+ [
1386
+ "f",
1387
+ "or</w>"
1388
+ ],
1389
+ [
1390
+ "wit",
1391
+ "h</w>"
1392
+ ],
1393
+ [
1394
+ "c",
1395
+ "h</w>"
1396
+ ],
1397
+ [
1398
+ "e",
1399
+ "m"
1400
+ ],
1401
+ [
1402
+ "m",
1403
+ "a"
1404
+ ],
1405
+ [
1406
+ "'",
1407
+ "s</w>"
1408
+ ],
1409
+ [
1410
+ "s",
1411
+ "u"
1412
+ ],
1413
+ [
1414
+ "t",
1415
+ "s</w>"
1416
+ ],
1417
+ [
1418
+ "v",
1419
+ "e</w>"
1420
+ ],
1421
+ [
1422
+ "b",
1423
+ "y</w>"
1424
+ ],
1425
+ [
1426
+ "en",
1427
+ "t</w>"
1428
+ ],
1429
+ [
1430
+ "th",
1431
+ "e"
1432
+ ],
1433
+ [
1434
+ "h",
1435
+ "a"
1436
+ ],
1437
+ [
1438
+ "c",
1439
+ "i"
1440
+ ],
1441
+ [
1442
+ "p",
1443
+ "ro"
1444
+ ],
1445
+ [
1446
+ "er",
1447
+ "e</w>"
1448
+ ],
1449
+ [
1450
+ "co",
1451
+ "m"
1452
+ ],
1453
+ [
1454
+ "a",
1455
+ "g"
1456
+ ],
1457
+ [
1458
+ "c",
1459
+ "e</w>"
1460
+ ],
1461
+ [
1462
+ "b",
1463
+ "u"
1464
+ ],
1465
+ [
1466
+ "i",
1467
+ "l"
1468
+ ],
1469
+ [
1470
+ "n",
1471
+ "o"
1472
+ ],
1473
+ [
1474
+ "w",
1475
+ "h"
1476
+ ],
1477
+ [
1478
+ "i",
1479
+ "s"
1480
+ ],
1481
+ [
1482
+ "s",
1483
+ "p"
1484
+ ],
1485
+ [
1486
+ "n",
1487
+ "e"
1488
+ ],
1489
+ [
1490
+ "o",
1491
+ "l"
1492
+ ],
1493
+ [
1494
+ "c",
1495
+ "a"
1496
+ ],
1497
+ [
1498
+ "t",
1499
+ "ed</w>"
1500
+ ],
1501
+ [
1502
+ "i",
1503
+ "t</w>"
1504
+ ],
1505
+ [
1506
+ "er",
1507
+ "s</w>"
1508
+ ],
1509
+ [
1510
+ "ti",
1511
+ "on"
1512
+ ],
1513
+ [
1514
+ "h",
1515
+ "e</w>"
1516
+ ],
1517
+ [
1518
+ "s",
1519
+ "e</w>"
1520
+ ],
1521
+ [
1522
+ "g",
1523
+ "h"
1524
+ ],
1525
+ [
1526
+ "f",
1527
+ "or"
1528
+ ],
1529
+ [
1530
+ "hi",
1531
+ "s</w>"
1532
+ ],
1533
+ [
1534
+ "r",
1535
+ "u"
1536
+ ],
1537
+ [
1538
+ "t",
1539
+ "h</w>"
1540
+ ],
1541
+ [
1542
+ "v",
1543
+ "er"
1544
+ ],
1545
+ [
1546
+ "a",
1547
+ "d"
1548
+ ],
1549
+ [
1550
+ "t",
1551
+ "o"
1552
+ ],
1553
+ [
1554
+ "m",
1555
+ "o"
1556
+ ],
1557
+ [
1558
+ "e",
1559
+ "x"
1560
+ ],
1561
+ [
1562
+ "f",
1563
+ "ro"
1564
+ ],
1565
+ [
1566
+ "fro",
1567
+ "m</w>"
1568
+ ],
1569
+ [
1570
+ "a",
1571
+ "b"
1572
+ ],
1573
+ [
1574
+ "w",
1575
+ "hi"
1576
+ ],
1577
+ [
1578
+ "p",
1579
+ "er"
1580
+ ],
1581
+ [
1582
+ "c",
1583
+ "u"
1584
+ ],
1585
+ [
1586
+ "e",
1587
+ "a"
1588
+ ],
1589
+ [
1590
+ "d",
1591
+ "s</w>"
1592
+ ],
1593
+ [
1594
+ "w",
1595
+ "ere</w>"
1596
+ ],
1597
+ [
1598
+ "i",
1599
+ "c"
1600
+ ],
1601
+ [
1602
+ "o",
1603
+ "m"
1604
+ ],
1605
+ [
1606
+ "a",
1607
+ "p"
1608
+ ],
1609
+ [
1610
+ "it",
1611
+ "y</w>"
1612
+ ],
1613
+ [
1614
+ "a",
1615
+ "tion</w>"
1616
+ ],
1617
+ [
1618
+ "t",
1619
+ "er</w>"
1620
+ ],
1621
+ [
1622
+ "p",
1623
+ "re"
1624
+ ],
1625
+ [
1626
+ "ou",
1627
+ "n"
1628
+ ],
1629
+ [
1630
+ "a",
1631
+ "i"
1632
+ ],
1633
+ [
1634
+ "f",
1635
+ "e"
1636
+ ],
1637
+ [
1638
+ "l",
1639
+ "u"
1640
+ ],
1641
+ [
1642
+ "t",
1643
+ "er"
1644
+ ],
1645
+ [
1646
+ "at",
1647
+ "ed</w>"
1648
+ ],
1649
+ [
1650
+ "d",
1651
+ "e</w>"
1652
+ ],
1653
+ [
1654
+ "d",
1655
+ "u"
1656
+ ],
1657
+ [
1658
+ "g",
1659
+ "o"
1660
+ ],
1661
+ [
1662
+ "b",
1663
+ "o"
1664
+ ],
1665
+ [
1666
+ "al",
1667
+ "l</w>"
1668
+ ],
1669
+ [
1670
+ "w",
1671
+ "e"
1672
+ ],
1673
+ [
1674
+ "at",
1675
+ "e</w>"
1676
+ ],
1677
+ [
1678
+ "ti",
1679
+ "m"
1680
+ ],
1681
+ [
1682
+ "re",
1683
+ "c"
1684
+ ],
1685
+ [
1686
+ "ar",
1687
+ "e</w>"
1688
+ ],
1689
+ [
1690
+ "q",
1691
+ "u"
1692
+ ],
1693
+ [
1694
+ "th",
1695
+ "er</w>"
1696
+ ],
1697
+ [
1698
+ "m",
1699
+ "an"
1700
+ ],
1701
+ [
1702
+ "d",
1703
+ "ing</w>"
1704
+ ],
1705
+ [
1706
+ "m",
1707
+ "e"
1708
+ ],
1709
+ [
1710
+ "o",
1711
+ "p"
1712
+ ],
1713
+ [
1714
+ "g",
1715
+ "u"
1716
+ ],
1717
+ [
1718
+ "p",
1719
+ "ar"
1720
+ ],
1721
+ [
1722
+ "t",
1723
+ "r"
1724
+ ],
1725
+ [
1726
+ "on",
1727
+ "e</w>"
1728
+ ],
1729
+ [
1730
+ "whi",
1731
+ "ch</w>"
1732
+ ],
1733
+ [
1734
+ "g",
1735
+ "i"
1736
+ ],
1737
+ [
1738
+ "e",
1739
+ "c"
1740
+ ],
1741
+ [
1742
+ "â",
1743
+ "Ģ"
1744
+ ],
1745
+ [
1746
+ "d",
1747
+ "ed</w>"
1748
+ ],
1749
+ [
1750
+ "s",
1751
+ "s</w>"
1752
+ ],
1753
+ [
1754
+ "p",
1755
+ "or"
1756
+ ],
1757
+ [
1758
+ "am",
1759
+ "e</w>"
1760
+ ],
1761
+ [
1762
+ "ha",
1763
+ "d</w>"
1764
+ ],
1765
+ [
1766
+ "w",
1767
+ "or"
1768
+ ],
1769
+ [
1770
+ "a",
1771
+ "f"
1772
+ ],
1773
+ [
1774
+ "d",
1775
+ "er"
1776
+ ],
1777
+ [
1778
+ "v",
1779
+ "er</w>"
1780
+ ],
1781
+ [
1782
+ "in",
1783
+ "g"
1784
+ ],
1785
+ [
1786
+ "s",
1787
+ "c"
1788
+ ],
1789
+ [
1790
+ "e",
1791
+ "ar"
1792
+ ],
1793
+ [
1794
+ "b",
1795
+ "e</w>"
1796
+ ],
1797
+ [
1798
+ "h",
1799
+ "o"
1800
+ ],
1801
+ [
1802
+ "s",
1803
+ "o</w>"
1804
+ ],
1805
+ [
1806
+ "tion",
1807
+ "s</w>"
1808
+ ],
1809
+ [
1810
+ "t",
1811
+ "a"
1812
+ ],
1813
+ [
1814
+ "b",
1815
+ "er</w>"
1816
+ ],
1817
+ [
1818
+ "l",
1819
+ "d</w>"
1820
+ ],
1821
+ [
1822
+ "w",
1823
+ "a"
1824
+ ],
1825
+ [
1826
+ "m",
1827
+ "u"
1828
+ ],
1829
+ [
1830
+ "n",
1831
+ "i"
1832
+ ],
1833
+ [
1834
+ "s",
1835
+ "ed</w>"
1836
+ ],
1837
+ [
1838
+ "m",
1839
+ "ar"
1840
+ ],
1841
+ [
1842
+ "t",
1843
+ "ur"
1844
+ ],
1845
+ [
1846
+ "al",
1847
+ "ly</w>"
1848
+ ],
1849
+ [
1850
+ "o",
1851
+ "f"
1852
+ ],
1853
+ [
1854
+ "p",
1855
+ "u"
1856
+ ],
1857
+ [
1858
+ "gh",
1859
+ "t</w>"
1860
+ ],
1861
+ [
1862
+ "s",
1863
+ "hi"
1864
+ ],
1865
+ [
1866
+ "m",
1867
+ "i"
1868
+ ],
1869
+ [
1870
+ "t",
1871
+ "w"
1872
+ ],
1873
+ [
1874
+ "e",
1875
+ "st"
1876
+ ],
1877
+ [
1878
+ "ou",
1879
+ "t</w>"
1880
+ ],
1881
+ [
1882
+ "it",
1883
+ "s</w>"
1884
+ ],
1885
+ [
1886
+ "g",
1887
+ "h</w>"
1888
+ ],
1889
+ [
1890
+ "fi",
1891
+ "r"
1892
+ ],
1893
+ [
1894
+ "h",
1895
+ "er</w>"
1896
+ ],
1897
+ [
1898
+ "i",
1899
+ "r</w>"
1900
+ ],
1901
+ [
1902
+ "u",
1903
+ "m"
1904
+ ],
1905
+ [
1906
+ "c",
1907
+ "e"
1908
+ ],
1909
+ [
1910
+ "p",
1911
+ "la"
1912
+ ],
1913
+ [
1914
+ "th",
1915
+ "is</w>"
1916
+ ],
1917
+ [
1918
+ "w",
1919
+ "n</w>"
1920
+ ],
1921
+ [
1922
+ "a",
1923
+ "u"
1924
+ ],
1925
+ [
1926
+ "ro",
1927
+ "u"
1928
+ ],
1929
+ [
1930
+ "p",
1931
+ "l"
1932
+ ],
1933
+ [
1934
+ "sh",
1935
+ "e</w>"
1936
+ ],
1937
+ [
1938
+ "âĢ",
1939
+ "ĵ</w>"
1940
+ ],
1941
+ [
1942
+ "k",
1943
+ "e</w>"
1944
+ ],
1945
+ [
1946
+ "in",
1947
+ "c"
1948
+ ],
1949
+ [
1950
+ "i",
1951
+ "m"
1952
+ ],
1953
+ [
1954
+ "al",
1955
+ "so</w>"
1956
+ ],
1957
+ [
1958
+ "d",
1959
+ "er</w>"
1960
+ ],
1961
+ [
1962
+ "g",
1963
+ "e</w>"
1964
+ ],
1965
+ [
1966
+ "n",
1967
+ "a"
1968
+ ],
1969
+ [
1970
+ "in",
1971
+ "e</w>"
1972
+ ],
1973
+ [
1974
+ "the",
1975
+ "ir</w>"
1976
+ ],
1977
+ [
1978
+ "on",
1979
+ "g</w>"
1980
+ ],
1981
+ [
1982
+ "p",
1983
+ "e"
1984
+ ],
1985
+ [
1986
+ "s",
1987
+ "er"
1988
+ ],
1989
+ [
1990
+ "v",
1991
+ "ed</w>"
1992
+ ],
1993
+ [
1994
+ "ar",
1995
+ "y</w>"
1996
+ ],
1997
+ [
1998
+ "s",
1999
+ "en"
2000
+ ],
2001
+ [
2002
+ "m",
2003
+ "ent</w>"
2004
+ ],
2005
+ [
2006
+ "f",
2007
+ "in"
2008
+ ],
2009
+ [
2010
+ "h",
2011
+ "as</w>"
2012
+ ],
2013
+ [
2014
+ "t",
2015
+ "ing</w>"
2016
+ ],
2017
+ [
2018
+ "d",
2019
+ "o"
2020
+ ],
2021
+ [
2022
+ "s",
2023
+ "h</w>"
2024
+ ],
2025
+ [
2026
+ "no",
2027
+ "t</w>"
2028
+ ],
2029
+ [
2030
+ "t",
2031
+ "e</w>"
2032
+ ],
2033
+ [
2034
+ "r",
2035
+ "an"
2036
+ ],
2037
+ [
2038
+ "s",
2039
+ "a"
2040
+ ],
2041
+ [
2042
+ "m",
2043
+ "or"
2044
+ ],
2045
+ [
2046
+ "or",
2047
+ "i"
2048
+ ],
2049
+ [
2050
+ "m",
2051
+ "in"
2052
+ ],
2053
+ [
2054
+ "l",
2055
+ "ed</w>"
2056
+ ],
2057
+ [
2058
+ ".",
2059
+ "@</w>"
2060
+ ],
2061
+ [
2062
+ "@",
2063
+ ".@</w>"
2064
+ ],
2065
+ [
2066
+ "bu",
2067
+ "t</w>"
2068
+ ],
2069
+ [
2070
+ "af",
2071
+ "ter</w>"
2072
+ ],
2073
+ [
2074
+ "tw",
2075
+ "o</w>"
2076
+ ],
2077
+ [
2078
+ "fir",
2079
+ "st</w>"
2080
+ ],
2081
+ [
2082
+ "s",
2083
+ "ti"
2084
+ ],
2085
+ [
2086
+ "s",
2087
+ "o"
2088
+ ],
2089
+ [
2090
+ "i",
2091
+ "r"
2092
+ ],
2093
+ [
2094
+ "f",
2095
+ "er"
2096
+ ],
2097
+ [
2098
+ "o",
2099
+ "ther</w>"
2100
+ ],
2101
+ [
2102
+ "t",
2103
+ "y</w>"
2104
+ ],
2105
+ [
2106
+ "en",
2107
+ "ts</w>"
2108
+ ],
2109
+ [
2110
+ "the",
2111
+ "y</w>"
2112
+ ],
2113
+ [
2114
+ "com",
2115
+ "m"
2116
+ ],
2117
+ [
2118
+ "t",
2119
+ "u"
2120
+ ],
2121
+ [
2122
+ "w",
2123
+ "i"
2124
+ ],
2125
+ [
2126
+ "g",
2127
+ "e"
2128
+ ],
2129
+ [
2130
+ "t",
2131
+ "e"
2132
+ ],
2133
+ [
2134
+ "ha",
2135
+ "ve</w>"
2136
+ ],
2137
+ [
2138
+ "n",
2139
+ "ed</w>"
2140
+ ],
2141
+ [
2142
+ "t",
2143
+ "en"
2144
+ ],
2145
+ [
2146
+ "s",
2147
+ "s"
2148
+ ],
2149
+ [
2150
+ "ou",
2151
+ "ld</w>"
2152
+ ],
2153
+ [
2154
+ "wh",
2155
+ "o</w>"
2156
+ ],
2157
+ [
2158
+ "p",
2159
+ "i"
2160
+ ],
2161
+ [
2162
+ "d",
2163
+ "a"
2164
+ ],
2165
+ [
2166
+ "as",
2167
+ "t</w>"
2168
+ ],
2169
+ [
2170
+ "ti",
2171
+ "es</w>"
2172
+ ],
2173
+ [
2174
+ "l",
2175
+ "ar"
2176
+ ],
2177
+ [
2178
+ "s",
2179
+ "on</w>"
2180
+ ],
2181
+ [
2182
+ "w",
2183
+ "ar"
2184
+ ],
2185
+ [
2186
+ "sh",
2187
+ "o"
2188
+ ],
2189
+ [
2190
+ "k",
2191
+ "e"
2192
+ ],
2193
+ [
2194
+ "ch",
2195
+ "ar"
2196
+ ],
2197
+ [
2198
+ "be",
2199
+ "en</w>"
2200
+ ],
2201
+ [
2202
+ "ou",
2203
+ "r"
2204
+ ],
2205
+ [
2206
+ ",",
2207
+ "@</w>"
2208
+ ],
2209
+ [
2210
+ "@",
2211
+ ",@</w>"
2212
+ ],
2213
+ [
2214
+ "m",
2215
+ "an</w>"
2216
+ ],
2217
+ [
2218
+ "ne",
2219
+ "w</w>"
2220
+ ],
2221
+ [
2222
+ "k",
2223
+ "s</w>"
2224
+ ],
2225
+ [
2226
+ "m",
2227
+ "on"
2228
+ ],
2229
+ [
2230
+ "si",
2231
+ "on</w>"
2232
+ ],
2233
+ [
2234
+ "g",
2235
+ "en"
2236
+ ],
2237
+ [
2238
+ "or",
2239
+ "y</w>"
2240
+ ],
2241
+ [
2242
+ "ur",
2243
+ "ing</w>"
2244
+ ],
2245
+ [
2246
+ "a",
2247
+ "r</w>"
2248
+ ],
2249
+ [
2250
+ "g",
2251
+ "re"
2252
+ ],
2253
+ [
2254
+ "at",
2255
+ "er</w>"
2256
+ ],
2257
+ [
2258
+ "lo",
2259
+ "w"
2260
+ ],
2261
+ [
2262
+ "an",
2263
+ "t</w>"
2264
+ ],
2265
+ [
2266
+ "si",
2267
+ "g"
2268
+ ],
2269
+ [
2270
+ "el",
2271
+ "y</w>"
2272
+ ],
2273
+ [
2274
+ "f",
2275
+ "t</w>"
2276
+ ],
2277
+ [
2278
+ "con",
2279
+ "t"
2280
+ ],
2281
+ [
2282
+ "f",
2283
+ "u"
2284
+ ],
2285
+ [
2286
+ "r",
2287
+ "it"
2288
+ ],
2289
+ [
2290
+ "ag",
2291
+ "e</w>"
2292
+ ],
2293
+ [
2294
+ "ou",
2295
+ "s</w>"
2296
+ ],
2297
+ [
2298
+ "c",
2299
+ "re"
2300
+ ],
2301
+ [
2302
+ "c",
2303
+ "en"
2304
+ ],
2305
+ [
2306
+ "st",
2307
+ "e"
2308
+ ],
2309
+ [
2310
+ "e",
2311
+ "l</w>"
2312
+ ],
2313
+ [
2314
+ "du",
2315
+ "c"
2316
+ ],
2317
+ [
2318
+ "u",
2319
+ "s</w>"
2320
+ ],
2321
+ [
2322
+ "po",
2323
+ "li"
2324
+ ],
2325
+ [
2326
+ "tion",
2327
+ "al</w>"
2328
+ ],
2329
+ [
2330
+ "om",
2331
+ "e</w>"
2332
+ ],
2333
+ [
2334
+ "tim",
2335
+ "e</w>"
2336
+ ],
2337
+ [
2338
+ "t",
2339
+ "ra"
2340
+ ],
2341
+ [
2342
+ "al",
2343
+ "i"
2344
+ ],
2345
+ [
2346
+ "pla",
2347
+ "y"
2348
+ ],
2349
+ [
2350
+ "k",
2351
+ "ing</w>"
2352
+ ],
2353
+ [
2354
+ "sp",
2355
+ "e"
2356
+ ],
2357
+ [
2358
+ "ou",
2359
+ "r</w>"
2360
+ ],
2361
+ [
2362
+ "o",
2363
+ "c"
2364
+ ],
2365
+ [
2366
+ "it",
2367
+ "ed</w>"
2368
+ ],
2369
+ [
2370
+ "fi",
2371
+ "l"
2372
+ ],
2373
+ [
2374
+ "ai",
2375
+ "r"
2376
+ ],
2377
+ [
2378
+ "b",
2379
+ "ri"
2380
+ ],
2381
+ [
2382
+ "al",
2383
+ "s</w>"
2384
+ ],
2385
+ [
2386
+ "e",
2387
+ "v"
2388
+ ],
2389
+ [
2390
+ "o",
2391
+ "o"
2392
+ ],
2393
+ [
2394
+ "ar",
2395
+ "i"
2396
+ ],
2397
+ [
2398
+ "in",
2399
+ "ter"
2400
+ ],
2401
+ [
2402
+ "ti",
2403
+ "c"
2404
+ ],
2405
+ [
2406
+ "un",
2407
+ "i"
2408
+ ],
2409
+ [
2410
+ "g",
2411
+ "ra"
2412
+ ],
2413
+ [
2414
+ "la",
2415
+ "r</w>"
2416
+ ],
2417
+ [
2418
+ "se",
2419
+ "as"
2420
+ ],
2421
+ [
2422
+ "d",
2423
+ "uring</w>"
2424
+ ],
2425
+ [
2426
+ "st",
2427
+ "ru"
2428
+ ],
2429
+ [
2430
+ "re",
2431
+ "s</w>"
2432
+ ],
2433
+ [
2434
+ "n",
2435
+ "or"
2436
+ ],
2437
+ [
2438
+ "p",
2439
+ "p"
2440
+ ],
2441
+ [
2442
+ "j",
2443
+ "o"
2444
+ ],
2445
+ [
2446
+ "th",
2447
+ "ou"
2448
+ ],
2449
+ [
2450
+ "em",
2451
+ "ber</w>"
2452
+ ],
2453
+ [
2454
+ "l",
2455
+ "and</w>"
2456
+ ],
2457
+ [
2458
+ "or",
2459
+ "d"
2460
+ ],
2461
+ [
2462
+ "c",
2463
+ "k</w>"
2464
+ ],
2465
+ [
2466
+ "it",
2467
+ "e</w>"
2468
+ ],
2469
+ [
2470
+ "inc",
2471
+ "lu"
2472
+ ],
2473
+ [
2474
+ "an",
2475
+ "ce</w>"
2476
+ ],
2477
+ [
2478
+ "st",
2479
+ "r"
2480
+ ],
2481
+ [
2482
+ "p",
2483
+ "ri"
2484
+ ],
2485
+ [
2486
+ "ur",
2487
+ "e</w>"
2488
+ ],
2489
+ [
2490
+ "ti",
2491
+ "ve</w>"
2492
+ ],
2493
+ [
2494
+ "at",
2495
+ "t"
2496
+ ],
2497
+ [
2498
+ "re",
2499
+ "e</w>"
2500
+ ],
2501
+ [
2502
+ "ac",
2503
+ "k</w>"
2504
+ ],
2505
+ [
2506
+ "co",
2507
+ "l"
2508
+ ],
2509
+ [
2510
+ "cu",
2511
+ "l"
2512
+ ],
2513
+ [
2514
+ "mor",
2515
+ "e</w>"
2516
+ ],
2517
+ [
2518
+ "b",
2519
+ "li"
2520
+ ],
2521
+ [
2522
+ "g",
2523
+ "ro"
2524
+ ],
2525
+ [
2526
+ "as",
2527
+ "ed</w>"
2528
+ ],
2529
+ [
2530
+ "p",
2531
+ "s</w>"
2532
+ ],
2533
+ [
2534
+ "th",
2535
+ "an</w>"
2536
+ ],
2537
+ [
2538
+ "for",
2539
+ "m"
2540
+ ],
2541
+ [
2542
+ "y",
2543
+ "p"
2544
+ ],
2545
+ [
2546
+ "com",
2547
+ "p"
2548
+ ],
2549
+ [
2550
+ "rec",
2551
+ "or"
2552
+ ],
2553
+ [
2554
+ "c",
2555
+ "or"
2556
+ ],
2557
+ [
2558
+ "el",
2559
+ "l</w>"
2560
+ ],
2561
+ [
2562
+ "mo",
2563
+ "st</w>"
2564
+ ],
2565
+ [
2566
+ "at",
2567
+ "es</w>"
2568
+ ],
2569
+ [
2570
+ "in",
2571
+ "s</w>"
2572
+ ],
2573
+ [
2574
+ "in",
2575
+ "ed</w>"
2576
+ ],
2577
+ [
2578
+ "c",
2579
+ "hi"
2580
+ ],
2581
+ [
2582
+ "pu",
2583
+ "bli"
2584
+ ],
2585
+ [
2586
+ "wa",
2587
+ "y</w>"
2588
+ ],
2589
+ [
2590
+ "e",
2591
+ "t</w>"
2592
+ ],
2593
+ [
2594
+ "c",
2595
+ "ar"
2596
+ ],
2597
+ [
2598
+ "l",
2599
+ "es</w>"
2600
+ ],
2601
+ [
2602
+ "a",
2603
+ "d</w>"
2604
+ ],
2605
+ [
2606
+ "c",
2607
+ "es</w>"
2608
+ ],
2609
+ [
2610
+ "s",
2611
+ "ch"
2612
+ ],
2613
+ [
2614
+ "spe",
2615
+ "ci"
2616
+ ],
2617
+ [
2618
+ "on",
2619
+ "s</w>"
2620
+ ],
2621
+ [
2622
+ "en",
2623
+ "ce</w>"
2624
+ ],
2625
+ [
2626
+ "al",
2627
+ "bu"
2628
+ ],
2629
+ [
2630
+ "v",
2631
+ "es</w>"
2632
+ ],
2633
+ [
2634
+ "ea",
2635
+ "r</w>"
2636
+ ],
2637
+ [
2638
+ "re",
2639
+ "n"
2640
+ ],
2641
+ [
2642
+ "ch",
2643
+ "a"
2644
+ ],
2645
+ [
2646
+ "shi",
2647
+ "p</w>"
2648
+ ],
2649
+ [
2650
+ "j",
2651
+ "u"
2652
+ ],
2653
+ [
2654
+ "oun",
2655
+ "d</w>"
2656
+ ],
2657
+ [
2658
+ "ol",
2659
+ "d</w>"
2660
+ ],
2661
+ [
2662
+ "k",
2663
+ "ed</w>"
2664
+ ],
2665
+ [
2666
+ "an",
2667
+ "d"
2668
+ ],
2669
+ [
2670
+ "ac",
2671
+ "e</w>"
2672
+ ],
2673
+ [
2674
+ "seas",
2675
+ "on</w>"
2676
+ ],
2677
+ [
2678
+ "s",
2679
+ "el"
2680
+ ],
2681
+ [
2682
+ "ab",
2683
+ "le</w>"
2684
+ ],
2685
+ [
2686
+ "in",
2687
+ "di"
2688
+ ],
2689
+ [
2690
+ "p",
2691
+ "h"
2692
+ ],
2693
+ [
2694
+ "t",
2695
+ "ri"
2696
+ ],
2697
+ [
2698
+ "e",
2699
+ "i"
2700
+ ],
2701
+ [
2702
+ "c",
2703
+ "ity</w>"
2704
+ ],
2705
+ [
2706
+ "ca",
2707
+ "u"
2708
+ ],
2709
+ [
2710
+ "m",
2711
+ "il"
2712
+ ],
2713
+ [
2714
+ "b",
2715
+ "i"
2716
+ ],
2717
+ [
2718
+ "t",
2719
+ "ly</w>"
2720
+ ],
2721
+ [
2722
+ "in",
2723
+ "to</w>"
2724
+ ],
2725
+ [
2726
+ "c",
2727
+ "l"
2728
+ ],
2729
+ [
2730
+ "r",
2731
+ "ed</w>"
2732
+ ],
2733
+ [
2734
+ "l",
2735
+ "s</w>"
2736
+ ],
2737
+ [
2738
+ "s",
2739
+ "ou"
2740
+ ],
2741
+ [
2742
+ "as",
2743
+ "e</w>"
2744
+ ],
2745
+ [
2746
+ "ing",
2747
+ "s</w>"
2748
+ ],
2749
+ [
2750
+ "v",
2751
+ "ing</w>"
2752
+ ],
2753
+ [
2754
+ "ac",
2755
+ "h"
2756
+ ],
2757
+ [
2758
+ "s",
2759
+ "y"
2760
+ ],
2761
+ [
2762
+ "wh",
2763
+ "en</w>"
2764
+ ],
2765
+ [
2766
+ "o",
2767
+ "lo"
2768
+ ],
2769
+ [
2770
+ "o",
2771
+ "ver</w>"
2772
+ ],
2773
+ [
2774
+ "hi",
2775
+ "st"
2776
+ ],
2777
+ [
2778
+ "thou",
2779
+ "gh</w>"
2780
+ ],
2781
+ [
2782
+ "en",
2783
+ "d</w>"
2784
+ ],
2785
+ [
2786
+ "ti",
2787
+ "c</w>"
2788
+ ],
2789
+ [
2790
+ "di",
2791
+ "s"
2792
+ ],
2793
+ [
2794
+ "se",
2795
+ "con"
2796
+ ],
2797
+ [
2798
+ "c",
2799
+ "an"
2800
+ ],
2801
+ [
2802
+ "s",
2803
+ "ur"
2804
+ ],
2805
+ [
2806
+ "on",
2807
+ "ly</w>"
2808
+ ],
2809
+ [
2810
+ "ma",
2811
+ "y</w>"
2812
+ ],
2813
+ [
2814
+ "ord",
2815
+ "an</w>"
2816
+ ],
2817
+ [
2818
+ "c",
2819
+ "oun"
2820
+ ],
2821
+ [
2822
+ "j",
2823
+ "ordan</w>"
2824
+ ],
2825
+ [
2826
+ "m",
2827
+ "s</w>"
2828
+ ],
2829
+ [
2830
+ "an",
2831
+ "s</w>"
2832
+ ],
2833
+ [
2834
+ "albu",
2835
+ "m</w>"
2836
+ ],
2837
+ [
2838
+ "er",
2839
+ "n</w>"
2840
+ ],
2841
+ [
2842
+ "b",
2843
+ "le</w>"
2844
+ ],
2845
+ [
2846
+ "r",
2847
+ "e</w>"
2848
+ ],
2849
+ [
2850
+ "w",
2851
+ "n"
2852
+ ],
2853
+ [
2854
+ "ac",
2855
+ "h</w>"
2856
+ ],
2857
+ [
2858
+ "am",
2859
+ "es</w>"
2860
+ ],
2861
+ [
2862
+ "o",
2863
+ "k</w>"
2864
+ ],
2865
+ [
2866
+ "y",
2867
+ "s</w>"
2868
+ ],
2869
+ [
2870
+ "u",
2871
+ "p</w>"
2872
+ ],
2873
+ [
2874
+ "th",
2875
+ "ere</w>"
2876
+ ],
2877
+ [
2878
+ "su",
2879
+ "b"
2880
+ ],
2881
+ [
2882
+ "e",
2883
+ "g"
2884
+ ],
2885
+ [
2886
+ "n",
2887
+ "um"
2888
+ ],
2889
+ [
2890
+ "man",
2891
+ "y</w>"
2892
+ ],
2893
+ [
2894
+ "th",
2895
+ "ree</w>"
2896
+ ],
2897
+ [
2898
+ "g",
2899
+ "in"
2900
+ ],
2901
+ [
2902
+ "re",
2903
+ "le"
2904
+ ],
2905
+ [
2906
+ "sh",
2907
+ "ed</w>"
2908
+ ],
2909
+ [
2910
+ "ag",
2911
+ "a"
2912
+ ],
2913
+ [
2914
+ "g",
2915
+ "al"
2916
+ ],
2917
+ [
2918
+ "k",
2919
+ "no"
2920
+ ],
2921
+ [
2922
+ "o",
2923
+ "d</w>"
2924
+ ],
2925
+ [
2926
+ "whi",
2927
+ "le</w>"
2928
+ ],
2929
+ [
2930
+ "y",
2931
+ "ear</w>"
2932
+ ],
2933
+ [
2934
+ "or",
2935
+ "s</w>"
2936
+ ],
2937
+ [
2938
+ "n",
2939
+ "ing</w>"
2940
+ ],
2941
+ [
2942
+ "p",
2943
+ "a"
2944
+ ],
2945
+ [
2946
+ "l",
2947
+ "ater</w>"
2948
+ ],
2949
+ [
2950
+ "v",
2951
+ "e"
2952
+ ],
2953
+ [
2954
+ "n",
2955
+ "o</w>"
2956
+ ],
2957
+ [
2958
+ "th",
2959
+ "rou"
2960
+ ],
2961
+ [
2962
+ "y",
2963
+ "ing</w>"
2964
+ ],
2965
+ [
2966
+ "em",
2967
+ "p"
2968
+ ],
2969
+ [
2970
+ "a",
2971
+ "tions</w>"
2972
+ ],
2973
+ [
2974
+ "i",
2975
+ "c</w>"
2976
+ ],
2977
+ [
2978
+ "vi",
2979
+ "e"
2980
+ ],
2981
+ [
2982
+ "wh",
2983
+ "e"
2984
+ ],
2985
+ [
2986
+ "s",
2987
+ "si"
2988
+ ],
2989
+ [
2990
+ "c",
2991
+ "ame</w>"
2992
+ ],
2993
+ [
2994
+ "si",
2995
+ "c</w>"
2996
+ ],
2997
+ [
2998
+ "f",
2999
+ "a"
3000
+ ],
3001
+ [
3002
+ "be",
3003
+ "t"
3004
+ ],
3005
+ [
3006
+ "wa",
3007
+ "r</w>"
3008
+ ],
3009
+ [
3010
+ "b",
3011
+ "ro"
3012
+ ],
3013
+ [
3014
+ "w",
3015
+ "ould</w>"
3016
+ ],
3017
+ [
3018
+ "s",
3019
+ "ome</w>"
3020
+ ],
3021
+ [
3022
+ "l",
3023
+ "l</w>"
3024
+ ],
3025
+ [
3026
+ "de",
3027
+ "v"
3028
+ ],
3029
+ [
3030
+ "ic",
3031
+ "al</w>"
3032
+ ],
3033
+ [
3034
+ "s",
3035
+ "k"
3036
+ ],
3037
+ [
3038
+ "pro",
3039
+ "duc"
3040
+ ],
3041
+ [
3042
+ "por",
3043
+ "t</w>"
3044
+ ],
3045
+ [
3046
+ "sc",
3047
+ "ri"
3048
+ ],
3049
+ [
3050
+ "bu",
3051
+ "il"
3052
+ ],
3053
+ [
3054
+ "b",
3055
+ "ar"
3056
+ ],
3057
+ [
3058
+ "g",
3059
+ "ame</w>"
3060
+ ],
3061
+ [
3062
+ "fil",
3063
+ "m</w>"
3064
+ ],
3065
+ [
3066
+ "b",
3067
+ "a"
3068
+ ],
3069
+ [
3070
+ "th",
3071
+ "o"
3072
+ ],
3073
+ [
3074
+ "lo",
3075
+ "c"
3076
+ ],
3077
+ [
3078
+ "be",
3079
+ "ing</w>"
3080
+ ],
3081
+ [
3082
+ "the",
3083
+ "se</w>"
3084
+ ],
3085
+ [
3086
+ "ab",
3087
+ "out</w>"
3088
+ ],
3089
+ [
3090
+ "so",
3091
+ "ci"
3092
+ ],
3093
+ [
3094
+ "s",
3095
+ "ing</w>"
3096
+ ],
3097
+ [
3098
+ "l",
3099
+ "an"
3100
+ ],
3101
+ [
3102
+ "t",
3103
+ "re"
3104
+ ],
3105
+ [
3106
+ "t",
3107
+ "en</w>"
3108
+ ],
3109
+ [
3110
+ "w",
3111
+ "rit"
3112
+ ],
3113
+ [
3114
+ "f",
3115
+ "ol"
3116
+ ],
3117
+ [
3118
+ "ar",
3119
+ "d</w>"
3120
+ ],
3121
+ [
3122
+ "u",
3123
+ "e</w>"
3124
+ ],
3125
+ [
3126
+ "ea",
3127
+ "m</w>"
3128
+ ],
3129
+ [
3130
+ "st",
3131
+ "s</w>"
3132
+ ],
3133
+ [
3134
+ "hi",
3135
+ "m</w>"
3136
+ ],
3137
+ [
3138
+ "ap",
3139
+ "p"
3140
+ ],
3141
+ [
3142
+ "g",
3143
+ "er"
3144
+ ],
3145
+ [
3146
+ "the",
3147
+ "m</w>"
3148
+ ],
3149
+ [
3150
+ "stru",
3151
+ "c"
3152
+ ],
3153
+ [
3154
+ "of",
3155
+ "fi"
3156
+ ],
3157
+ [
3158
+ "m",
3159
+ "y</w>"
3160
+ ],
3161
+ [
3162
+ "an",
3163
+ "i"
3164
+ ],
3165
+ [
3166
+ "da",
3167
+ "y</w>"
3168
+ ],
3169
+ [
3170
+ "d",
3171
+ "y</w>"
3172
+ ],
3173
+ [
3174
+ "h",
3175
+ "e"
3176
+ ],
3177
+ [
3178
+ "u",
3179
+ "m</w>"
3180
+ ],
3181
+ [
3182
+ "st",
3183
+ "ri"
3184
+ ],
3185
+ [
3186
+ "st",
3187
+ "u"
3188
+ ],
3189
+ [
3190
+ "el",
3191
+ "e"
3192
+ ],
3193
+ [
3194
+ "whe",
3195
+ "el"
3196
+ ],
3197
+ [
3198
+ "c",
3199
+ "ra"
3200
+ ],
3201
+ [
3202
+ "secon",
3203
+ "d</w>"
3204
+ ],
3205
+ [
3206
+ "on",
3207
+ "g"
3208
+ ],
3209
+ [
3210
+ "si",
3211
+ "de</w>"
3212
+ ],
3213
+ [
3214
+ "su",
3215
+ "ch</w>"
3216
+ ],
3217
+ [
3218
+ "t",
3219
+ "eam</w>"
3220
+ ],
3221
+ [
3222
+ "at",
3223
+ "ing</w>"
3224
+ ],
3225
+ [
3226
+ "c",
3227
+ "an</w>"
3228
+ ],
3229
+ [
3230
+ "f",
3231
+ "ac"
3232
+ ],
3233
+ [
3234
+ "m",
3235
+ "is"
3236
+ ],
3237
+ [
3238
+ "wheel",
3239
+ "er</w>"
3240
+ ],
3241
+ [
3242
+ "d",
3243
+ "en"
3244
+ ],
3245
+ [
3246
+ "m",
3247
+ "e</w>"
3248
+ ],
3249
+ [
3250
+ "c",
3251
+ "ri"
3252
+ ],
3253
+ [
3254
+ "ch",
3255
+ "ri"
3256
+ ],
3257
+ [
3258
+ "we",
3259
+ "en</w>"
3260
+ ],
3261
+ [
3262
+ "cha",
3263
+ "e"
3264
+ ],
3265
+ [
3266
+ "g",
3267
+ "a"
3268
+ ],
3269
+ [
3270
+ "l",
3271
+ "ing</w>"
3272
+ ],
3273
+ [
3274
+ "s",
3275
+ "es</w>"
3276
+ ],
3277
+ [
3278
+ "bet",
3279
+ "ween</w>"
3280
+ ],
3281
+ [
3282
+ "m",
3283
+ "at"
3284
+ ],
3285
+ [
3286
+ "v",
3287
+ "est"
3288
+ ],
3289
+ [
3290
+ "po",
3291
+ "in"
3292
+ ],
3293
+ [
3294
+ "gen",
3295
+ "er"
3296
+ ],
3297
+ [
3298
+ "c",
3299
+ "al"
3300
+ ],
3301
+ [
3302
+ "w",
3303
+ "il"
3304
+ ],
3305
+ [
3306
+ "ti",
3307
+ "sh</w>"
3308
+ ],
3309
+ [
3310
+ "ar",
3311
+ "chae"
3312
+ ],
3313
+ [
3314
+ "ear",
3315
+ "s</w>"
3316
+ ],
3317
+ [
3318
+ "archae",
3319
+ "olo"
3320
+ ],
3321
+ [
3322
+ "j",
3323
+ "ec"
3324
+ ],
3325
+ [
3326
+ "t",
3327
+ "al</w>"
3328
+ ],
3329
+ [
3330
+ "un",
3331
+ "d</w>"
3332
+ ],
3333
+ [
3334
+ "s",
3335
+ "in"
3336
+ ],
3337
+ [
3338
+ "v",
3339
+ "en"
3340
+ ],
3341
+ [
3342
+ "ma",
3343
+ "de</w>"
3344
+ ],
3345
+ [
3346
+ "su",
3347
+ "l"
3348
+ ],
3349
+ [
3350
+ "tur",
3351
+ "e</w>"
3352
+ ],
3353
+ [
3354
+ "o",
3355
+ "per"
3356
+ ],
3357
+ [
3358
+ "v",
3359
+ "en</w>"
3360
+ ],
3361
+ [
3362
+ "w",
3363
+ "s</w>"
3364
+ ],
3365
+ [
3366
+ "wh",
3367
+ "ere</w>"
3368
+ ],
3369
+ [
3370
+ "r",
3371
+ "on"
3372
+ ],
3373
+ [
3374
+ "con",
3375
+ "si"
3376
+ ],
3377
+ [
3378
+ "f",
3379
+ "our</w>"
3380
+ ],
3381
+ [
3382
+ "t",
3383
+ "on</w>"
3384
+ ],
3385
+ [
3386
+ "o",
3387
+ "b"
3388
+ ],
3389
+ [
3390
+ "w",
3391
+ "er</w>"
3392
+ ],
3393
+ [
3394
+ "se",
3395
+ "ver"
3396
+ ],
3397
+ [
3398
+ "un",
3399
+ "der</w>"
3400
+ ],
3401
+ [
3402
+ "wor",
3403
+ "k</w>"
3404
+ ],
3405
+ [
3406
+ "am",
3407
+ "er"
3408
+ ],
3409
+ [
3410
+ "ca",
3411
+ "p"
3412
+ ],
3413
+ [
3414
+ "na",
3415
+ "tional</w>"
3416
+ ],
3417
+ [
3418
+ "wi",
3419
+ "th"
3420
+ ],
3421
+ [
3422
+ "for",
3423
+ "e</w>"
3424
+ ],
3425
+ [
3426
+ "th",
3427
+ "en</w>"
3428
+ ],
3429
+ [
3430
+ "al",
3431
+ "though</w>"
3432
+ ],
3433
+ [
3434
+ "s",
3435
+ "m"
3436
+ ],
3437
+ [
3438
+ "on",
3439
+ "y</w>"
3440
+ ],
3441
+ [
3442
+ "el",
3443
+ "d</w>"
3444
+ ],
3445
+ [
3446
+ "ch",
3447
+ "ur"
3448
+ ],
3449
+ [
3450
+ "bri",
3451
+ "tish</w>"
3452
+ ],
3453
+ [
3454
+ "gal",
3455
+ "vest"
3456
+ ],
3457
+ [
3458
+ "bo",
3459
+ "th</w>"
3460
+ ],
3461
+ [
3462
+ "b",
3463
+ "er"
3464
+ ],
3465
+ [
3466
+ "st",
3467
+ "ed</w>"
3468
+ ],
3469
+ [
3470
+ "di",
3471
+ "rec"
3472
+ ],
3473
+ [
3474
+ "galvest",
3475
+ "on</w>"
3476
+ ],
3477
+ [
3478
+ "f",
3479
+ "e</w>"
3480
+ ],
3481
+ [
3482
+ "w",
3483
+ "ell</w>"
3484
+ ],
3485
+ [
3486
+ "d",
3487
+ "re"
3488
+ ],
3489
+ [
3490
+ "y",
3491
+ "or"
3492
+ ],
3493
+ [
3494
+ "no",
3495
+ "v"
3496
+ ],
3497
+ [
3498
+ "l",
3499
+ "it"
3500
+ ],
3501
+ [
3502
+ "t",
3503
+ "ro"
3504
+ ],
3505
+ [
3506
+ "de",
3507
+ "scri"
3508
+ ],
3509
+ [
3510
+ "ca",
3511
+ "tion</w>"
3512
+ ],
3513
+ [
3514
+ "ai",
3515
+ "d</w>"
3516
+ ],
3517
+ [
3518
+ "tr",
3519
+ "an"
3520
+ ],
3521
+ [
3522
+ "in",
3523
+ "i"
3524
+ ],
3525
+ [
3526
+ "st",
3527
+ "ate</w>"
3528
+ ],
3529
+ [
3530
+ "per",
3531
+ "i"
3532
+ ],
3533
+ [
3534
+ "d",
3535
+ "es</w>"
3536
+ ],
3537
+ [
3538
+ "e",
3539
+ "st</w>"
3540
+ ],
3541
+ [
3542
+ "h",
3543
+ "ea"
3544
+ ],
3545
+ [
3546
+ "p",
3547
+ "en"
3548
+ ],
3549
+ [
3550
+ "y",
3551
+ "ears</w>"
3552
+ ],
3553
+ [
3554
+ "wor",
3555
+ "ld</w>"
3556
+ ],
3557
+ [
3558
+ "i",
3559
+ "es</w>"
3560
+ ],
3561
+ [
3562
+ "u",
3563
+ "sed</w>"
3564
+ ],
3565
+ [
3566
+ "go",
3567
+ "ds</w>"
3568
+ ],
3569
+ [
3570
+ "t",
3571
+ "ers</w>"
3572
+ ],
3573
+ [
3574
+ "di",
3575
+ "f"
3576
+ ],
3577
+ [
3578
+ "fol",
3579
+ "low"
3580
+ ],
3581
+ [
3582
+ "a",
3583
+ "re"
3584
+ ],
3585
+ [
3586
+ "e",
3587
+ "s"
3588
+ ],
3589
+ [
3590
+ "g",
3591
+ "an</w>"
3592
+ ],
3593
+ [
3594
+ "st",
3595
+ "ar"
3596
+ ],
3597
+ [
3598
+ "li",
3599
+ "ke</w>"
3600
+ ],
3601
+ [
3602
+ "ear",
3603
+ "ly</w>"
3604
+ ],
3605
+ [
3606
+ "m",
3607
+ "en"
3608
+ ],
3609
+ [
3610
+ "s",
3611
+ "ing"
3612
+ ],
3613
+ [
3614
+ "b",
3615
+ "or"
3616
+ ],
3617
+ [
3618
+ "t",
3619
+ "or</w>"
3620
+ ],
3621
+ [
3622
+ "mu",
3623
+ "sic</w>"
3624
+ ],
3625
+ [
3626
+ "cl",
3627
+ "as"
3628
+ ],
3629
+ [
3630
+ "sever",
3631
+ "al</w>"
3632
+ ],
3633
+ [
3634
+ "un",
3635
+ "ited</w>"
3636
+ ],
3637
+ [
3638
+ "num",
3639
+ "ber</w>"
3640
+ ],
3641
+ [
3642
+ "chur",
3643
+ "ch</w>"
3644
+ ],
3645
+ [
3646
+ "yor",
3647
+ "k</w>"
3648
+ ],
3649
+ [
3650
+ "c",
3651
+ "ur"
3652
+ ],
3653
+ [
3654
+ "c",
3655
+ "lo"
3656
+ ],
3657
+ [
3658
+ "an",
3659
+ "g"
3660
+ ],
3661
+ [
3662
+ "re",
3663
+ "sp"
3664
+ ],
3665
+ [
3666
+ "am",
3667
+ "i"
3668
+ ],
3669
+ [
3670
+ "m",
3671
+ "em"
3672
+ ],
3673
+ [
3674
+ "c",
3675
+ "lu"
3676
+ ],
3677
+ [
3678
+ "par",
3679
+ "t</w>"
3680
+ ],
3681
+ [
3682
+ "c",
3683
+ "ed</w>"
3684
+ ],
3685
+ [
3686
+ "c",
3687
+ "er"
3688
+ ],
3689
+ [
3690
+ "j",
3691
+ "e"
3692
+ ],
3693
+ [
3694
+ "t",
3695
+ "ru"
3696
+ ],
3697
+ [
3698
+ "en",
3699
+ "g"
3700
+ ],
3701
+ [
3702
+ "be",
3703
+ "fore</w>"
3704
+ ],
3705
+ [
3706
+ "kno",
3707
+ "wn</w>"
3708
+ ],
3709
+ [
3710
+ "amer",
3711
+ "ic"
3712
+ ],
3713
+ [
3714
+ "l",
3715
+ "ong</w>"
3716
+ ],
3717
+ [
3718
+ "n",
3719
+ "am"
3720
+ ],
3721
+ [
3722
+ "st",
3723
+ "an"
3724
+ ],
3725
+ [
3726
+ "st",
3727
+ "er</w>"
3728
+ ],
3729
+ [
3730
+ "al",
3731
+ "e</w>"
3732
+ ]
3733
+ ]
3734
+ }
3735
+ }
aimv2/Aimv2Model/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<start_of_text>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<end_of_text>",
6
+ "errors": "replace",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 77,
10
+ "pad_token": "<end_of_text>",
11
+ "processor_class": "CLIPProcessor",
12
+ "tokenizer_class": "CLIPTokenizer",
13
+ "unk_token": "<end_of_text>",
14
+ "use_fast": true
15
+ }
aimv2_text_model/Aimv2TextModel/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Aimv2TextModel"
4
+ ],
5
+ "attention_dropout": 0.1,
6
+ "dropout": 0.1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 1023,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 32,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 37,
13
+ "max_position_embeddings": 25,
14
+ "mlp_bias": false,
15
+ "model_type": "aimv2_text_model",
16
+ "num_attention_heads": 4,
17
+ "num_hidden_layers": 2,
18
+ "projection_dim": 32,
19
+ "qkv_bias": false,
20
+ "rms_norm_eps": 1e-05,
21
+ "transformers_version": "5.15.0.dev0",
22
+ "vocab_size": 1024
23
+ }
aimv2_text_model/Aimv2TextModel/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab767f1610ca035ead16c9ee6882e8d4e82bea835911bb8b5f790644c8ee282
3
+ size 198264
aimv2_text_model/Aimv2TextModel/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "data_format": "channels_first",
7
+ "default_to_square": false,
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessor",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 224
28
+ }
29
+ }
aimv2_text_model/Aimv2TextModel/tokenizer.json ADDED
@@ -0,0 +1,3735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<start_of_text>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<end_of_text>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": {
26
+ "type": "Sequence",
27
+ "normalizers": [
28
+ {
29
+ "type": "NFC"
30
+ },
31
+ {
32
+ "type": "Replace",
33
+ "pattern": {
34
+ "Regex": "\\s+"
35
+ },
36
+ "content": " "
37
+ },
38
+ {
39
+ "type": "Lowercase"
40
+ }
41
+ ]
42
+ },
43
+ "pre_tokenizer": {
44
+ "type": "Sequence",
45
+ "pretokenizers": [
46
+ {
47
+ "type": "Split",
48
+ "pattern": {
49
+ "Regex": "<\\|startoftext\\|>|<\\|endoftext\\|>|'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
50
+ },
51
+ "behavior": "Removed",
52
+ "invert": true
53
+ },
54
+ {
55
+ "type": "ByteLevel",
56
+ "add_prefix_space": false,
57
+ "trim_offsets": true,
58
+ "use_regex": true
59
+ }
60
+ ]
61
+ },
62
+ "post_processor": {
63
+ "type": "RobertaProcessing",
64
+ "sep": [
65
+ "<end_of_text>",
66
+ 1
67
+ ],
68
+ "cls": [
69
+ "<start_of_text>",
70
+ 0
71
+ ],
72
+ "trim_offsets": false,
73
+ "add_prefix_space": false
74
+ },
75
+ "decoder": {
76
+ "type": "ByteLevel",
77
+ "add_prefix_space": true,
78
+ "trim_offsets": true,
79
+ "use_regex": true
80
+ },
81
+ "model": {
82
+ "type": "BPE",
83
+ "dropout": null,
84
+ "unk_token": "<end_of_text>",
85
+ "continuing_subword_prefix": "",
86
+ "end_of_word_suffix": "</w>",
87
+ "fuse_unk": false,
88
+ "byte_fallback": false,
89
+ "ignore_merges": false,
90
+ "vocab": {
91
+ "<start_of_text>": 0,
92
+ "<end_of_text>": 1,
93
+ "!": 2,
94
+ "\"": 3,
95
+ "#": 4,
96
+ "$": 5,
97
+ "%": 6,
98
+ "&": 7,
99
+ "'": 8,
100
+ "(": 9,
101
+ ")": 10,
102
+ "*": 11,
103
+ "+": 12,
104
+ ",": 13,
105
+ "-": 14,
106
+ ".": 15,
107
+ "/": 16,
108
+ "0": 17,
109
+ "1": 18,
110
+ "2": 19,
111
+ "3": 20,
112
+ "4": 21,
113
+ "5": 22,
114
+ "6": 23,
115
+ "7": 24,
116
+ "8": 25,
117
+ "9": 26,
118
+ ":": 27,
119
+ ";": 28,
120
+ "<": 29,
121
+ "=": 30,
122
+ ">": 31,
123
+ "?": 32,
124
+ "@": 33,
125
+ "A": 34,
126
+ "B": 35,
127
+ "C": 36,
128
+ "D": 37,
129
+ "E": 38,
130
+ "F": 39,
131
+ "G": 40,
132
+ "H": 41,
133
+ "I": 42,
134
+ "J": 43,
135
+ "K": 44,
136
+ "L": 45,
137
+ "M": 46,
138
+ "N": 47,
139
+ "O": 48,
140
+ "P": 49,
141
+ "Q": 50,
142
+ "R": 51,
143
+ "S": 52,
144
+ "T": 53,
145
+ "U": 54,
146
+ "V": 55,
147
+ "W": 56,
148
+ "X": 57,
149
+ "Y": 58,
150
+ "Z": 59,
151
+ "[": 60,
152
+ "\\": 61,
153
+ "]": 62,
154
+ "^": 63,
155
+ "_": 64,
156
+ "`": 65,
157
+ "a": 66,
158
+ "b": 67,
159
+ "c": 68,
160
+ "d": 69,
161
+ "e": 70,
162
+ "f": 71,
163
+ "g": 72,
164
+ "h": 73,
165
+ "i": 74,
166
+ "j": 75,
167
+ "k": 76,
168
+ "l": 77,
169
+ "m": 78,
170
+ "n": 79,
171
+ "o": 80,
172
+ "p": 81,
173
+ "q": 82,
174
+ "r": 83,
175
+ "s": 84,
176
+ "t": 85,
177
+ "u": 86,
178
+ "v": 87,
179
+ "w": 88,
180
+ "x": 89,
181
+ "y": 90,
182
+ "z": 91,
183
+ "{": 92,
184
+ "|": 93,
185
+ "}": 94,
186
+ "~": 95,
187
+ "¡": 96,
188
+ "¢": 97,
189
+ "£": 98,
190
+ "¤": 99,
191
+ "¥": 100,
192
+ "¦": 101,
193
+ "§": 102,
194
+ "¨": 103,
195
+ "©": 104,
196
+ "ª": 105,
197
+ "«": 106,
198
+ "¬": 107,
199
+ "®": 108,
200
+ "¯": 109,
201
+ "°": 110,
202
+ "±": 111,
203
+ "²": 112,
204
+ "³": 113,
205
+ "´": 114,
206
+ "µ": 115,
207
+ "¶": 116,
208
+ "·": 117,
209
+ "¸": 118,
210
+ "¹": 119,
211
+ "º": 120,
212
+ "»": 121,
213
+ "¼": 122,
214
+ "½": 123,
215
+ "¾": 124,
216
+ "¿": 125,
217
+ "À": 126,
218
+ "Á": 127,
219
+ "Â": 128,
220
+ "Ã": 129,
221
+ "Ä": 130,
222
+ "Å": 131,
223
+ "Æ": 132,
224
+ "Ç": 133,
225
+ "È": 134,
226
+ "É": 135,
227
+ "Ê": 136,
228
+ "Ë": 137,
229
+ "Ì": 138,
230
+ "Í": 139,
231
+ "Î": 140,
232
+ "Ï": 141,
233
+ "Ð": 142,
234
+ "Ñ": 143,
235
+ "Ò": 144,
236
+ "Ó": 145,
237
+ "Ô": 146,
238
+ "Õ": 147,
239
+ "Ö": 148,
240
+ "×": 149,
241
+ "Ø": 150,
242
+ "Ù": 151,
243
+ "Ú": 152,
244
+ "Û": 153,
245
+ "Ü": 154,
246
+ "Ý": 155,
247
+ "Þ": 156,
248
+ "ß": 157,
249
+ "à": 158,
250
+ "á": 159,
251
+ "â": 160,
252
+ "ã": 161,
253
+ "ä": 162,
254
+ "å": 163,
255
+ "æ": 164,
256
+ "ç": 165,
257
+ "è": 166,
258
+ "é": 167,
259
+ "ê": 168,
260
+ "ë": 169,
261
+ "ì": 170,
262
+ "í": 171,
263
+ "î": 172,
264
+ "ï": 173,
265
+ "ð": 174,
266
+ "ñ": 175,
267
+ "ò": 176,
268
+ "ó": 177,
269
+ "ô": 178,
270
+ "õ": 179,
271
+ "ö": 180,
272
+ "÷": 181,
273
+ "ø": 182,
274
+ "ù": 183,
275
+ "ú": 184,
276
+ "û": 185,
277
+ "ü": 186,
278
+ "ý": 187,
279
+ "þ": 188,
280
+ "ÿ": 189,
281
+ "Ā": 190,
282
+ "ā": 191,
283
+ "Ă": 192,
284
+ "ă": 193,
285
+ "Ą": 194,
286
+ "ą": 195,
287
+ "Ć": 196,
288
+ "ć": 197,
289
+ "Ĉ": 198,
290
+ "ĉ": 199,
291
+ "Ċ": 200,
292
+ "ċ": 201,
293
+ "Č": 202,
294
+ "č": 203,
295
+ "Ď": 204,
296
+ "ď": 205,
297
+ "Đ": 206,
298
+ "đ": 207,
299
+ "Ē": 208,
300
+ "ē": 209,
301
+ "Ĕ": 210,
302
+ "ĕ": 211,
303
+ "Ė": 212,
304
+ "ė": 213,
305
+ "Ę": 214,
306
+ "ę": 215,
307
+ "Ě": 216,
308
+ "ě": 217,
309
+ "Ĝ": 218,
310
+ "ĝ": 219,
311
+ "Ğ": 220,
312
+ "ğ": 221,
313
+ "Ġ": 222,
314
+ "ġ": 223,
315
+ "Ģ": 224,
316
+ "ģ": 225,
317
+ "Ĥ": 226,
318
+ "ĥ": 227,
319
+ "Ħ": 228,
320
+ "ħ": 229,
321
+ "Ĩ": 230,
322
+ "ĩ": 231,
323
+ "Ī": 232,
324
+ "ī": 233,
325
+ "Ĭ": 234,
326
+ "ĭ": 235,
327
+ "Į": 236,
328
+ "į": 237,
329
+ "İ": 238,
330
+ "ı": 239,
331
+ "IJ": 240,
332
+ "ij": 241,
333
+ "Ĵ": 242,
334
+ "ĵ": 243,
335
+ "Ķ": 244,
336
+ "ķ": 245,
337
+ "ĸ": 246,
338
+ "Ĺ": 247,
339
+ "ĺ": 248,
340
+ "Ļ": 249,
341
+ "ļ": 250,
342
+ "Ľ": 251,
343
+ "ľ": 252,
344
+ "Ŀ": 253,
345
+ "ŀ": 254,
346
+ "Ł": 255,
347
+ "ł": 256,
348
+ "Ń": 257,
349
+ "a</w>": 258,
350
+ "g</w>": 259,
351
+ "d</w>": 260,
352
+ "s</w>": 261,
353
+ "e</w>": 262,
354
+ "n</w>": 263,
355
+ "t</w>": 264,
356
+ "y</w>": 265,
357
+ "Ĥ</w>": 266,
358
+ "p</w>": 267,
359
+ "r</w>": 268,
360
+ "k</w>": 269,
361
+ "l</w>": 270,
362
+ "b</w>": 271,
363
+ "w</w>": 272,
364
+ "i</w>": 273,
365
+ "f</w>": 274,
366
+ "h</w>": 275,
367
+ "m</w>": 276,
368
+ "c</w>": 277,
369
+ "v</w>": 278,
370
+ "o</w>": 279,
371
+ "x</w>": 280,
372
+ "´</w>": 281,
373
+ "u</w>": 282,
374
+ "~</w>": 283,
375
+ "&</w>": 284,
376
+ "ŀ</w>": 285,
377
+ "Ħ</w>": 286,
378
+ "Ļ</w>": 287,
379
+ "z</w>": 288,
380
+ "Ĵ</w>": 289,
381
+ "±</w>": 290,
382
+ "8</w>": 291,
383
+ "6</w>": 292,
384
+ "Ķ</w>": 293,
385
+ ".</w>": 294,
386
+ "į</w>": 295,
387
+ "µ</w>": 296,
388
+ "j</w>": 297,
389
+ "³</w>": 298,
390
+ "¾</w>": 299,
391
+ "9</w>": 300,
392
+ "¹</w>": 301,
393
+ "Ĭ</w>": 302,
394
+ "²</w>": 303,
395
+ "Ĺ</w>": 304,
396
+ "q</w>": 305,
397
+ ")</w>": 306,
398
+ "§</w>": 307,
399
+ "*</w>": 308,
400
+ "¯</w>": 309,
401
+ "©</w>": 310,
402
+ "ģ</w>": 311,
403
+ "#</w>": 312,
404
+ "2</w>": 313,
405
+ "ķ</w>": 314,
406
+ "¶</w>": 315,
407
+ "ĵ</w>": 316,
408
+ "ļ</w>": 317,
409
+ "¡</w>": 318,
410
+ "¨</w>": 319,
411
+ "7</w>": 320,
412
+ "¢</w>": 321,
413
+ "%</w>": 322,
414
+ "!</w>": 323,
415
+ "Ī</w>": 324,
416
+ ";</w>": 325,
417
+ "ľ</w>": 326,
418
+ "ł</w>": 327,
419
+ "ª</w>": 328,
420
+ "Ŀ</w>": 329,
421
+ "½</w>": 330,
422
+ "ħ</w>": 331,
423
+ "£</w>": 332,
424
+ "5</w>": 333,
425
+ "Ń</w>": 334,
426
+ "`</w>": 335,
427
+ "ĩ</w>": 336,
428
+ "Į</w>": 337,
429
+ "/</w>": 338,
430
+ "·</w>": 339,
431
+ "ī</w>": 340,
432
+ "Ľ</w>": 341,
433
+ "></w>": 342,
434
+ "İ</w>": 343,
435
+ "'</w>": 344,
436
+ "=</w>": 345,
437
+ "\"</w>": 346,
438
+ "°</w>": 347,
439
+ "+</w>": 348,
440
+ "IJ</w>": 349,
441
+ "º</w>": 350,
442
+ "]</w>": 351,
443
+ "3</w>": 352,
444
+ "@</w>": 353,
445
+ "4</w>": 354,
446
+ ":</w>": 355,
447
+ "<</w>": 356,
448
+ "-</w>": 357,
449
+ "$</w>": 358,
450
+ "¤</w>": 359,
451
+ "?</w>": 360,
452
+ "ĺ</w>": 361,
453
+ "^</w>": 362,
454
+ "¦</w>": 363,
455
+ ",</w>": 364,
456
+ "ĭ</w>": 365,
457
+ "(</w>": 366,
458
+ "0</w>": 367,
459
+ "1</w>": 368,
460
+ "[</w>": 369,
461
+ "th": 370,
462
+ "the</w>": 371,
463
+ "in": 372,
464
+ "an": 373,
465
+ "ed</w>": 374,
466
+ "er": 375,
467
+ "re": 376,
468
+ "ti": 377,
469
+ "ar": 378,
470
+ "or": 379,
471
+ "on": 380,
472
+ "of</w>": 381,
473
+ "en": 382,
474
+ "and</w>": 383,
475
+ "er</w>": 384,
476
+ "on</w>": 385,
477
+ "in</w>": 386,
478
+ "st": 387,
479
+ "al": 388,
480
+ "ing</w>": 389,
481
+ "it": 390,
482
+ "ro": 391,
483
+ "as</w>": 392,
484
+ "to</w>": 393,
485
+ "at": 394,
486
+ "es</w>": 395,
487
+ "hi": 396,
488
+ "ou": 397,
489
+ "al</w>": 398,
490
+ "an</w>": 399,
491
+ "ac": 400,
492
+ "at</w>": 401,
493
+ "li": 402,
494
+ "si": 403,
495
+ "ri": 404,
496
+ "el": 405,
497
+ "or</w>": 406,
498
+ "as": 407,
499
+ "de": 408,
500
+ "ur": 409,
501
+ "co": 410,
502
+ "am": 411,
503
+ "di": 412,
504
+ "ch": 413,
505
+ "was</w>": 414,
506
+ "tion</w>": 415,
507
+ "le": 416,
508
+ "st</w>": 417,
509
+ "ly</w>": 418,
510
+ "se": 419,
511
+ "lo": 420,
512
+ "un": 421,
513
+ "-@</w>": 422,
514
+ "@-@</w>": 423,
515
+ "is</w>": 424,
516
+ "be": 425,
517
+ "fi": 426,
518
+ "en</w>": 427,
519
+ "la": 428,
520
+ "ra": 429,
521
+ "le</w>": 430,
522
+ "con": 431,
523
+ "sh": 432,
524
+ "po": 433,
525
+ "that</w>": 434,
526
+ "wit": 435,
527
+ "vi": 436,
528
+ "for</w>": 437,
529
+ "with</w>": 438,
530
+ "ch</w>": 439,
531
+ "em": 440,
532
+ "ma": 441,
533
+ "'s</w>": 442,
534
+ "su": 443,
535
+ "ts</w>": 444,
536
+ "ve</w>": 445,
537
+ "by</w>": 446,
538
+ "ent</w>": 447,
539
+ "the": 448,
540
+ "ha": 449,
541
+ "ci": 450,
542
+ "pro": 451,
543
+ "ere</w>": 452,
544
+ "com": 453,
545
+ "ag": 454,
546
+ "ce</w>": 455,
547
+ "bu": 456,
548
+ "il": 457,
549
+ "no": 458,
550
+ "wh": 459,
551
+ "is": 460,
552
+ "sp": 461,
553
+ "ne": 462,
554
+ "ol": 463,
555
+ "ca": 464,
556
+ "ted</w>": 465,
557
+ "it</w>": 466,
558
+ "ers</w>": 467,
559
+ "tion": 468,
560
+ "he</w>": 469,
561
+ "se</w>": 470,
562
+ "gh": 471,
563
+ "for": 472,
564
+ "his</w>": 473,
565
+ "ru": 474,
566
+ "th</w>": 475,
567
+ "ver": 476,
568
+ "ad": 477,
569
+ "to": 478,
570
+ "mo": 479,
571
+ "ex": 480,
572
+ "fro": 481,
573
+ "from</w>": 482,
574
+ "ab": 483,
575
+ "whi": 484,
576
+ "per": 485,
577
+ "cu": 486,
578
+ "ea": 487,
579
+ "ds</w>": 488,
580
+ "were</w>": 489,
581
+ "ic": 490,
582
+ "om": 491,
583
+ "ap": 492,
584
+ "ity</w>": 493,
585
+ "ation</w>": 494,
586
+ "ter</w>": 495,
587
+ "pre": 496,
588
+ "oun": 497,
589
+ "ai": 498,
590
+ "fe": 499,
591
+ "lu": 500,
592
+ "ter": 501,
593
+ "ated</w>": 502,
594
+ "de</w>": 503,
595
+ "du": 504,
596
+ "go": 505,
597
+ "bo": 506,
598
+ "all</w>": 507,
599
+ "we": 508,
600
+ "ate</w>": 509,
601
+ "tim": 510,
602
+ "rec": 511,
603
+ "are</w>": 512,
604
+ "qu": 513,
605
+ "ther</w>": 514,
606
+ "man": 515,
607
+ "ding</w>": 516,
608
+ "me": 517,
609
+ "op": 518,
610
+ "gu": 519,
611
+ "par": 520,
612
+ "tr": 521,
613
+ "one</w>": 522,
614
+ "which</w>": 523,
615
+ "gi": 524,
616
+ "ec": 525,
617
+ "âĢ": 526,
618
+ "ded</w>": 527,
619
+ "ss</w>": 528,
620
+ "por": 529,
621
+ "ame</w>": 530,
622
+ "had</w>": 531,
623
+ "wor": 532,
624
+ "af": 533,
625
+ "der": 534,
626
+ "ver</w>": 535,
627
+ "ing": 536,
628
+ "sc": 537,
629
+ "ear": 538,
630
+ "be</w>": 539,
631
+ "ho": 540,
632
+ "so</w>": 541,
633
+ "tions</w>": 542,
634
+ "ta": 543,
635
+ "ber</w>": 544,
636
+ "ld</w>": 545,
637
+ "wa": 546,
638
+ "mu": 547,
639
+ "ni": 548,
640
+ "sed</w>": 549,
641
+ "mar": 550,
642
+ "tur": 551,
643
+ "ally</w>": 552,
644
+ "of": 553,
645
+ "pu": 554,
646
+ "ght</w>": 555,
647
+ "shi": 556,
648
+ "mi": 557,
649
+ "tw": 558,
650
+ "est": 559,
651
+ "out</w>": 560,
652
+ "its</w>": 561,
653
+ "gh</w>": 562,
654
+ "fir": 563,
655
+ "her</w>": 564,
656
+ "ir</w>": 565,
657
+ "um": 566,
658
+ "ce": 567,
659
+ "pla": 568,
660
+ "this</w>": 569,
661
+ "wn</w>": 570,
662
+ "au": 571,
663
+ "rou": 572,
664
+ "pl": 573,
665
+ "she</w>": 574,
666
+ "âĢĵ</w>": 575,
667
+ "ke</w>": 576,
668
+ "inc": 577,
669
+ "im": 578,
670
+ "also</w>": 579,
671
+ "der</w>": 580,
672
+ "ge</w>": 581,
673
+ "na": 582,
674
+ "ine</w>": 583,
675
+ "their</w>": 584,
676
+ "ong</w>": 585,
677
+ "pe": 586,
678
+ "ser": 587,
679
+ "ved</w>": 588,
680
+ "ary</w>": 589,
681
+ "sen": 590,
682
+ "ment</w>": 591,
683
+ "fin": 592,
684
+ "has</w>": 593,
685
+ "ting</w>": 594,
686
+ "do": 595,
687
+ "sh</w>": 596,
688
+ "not</w>": 597,
689
+ "te</w>": 598,
690
+ "ran": 599,
691
+ "sa": 600,
692
+ "mor": 601,
693
+ "ori": 602,
694
+ "min": 603,
695
+ "led</w>": 604,
696
+ ".@</w>": 605,
697
+ "@.@</w>": 606,
698
+ "but</w>": 607,
699
+ "after</w>": 608,
700
+ "two</w>": 609,
701
+ "first</w>": 610,
702
+ "sti": 611,
703
+ "so": 612,
704
+ "ir": 613,
705
+ "fer": 614,
706
+ "other</w>": 615,
707
+ "ty</w>": 616,
708
+ "ents</w>": 617,
709
+ "they</w>": 618,
710
+ "comm": 619,
711
+ "tu": 620,
712
+ "wi": 621,
713
+ "ge": 622,
714
+ "te": 623,
715
+ "have</w>": 624,
716
+ "ned</w>": 625,
717
+ "ten": 626,
718
+ "ss": 627,
719
+ "ould</w>": 628,
720
+ "who</w>": 629,
721
+ "pi": 630,
722
+ "da": 631,
723
+ "ast</w>": 632,
724
+ "ties</w>": 633,
725
+ "lar": 634,
726
+ "son</w>": 635,
727
+ "war": 636,
728
+ "sho": 637,
729
+ "ke": 638,
730
+ "char": 639,
731
+ "been</w>": 640,
732
+ "our": 641,
733
+ ",@</w>": 642,
734
+ "@,@</w>": 643,
735
+ "man</w>": 644,
736
+ "new</w>": 645,
737
+ "ks</w>": 646,
738
+ "mon": 647,
739
+ "sion</w>": 648,
740
+ "gen": 649,
741
+ "ory</w>": 650,
742
+ "uring</w>": 651,
743
+ "ar</w>": 652,
744
+ "gre": 653,
745
+ "ater</w>": 654,
746
+ "low": 655,
747
+ "ant</w>": 656,
748
+ "sig": 657,
749
+ "ely</w>": 658,
750
+ "ft</w>": 659,
751
+ "cont": 660,
752
+ "fu": 661,
753
+ "rit": 662,
754
+ "age</w>": 663,
755
+ "ous</w>": 664,
756
+ "cre": 665,
757
+ "cen": 666,
758
+ "ste": 667,
759
+ "el</w>": 668,
760
+ "duc": 669,
761
+ "us</w>": 670,
762
+ "poli": 671,
763
+ "tional</w>": 672,
764
+ "ome</w>": 673,
765
+ "time</w>": 674,
766
+ "tra": 675,
767
+ "ali": 676,
768
+ "play": 677,
769
+ "king</w>": 678,
770
+ "spe": 679,
771
+ "our</w>": 680,
772
+ "oc": 681,
773
+ "ited</w>": 682,
774
+ "fil": 683,
775
+ "air": 684,
776
+ "bri": 685,
777
+ "als</w>": 686,
778
+ "ev": 687,
779
+ "oo": 688,
780
+ "ari": 689,
781
+ "inter": 690,
782
+ "tic": 691,
783
+ "uni": 692,
784
+ "gra": 693,
785
+ "lar</w>": 694,
786
+ "seas": 695,
787
+ "during</w>": 696,
788
+ "stru": 697,
789
+ "res</w>": 698,
790
+ "nor": 699,
791
+ "pp": 700,
792
+ "jo": 701,
793
+ "thou": 702,
794
+ "ember</w>": 703,
795
+ "land</w>": 704,
796
+ "ord": 705,
797
+ "ck</w>": 706,
798
+ "ite</w>": 707,
799
+ "inclu": 708,
800
+ "ance</w>": 709,
801
+ "str": 710,
802
+ "pri": 711,
803
+ "ure</w>": 712,
804
+ "tive</w>": 713,
805
+ "att": 714,
806
+ "ree</w>": 715,
807
+ "ack</w>": 716,
808
+ "col": 717,
809
+ "cul": 718,
810
+ "more</w>": 719,
811
+ "bli": 720,
812
+ "gro": 721,
813
+ "ased</w>": 722,
814
+ "ps</w>": 723,
815
+ "than</w>": 724,
816
+ "form": 725,
817
+ "yp": 726,
818
+ "comp": 727,
819
+ "recor": 728,
820
+ "cor": 729,
821
+ "ell</w>": 730,
822
+ "most</w>": 731,
823
+ "ates</w>": 732,
824
+ "ins</w>": 733,
825
+ "ined</w>": 734,
826
+ "chi": 735,
827
+ "publi": 736,
828
+ "way</w>": 737,
829
+ "et</w>": 738,
830
+ "car": 739,
831
+ "les</w>": 740,
832
+ "ad</w>": 741,
833
+ "ces</w>": 742,
834
+ "sch": 743,
835
+ "speci": 744,
836
+ "ons</w>": 745,
837
+ "ence</w>": 746,
838
+ "albu": 747,
839
+ "ves</w>": 748,
840
+ "ear</w>": 749,
841
+ "ren": 750,
842
+ "cha": 751,
843
+ "ship</w>": 752,
844
+ "ju": 753,
845
+ "ound</w>": 754,
846
+ "old</w>": 755,
847
+ "ked</w>": 756,
848
+ "and": 757,
849
+ "ace</w>": 758,
850
+ "season</w>": 759,
851
+ "sel": 760,
852
+ "able</w>": 761,
853
+ "indi": 762,
854
+ "ph": 763,
855
+ "tri": 764,
856
+ "ei": 765,
857
+ "city</w>": 766,
858
+ "cau": 767,
859
+ "mil": 768,
860
+ "bi": 769,
861
+ "tly</w>": 770,
862
+ "into</w>": 771,
863
+ "cl": 772,
864
+ "red</w>": 773,
865
+ "ls</w>": 774,
866
+ "sou": 775,
867
+ "ase</w>": 776,
868
+ "ings</w>": 777,
869
+ "ving</w>": 778,
870
+ "ach": 779,
871
+ "sy": 780,
872
+ "when</w>": 781,
873
+ "olo": 782,
874
+ "over</w>": 783,
875
+ "hist": 784,
876
+ "though</w>": 785,
877
+ "end</w>": 786,
878
+ "tic</w>": 787,
879
+ "dis": 788,
880
+ "secon": 789,
881
+ "can": 790,
882
+ "sur": 791,
883
+ "only</w>": 792,
884
+ "may</w>": 793,
885
+ "ordan</w>": 794,
886
+ "coun": 795,
887
+ "jordan</w>": 796,
888
+ "ms</w>": 797,
889
+ "ans</w>": 798,
890
+ "album</w>": 799,
891
+ "ern</w>": 800,
892
+ "ble</w>": 801,
893
+ "re</w>": 802,
894
+ "wn": 803,
895
+ "ach</w>": 804,
896
+ "ames</w>": 805,
897
+ "ok</w>": 806,
898
+ "ys</w>": 807,
899
+ "up</w>": 808,
900
+ "there</w>": 809,
901
+ "sub": 810,
902
+ "eg": 811,
903
+ "num": 812,
904
+ "many</w>": 813,
905
+ "three</w>": 814,
906
+ "gin": 815,
907
+ "rele": 816,
908
+ "shed</w>": 817,
909
+ "aga": 818,
910
+ "gal": 819,
911
+ "kno": 820,
912
+ "od</w>": 821,
913
+ "while</w>": 822,
914
+ "year</w>": 823,
915
+ "ors</w>": 824,
916
+ "ning</w>": 825,
917
+ "pa": 826,
918
+ "later</w>": 827,
919
+ "ve": 828,
920
+ "no</w>": 829,
921
+ "throu": 830,
922
+ "ying</w>": 831,
923
+ "emp": 832,
924
+ "ations</w>": 833,
925
+ "ic</w>": 834,
926
+ "vie": 835,
927
+ "whe": 836,
928
+ "ssi": 837,
929
+ "came</w>": 838,
930
+ "sic</w>": 839,
931
+ "fa": 840,
932
+ "bet": 841,
933
+ "war</w>": 842,
934
+ "bro": 843,
935
+ "would</w>": 844,
936
+ "some</w>": 845,
937
+ "ll</w>": 846,
938
+ "dev": 847,
939
+ "ical</w>": 848,
940
+ "sk": 849,
941
+ "produc": 850,
942
+ "port</w>": 851,
943
+ "scri": 852,
944
+ "buil": 853,
945
+ "bar": 854,
946
+ "game</w>": 855,
947
+ "film</w>": 856,
948
+ "ba": 857,
949
+ "tho": 858,
950
+ "loc": 859,
951
+ "being</w>": 860,
952
+ "these</w>": 861,
953
+ "about</w>": 862,
954
+ "soci": 863,
955
+ "sing</w>": 864,
956
+ "lan": 865,
957
+ "tre": 866,
958
+ "ten</w>": 867,
959
+ "writ": 868,
960
+ "fol": 869,
961
+ "ard</w>": 870,
962
+ "ue</w>": 871,
963
+ "eam</w>": 872,
964
+ "sts</w>": 873,
965
+ "him</w>": 874,
966
+ "app": 875,
967
+ "ger": 876,
968
+ "them</w>": 877,
969
+ "struc": 878,
970
+ "offi": 879,
971
+ "my</w>": 880,
972
+ "ani": 881,
973
+ "day</w>": 882,
974
+ "dy</w>": 883,
975
+ "he": 884,
976
+ "um</w>": 885,
977
+ "stri": 886,
978
+ "stu": 887,
979
+ "ele": 888,
980
+ "wheel": 889,
981
+ "cra": 890,
982
+ "second</w>": 891,
983
+ "ong": 892,
984
+ "side</w>": 893,
985
+ "such</w>": 894,
986
+ "team</w>": 895,
987
+ "ating</w>": 896,
988
+ "can</w>": 897,
989
+ "fac": 898,
990
+ "mis": 899,
991
+ "wheeler</w>": 900,
992
+ "den": 901,
993
+ "me</w>": 902,
994
+ "cri": 903,
995
+ "chri": 904,
996
+ "ween</w>": 905,
997
+ "chae": 906,
998
+ "ga": 907,
999
+ "ling</w>": 908,
1000
+ "ses</w>": 909,
1001
+ "between</w>": 910,
1002
+ "mat": 911,
1003
+ "vest": 912,
1004
+ "poin": 913,
1005
+ "gener": 914,
1006
+ "cal": 915,
1007
+ "wil": 916,
1008
+ "tish</w>": 917,
1009
+ "archae": 918,
1010
+ "ears</w>": 919,
1011
+ "archaeolo": 920,
1012
+ "jec": 921,
1013
+ "tal</w>": 922,
1014
+ "und</w>": 923,
1015
+ "sin": 924,
1016
+ "ven": 925,
1017
+ "made</w>": 926,
1018
+ "sul": 927,
1019
+ "ture</w>": 928,
1020
+ "oper": 929,
1021
+ "ven</w>": 930,
1022
+ "ws</w>": 931,
1023
+ "where</w>": 932,
1024
+ "ron": 933,
1025
+ "consi": 934,
1026
+ "four</w>": 935,
1027
+ "ton</w>": 936,
1028
+ "ob": 937,
1029
+ "wer</w>": 938,
1030
+ "sever": 939,
1031
+ "under</w>": 940,
1032
+ "work</w>": 941,
1033
+ "amer": 942,
1034
+ "cap": 943,
1035
+ "national</w>": 944,
1036
+ "with": 945,
1037
+ "fore</w>": 946,
1038
+ "then</w>": 947,
1039
+ "although</w>": 948,
1040
+ "sm": 949,
1041
+ "ony</w>": 950,
1042
+ "eld</w>": 951,
1043
+ "chur": 952,
1044
+ "british</w>": 953,
1045
+ "galvest": 954,
1046
+ "both</w>": 955,
1047
+ "ber": 956,
1048
+ "sted</w>": 957,
1049
+ "direc": 958,
1050
+ "galveston</w>": 959,
1051
+ "fe</w>": 960,
1052
+ "well</w>": 961,
1053
+ "dre": 962,
1054
+ "yor": 963,
1055
+ "nov": 964,
1056
+ "lit": 965,
1057
+ "tro": 966,
1058
+ "descri": 967,
1059
+ "cation</w>": 968,
1060
+ "aid</w>": 969,
1061
+ "tran": 970,
1062
+ "ini": 971,
1063
+ "state</w>": 972,
1064
+ "peri": 973,
1065
+ "des</w>": 974,
1066
+ "est</w>": 975,
1067
+ "hea": 976,
1068
+ "pen": 977,
1069
+ "years</w>": 978,
1070
+ "world</w>": 979,
1071
+ "ies</w>": 980,
1072
+ "used</w>": 981,
1073
+ "gods</w>": 982,
1074
+ "ters</w>": 983,
1075
+ "dif": 984,
1076
+ "follow": 985,
1077
+ "are": 986,
1078
+ "es": 987,
1079
+ "gan</w>": 988,
1080
+ "star": 989,
1081
+ "like</w>": 990,
1082
+ "early</w>": 991,
1083
+ "men": 992,
1084
+ "sing": 993,
1085
+ "bor": 994,
1086
+ "tor</w>": 995,
1087
+ "music</w>": 996,
1088
+ "clas": 997,
1089
+ "several</w>": 998,
1090
+ "united</w>": 999,
1091
+ "number</w>": 1000,
1092
+ "church</w>": 1001,
1093
+ "york</w>": 1002,
1094
+ "cur": 1003,
1095
+ "clo": 1004,
1096
+ "ang": 1005,
1097
+ "resp": 1006,
1098
+ "ami": 1007,
1099
+ "mem": 1008,
1100
+ "clu": 1009,
1101
+ "part</w>": 1010,
1102
+ "ced</w>": 1011,
1103
+ "cer": 1012,
1104
+ "je": 1013,
1105
+ "tru": 1014,
1106
+ "eng": 1015,
1107
+ "before</w>": 1016,
1108
+ "known</w>": 1017,
1109
+ "americ": 1018,
1110
+ "long</w>": 1019,
1111
+ "nam": 1020,
1112
+ "stan": 1021,
1113
+ "ster</w>": 1022,
1114
+ "ale</w>": 1023
1115
+ },
1116
+ "merges": [
1117
+ [
1118
+ "t",
1119
+ "h"
1120
+ ],
1121
+ [
1122
+ "th",
1123
+ "e</w>"
1124
+ ],
1125
+ [
1126
+ "i",
1127
+ "n"
1128
+ ],
1129
+ [
1130
+ "a",
1131
+ "n"
1132
+ ],
1133
+ [
1134
+ "e",
1135
+ "d</w>"
1136
+ ],
1137
+ [
1138
+ "e",
1139
+ "r"
1140
+ ],
1141
+ [
1142
+ "r",
1143
+ "e"
1144
+ ],
1145
+ [
1146
+ "t",
1147
+ "i"
1148
+ ],
1149
+ [
1150
+ "a",
1151
+ "r"
1152
+ ],
1153
+ [
1154
+ "o",
1155
+ "r"
1156
+ ],
1157
+ [
1158
+ "o",
1159
+ "n"
1160
+ ],
1161
+ [
1162
+ "o",
1163
+ "f</w>"
1164
+ ],
1165
+ [
1166
+ "e",
1167
+ "n"
1168
+ ],
1169
+ [
1170
+ "an",
1171
+ "d</w>"
1172
+ ],
1173
+ [
1174
+ "e",
1175
+ "r</w>"
1176
+ ],
1177
+ [
1178
+ "o",
1179
+ "n</w>"
1180
+ ],
1181
+ [
1182
+ "i",
1183
+ "n</w>"
1184
+ ],
1185
+ [
1186
+ "s",
1187
+ "t"
1188
+ ],
1189
+ [
1190
+ "a",
1191
+ "l"
1192
+ ],
1193
+ [
1194
+ "in",
1195
+ "g</w>"
1196
+ ],
1197
+ [
1198
+ "i",
1199
+ "t"
1200
+ ],
1201
+ [
1202
+ "r",
1203
+ "o"
1204
+ ],
1205
+ [
1206
+ "a",
1207
+ "s</w>"
1208
+ ],
1209
+ [
1210
+ "t",
1211
+ "o</w>"
1212
+ ],
1213
+ [
1214
+ "a",
1215
+ "t"
1216
+ ],
1217
+ [
1218
+ "e",
1219
+ "s</w>"
1220
+ ],
1221
+ [
1222
+ "h",
1223
+ "i"
1224
+ ],
1225
+ [
1226
+ "o",
1227
+ "u"
1228
+ ],
1229
+ [
1230
+ "a",
1231
+ "l</w>"
1232
+ ],
1233
+ [
1234
+ "a",
1235
+ "n</w>"
1236
+ ],
1237
+ [
1238
+ "a",
1239
+ "c"
1240
+ ],
1241
+ [
1242
+ "a",
1243
+ "t</w>"
1244
+ ],
1245
+ [
1246
+ "l",
1247
+ "i"
1248
+ ],
1249
+ [
1250
+ "s",
1251
+ "i"
1252
+ ],
1253
+ [
1254
+ "r",
1255
+ "i"
1256
+ ],
1257
+ [
1258
+ "e",
1259
+ "l"
1260
+ ],
1261
+ [
1262
+ "o",
1263
+ "r</w>"
1264
+ ],
1265
+ [
1266
+ "a",
1267
+ "s"
1268
+ ],
1269
+ [
1270
+ "d",
1271
+ "e"
1272
+ ],
1273
+ [
1274
+ "u",
1275
+ "r"
1276
+ ],
1277
+ [
1278
+ "c",
1279
+ "o"
1280
+ ],
1281
+ [
1282
+ "a",
1283
+ "m"
1284
+ ],
1285
+ [
1286
+ "d",
1287
+ "i"
1288
+ ],
1289
+ [
1290
+ "c",
1291
+ "h"
1292
+ ],
1293
+ [
1294
+ "w",
1295
+ "as</w>"
1296
+ ],
1297
+ [
1298
+ "ti",
1299
+ "on</w>"
1300
+ ],
1301
+ [
1302
+ "l",
1303
+ "e"
1304
+ ],
1305
+ [
1306
+ "s",
1307
+ "t</w>"
1308
+ ],
1309
+ [
1310
+ "l",
1311
+ "y</w>"
1312
+ ],
1313
+ [
1314
+ "s",
1315
+ "e"
1316
+ ],
1317
+ [
1318
+ "l",
1319
+ "o"
1320
+ ],
1321
+ [
1322
+ "u",
1323
+ "n"
1324
+ ],
1325
+ [
1326
+ "-",
1327
+ "@</w>"
1328
+ ],
1329
+ [
1330
+ "@",
1331
+ "-@</w>"
1332
+ ],
1333
+ [
1334
+ "i",
1335
+ "s</w>"
1336
+ ],
1337
+ [
1338
+ "b",
1339
+ "e"
1340
+ ],
1341
+ [
1342
+ "f",
1343
+ "i"
1344
+ ],
1345
+ [
1346
+ "e",
1347
+ "n</w>"
1348
+ ],
1349
+ [
1350
+ "l",
1351
+ "a"
1352
+ ],
1353
+ [
1354
+ "r",
1355
+ "a"
1356
+ ],
1357
+ [
1358
+ "l",
1359
+ "e</w>"
1360
+ ],
1361
+ [
1362
+ "c",
1363
+ "on"
1364
+ ],
1365
+ [
1366
+ "s",
1367
+ "h"
1368
+ ],
1369
+ [
1370
+ "p",
1371
+ "o"
1372
+ ],
1373
+ [
1374
+ "th",
1375
+ "at</w>"
1376
+ ],
1377
+ [
1378
+ "w",
1379
+ "it"
1380
+ ],
1381
+ [
1382
+ "v",
1383
+ "i"
1384
+ ],
1385
+ [
1386
+ "f",
1387
+ "or</w>"
1388
+ ],
1389
+ [
1390
+ "wit",
1391
+ "h</w>"
1392
+ ],
1393
+ [
1394
+ "c",
1395
+ "h</w>"
1396
+ ],
1397
+ [
1398
+ "e",
1399
+ "m"
1400
+ ],
1401
+ [
1402
+ "m",
1403
+ "a"
1404
+ ],
1405
+ [
1406
+ "'",
1407
+ "s</w>"
1408
+ ],
1409
+ [
1410
+ "s",
1411
+ "u"
1412
+ ],
1413
+ [
1414
+ "t",
1415
+ "s</w>"
1416
+ ],
1417
+ [
1418
+ "v",
1419
+ "e</w>"
1420
+ ],
1421
+ [
1422
+ "b",
1423
+ "y</w>"
1424
+ ],
1425
+ [
1426
+ "en",
1427
+ "t</w>"
1428
+ ],
1429
+ [
1430
+ "th",
1431
+ "e"
1432
+ ],
1433
+ [
1434
+ "h",
1435
+ "a"
1436
+ ],
1437
+ [
1438
+ "c",
1439
+ "i"
1440
+ ],
1441
+ [
1442
+ "p",
1443
+ "ro"
1444
+ ],
1445
+ [
1446
+ "er",
1447
+ "e</w>"
1448
+ ],
1449
+ [
1450
+ "co",
1451
+ "m"
1452
+ ],
1453
+ [
1454
+ "a",
1455
+ "g"
1456
+ ],
1457
+ [
1458
+ "c",
1459
+ "e</w>"
1460
+ ],
1461
+ [
1462
+ "b",
1463
+ "u"
1464
+ ],
1465
+ [
1466
+ "i",
1467
+ "l"
1468
+ ],
1469
+ [
1470
+ "n",
1471
+ "o"
1472
+ ],
1473
+ [
1474
+ "w",
1475
+ "h"
1476
+ ],
1477
+ [
1478
+ "i",
1479
+ "s"
1480
+ ],
1481
+ [
1482
+ "s",
1483
+ "p"
1484
+ ],
1485
+ [
1486
+ "n",
1487
+ "e"
1488
+ ],
1489
+ [
1490
+ "o",
1491
+ "l"
1492
+ ],
1493
+ [
1494
+ "c",
1495
+ "a"
1496
+ ],
1497
+ [
1498
+ "t",
1499
+ "ed</w>"
1500
+ ],
1501
+ [
1502
+ "i",
1503
+ "t</w>"
1504
+ ],
1505
+ [
1506
+ "er",
1507
+ "s</w>"
1508
+ ],
1509
+ [
1510
+ "ti",
1511
+ "on"
1512
+ ],
1513
+ [
1514
+ "h",
1515
+ "e</w>"
1516
+ ],
1517
+ [
1518
+ "s",
1519
+ "e</w>"
1520
+ ],
1521
+ [
1522
+ "g",
1523
+ "h"
1524
+ ],
1525
+ [
1526
+ "f",
1527
+ "or"
1528
+ ],
1529
+ [
1530
+ "hi",
1531
+ "s</w>"
1532
+ ],
1533
+ [
1534
+ "r",
1535
+ "u"
1536
+ ],
1537
+ [
1538
+ "t",
1539
+ "h</w>"
1540
+ ],
1541
+ [
1542
+ "v",
1543
+ "er"
1544
+ ],
1545
+ [
1546
+ "a",
1547
+ "d"
1548
+ ],
1549
+ [
1550
+ "t",
1551
+ "o"
1552
+ ],
1553
+ [
1554
+ "m",
1555
+ "o"
1556
+ ],
1557
+ [
1558
+ "e",
1559
+ "x"
1560
+ ],
1561
+ [
1562
+ "f",
1563
+ "ro"
1564
+ ],
1565
+ [
1566
+ "fro",
1567
+ "m</w>"
1568
+ ],
1569
+ [
1570
+ "a",
1571
+ "b"
1572
+ ],
1573
+ [
1574
+ "w",
1575
+ "hi"
1576
+ ],
1577
+ [
1578
+ "p",
1579
+ "er"
1580
+ ],
1581
+ [
1582
+ "c",
1583
+ "u"
1584
+ ],
1585
+ [
1586
+ "e",
1587
+ "a"
1588
+ ],
1589
+ [
1590
+ "d",
1591
+ "s</w>"
1592
+ ],
1593
+ [
1594
+ "w",
1595
+ "ere</w>"
1596
+ ],
1597
+ [
1598
+ "i",
1599
+ "c"
1600
+ ],
1601
+ [
1602
+ "o",
1603
+ "m"
1604
+ ],
1605
+ [
1606
+ "a",
1607
+ "p"
1608
+ ],
1609
+ [
1610
+ "it",
1611
+ "y</w>"
1612
+ ],
1613
+ [
1614
+ "a",
1615
+ "tion</w>"
1616
+ ],
1617
+ [
1618
+ "t",
1619
+ "er</w>"
1620
+ ],
1621
+ [
1622
+ "p",
1623
+ "re"
1624
+ ],
1625
+ [
1626
+ "ou",
1627
+ "n"
1628
+ ],
1629
+ [
1630
+ "a",
1631
+ "i"
1632
+ ],
1633
+ [
1634
+ "f",
1635
+ "e"
1636
+ ],
1637
+ [
1638
+ "l",
1639
+ "u"
1640
+ ],
1641
+ [
1642
+ "t",
1643
+ "er"
1644
+ ],
1645
+ [
1646
+ "at",
1647
+ "ed</w>"
1648
+ ],
1649
+ [
1650
+ "d",
1651
+ "e</w>"
1652
+ ],
1653
+ [
1654
+ "d",
1655
+ "u"
1656
+ ],
1657
+ [
1658
+ "g",
1659
+ "o"
1660
+ ],
1661
+ [
1662
+ "b",
1663
+ "o"
1664
+ ],
1665
+ [
1666
+ "al",
1667
+ "l</w>"
1668
+ ],
1669
+ [
1670
+ "w",
1671
+ "e"
1672
+ ],
1673
+ [
1674
+ "at",
1675
+ "e</w>"
1676
+ ],
1677
+ [
1678
+ "ti",
1679
+ "m"
1680
+ ],
1681
+ [
1682
+ "re",
1683
+ "c"
1684
+ ],
1685
+ [
1686
+ "ar",
1687
+ "e</w>"
1688
+ ],
1689
+ [
1690
+ "q",
1691
+ "u"
1692
+ ],
1693
+ [
1694
+ "th",
1695
+ "er</w>"
1696
+ ],
1697
+ [
1698
+ "m",
1699
+ "an"
1700
+ ],
1701
+ [
1702
+ "d",
1703
+ "ing</w>"
1704
+ ],
1705
+ [
1706
+ "m",
1707
+ "e"
1708
+ ],
1709
+ [
1710
+ "o",
1711
+ "p"
1712
+ ],
1713
+ [
1714
+ "g",
1715
+ "u"
1716
+ ],
1717
+ [
1718
+ "p",
1719
+ "ar"
1720
+ ],
1721
+ [
1722
+ "t",
1723
+ "r"
1724
+ ],
1725
+ [
1726
+ "on",
1727
+ "e</w>"
1728
+ ],
1729
+ [
1730
+ "whi",
1731
+ "ch</w>"
1732
+ ],
1733
+ [
1734
+ "g",
1735
+ "i"
1736
+ ],
1737
+ [
1738
+ "e",
1739
+ "c"
1740
+ ],
1741
+ [
1742
+ "â",
1743
+ "Ģ"
1744
+ ],
1745
+ [
1746
+ "d",
1747
+ "ed</w>"
1748
+ ],
1749
+ [
1750
+ "s",
1751
+ "s</w>"
1752
+ ],
1753
+ [
1754
+ "p",
1755
+ "or"
1756
+ ],
1757
+ [
1758
+ "am",
1759
+ "e</w>"
1760
+ ],
1761
+ [
1762
+ "ha",
1763
+ "d</w>"
1764
+ ],
1765
+ [
1766
+ "w",
1767
+ "or"
1768
+ ],
1769
+ [
1770
+ "a",
1771
+ "f"
1772
+ ],
1773
+ [
1774
+ "d",
1775
+ "er"
1776
+ ],
1777
+ [
1778
+ "v",
1779
+ "er</w>"
1780
+ ],
1781
+ [
1782
+ "in",
1783
+ "g"
1784
+ ],
1785
+ [
1786
+ "s",
1787
+ "c"
1788
+ ],
1789
+ [
1790
+ "e",
1791
+ "ar"
1792
+ ],
1793
+ [
1794
+ "b",
1795
+ "e</w>"
1796
+ ],
1797
+ [
1798
+ "h",
1799
+ "o"
1800
+ ],
1801
+ [
1802
+ "s",
1803
+ "o</w>"
1804
+ ],
1805
+ [
1806
+ "tion",
1807
+ "s</w>"
1808
+ ],
1809
+ [
1810
+ "t",
1811
+ "a"
1812
+ ],
1813
+ [
1814
+ "b",
1815
+ "er</w>"
1816
+ ],
1817
+ [
1818
+ "l",
1819
+ "d</w>"
1820
+ ],
1821
+ [
1822
+ "w",
1823
+ "a"
1824
+ ],
1825
+ [
1826
+ "m",
1827
+ "u"
1828
+ ],
1829
+ [
1830
+ "n",
1831
+ "i"
1832
+ ],
1833
+ [
1834
+ "s",
1835
+ "ed</w>"
1836
+ ],
1837
+ [
1838
+ "m",
1839
+ "ar"
1840
+ ],
1841
+ [
1842
+ "t",
1843
+ "ur"
1844
+ ],
1845
+ [
1846
+ "al",
1847
+ "ly</w>"
1848
+ ],
1849
+ [
1850
+ "o",
1851
+ "f"
1852
+ ],
1853
+ [
1854
+ "p",
1855
+ "u"
1856
+ ],
1857
+ [
1858
+ "gh",
1859
+ "t</w>"
1860
+ ],
1861
+ [
1862
+ "s",
1863
+ "hi"
1864
+ ],
1865
+ [
1866
+ "m",
1867
+ "i"
1868
+ ],
1869
+ [
1870
+ "t",
1871
+ "w"
1872
+ ],
1873
+ [
1874
+ "e",
1875
+ "st"
1876
+ ],
1877
+ [
1878
+ "ou",
1879
+ "t</w>"
1880
+ ],
1881
+ [
1882
+ "it",
1883
+ "s</w>"
1884
+ ],
1885
+ [
1886
+ "g",
1887
+ "h</w>"
1888
+ ],
1889
+ [
1890
+ "fi",
1891
+ "r"
1892
+ ],
1893
+ [
1894
+ "h",
1895
+ "er</w>"
1896
+ ],
1897
+ [
1898
+ "i",
1899
+ "r</w>"
1900
+ ],
1901
+ [
1902
+ "u",
1903
+ "m"
1904
+ ],
1905
+ [
1906
+ "c",
1907
+ "e"
1908
+ ],
1909
+ [
1910
+ "p",
1911
+ "la"
1912
+ ],
1913
+ [
1914
+ "th",
1915
+ "is</w>"
1916
+ ],
1917
+ [
1918
+ "w",
1919
+ "n</w>"
1920
+ ],
1921
+ [
1922
+ "a",
1923
+ "u"
1924
+ ],
1925
+ [
1926
+ "ro",
1927
+ "u"
1928
+ ],
1929
+ [
1930
+ "p",
1931
+ "l"
1932
+ ],
1933
+ [
1934
+ "sh",
1935
+ "e</w>"
1936
+ ],
1937
+ [
1938
+ "âĢ",
1939
+ "ĵ</w>"
1940
+ ],
1941
+ [
1942
+ "k",
1943
+ "e</w>"
1944
+ ],
1945
+ [
1946
+ "in",
1947
+ "c"
1948
+ ],
1949
+ [
1950
+ "i",
1951
+ "m"
1952
+ ],
1953
+ [
1954
+ "al",
1955
+ "so</w>"
1956
+ ],
1957
+ [
1958
+ "d",
1959
+ "er</w>"
1960
+ ],
1961
+ [
1962
+ "g",
1963
+ "e</w>"
1964
+ ],
1965
+ [
1966
+ "n",
1967
+ "a"
1968
+ ],
1969
+ [
1970
+ "in",
1971
+ "e</w>"
1972
+ ],
1973
+ [
1974
+ "the",
1975
+ "ir</w>"
1976
+ ],
1977
+ [
1978
+ "on",
1979
+ "g</w>"
1980
+ ],
1981
+ [
1982
+ "p",
1983
+ "e"
1984
+ ],
1985
+ [
1986
+ "s",
1987
+ "er"
1988
+ ],
1989
+ [
1990
+ "v",
1991
+ "ed</w>"
1992
+ ],
1993
+ [
1994
+ "ar",
1995
+ "y</w>"
1996
+ ],
1997
+ [
1998
+ "s",
1999
+ "en"
2000
+ ],
2001
+ [
2002
+ "m",
2003
+ "ent</w>"
2004
+ ],
2005
+ [
2006
+ "f",
2007
+ "in"
2008
+ ],
2009
+ [
2010
+ "h",
2011
+ "as</w>"
2012
+ ],
2013
+ [
2014
+ "t",
2015
+ "ing</w>"
2016
+ ],
2017
+ [
2018
+ "d",
2019
+ "o"
2020
+ ],
2021
+ [
2022
+ "s",
2023
+ "h</w>"
2024
+ ],
2025
+ [
2026
+ "no",
2027
+ "t</w>"
2028
+ ],
2029
+ [
2030
+ "t",
2031
+ "e</w>"
2032
+ ],
2033
+ [
2034
+ "r",
2035
+ "an"
2036
+ ],
2037
+ [
2038
+ "s",
2039
+ "a"
2040
+ ],
2041
+ [
2042
+ "m",
2043
+ "or"
2044
+ ],
2045
+ [
2046
+ "or",
2047
+ "i"
2048
+ ],
2049
+ [
2050
+ "m",
2051
+ "in"
2052
+ ],
2053
+ [
2054
+ "l",
2055
+ "ed</w>"
2056
+ ],
2057
+ [
2058
+ ".",
2059
+ "@</w>"
2060
+ ],
2061
+ [
2062
+ "@",
2063
+ ".@</w>"
2064
+ ],
2065
+ [
2066
+ "bu",
2067
+ "t</w>"
2068
+ ],
2069
+ [
2070
+ "af",
2071
+ "ter</w>"
2072
+ ],
2073
+ [
2074
+ "tw",
2075
+ "o</w>"
2076
+ ],
2077
+ [
2078
+ "fir",
2079
+ "st</w>"
2080
+ ],
2081
+ [
2082
+ "s",
2083
+ "ti"
2084
+ ],
2085
+ [
2086
+ "s",
2087
+ "o"
2088
+ ],
2089
+ [
2090
+ "i",
2091
+ "r"
2092
+ ],
2093
+ [
2094
+ "f",
2095
+ "er"
2096
+ ],
2097
+ [
2098
+ "o",
2099
+ "ther</w>"
2100
+ ],
2101
+ [
2102
+ "t",
2103
+ "y</w>"
2104
+ ],
2105
+ [
2106
+ "en",
2107
+ "ts</w>"
2108
+ ],
2109
+ [
2110
+ "the",
2111
+ "y</w>"
2112
+ ],
2113
+ [
2114
+ "com",
2115
+ "m"
2116
+ ],
2117
+ [
2118
+ "t",
2119
+ "u"
2120
+ ],
2121
+ [
2122
+ "w",
2123
+ "i"
2124
+ ],
2125
+ [
2126
+ "g",
2127
+ "e"
2128
+ ],
2129
+ [
2130
+ "t",
2131
+ "e"
2132
+ ],
2133
+ [
2134
+ "ha",
2135
+ "ve</w>"
2136
+ ],
2137
+ [
2138
+ "n",
2139
+ "ed</w>"
2140
+ ],
2141
+ [
2142
+ "t",
2143
+ "en"
2144
+ ],
2145
+ [
2146
+ "s",
2147
+ "s"
2148
+ ],
2149
+ [
2150
+ "ou",
2151
+ "ld</w>"
2152
+ ],
2153
+ [
2154
+ "wh",
2155
+ "o</w>"
2156
+ ],
2157
+ [
2158
+ "p",
2159
+ "i"
2160
+ ],
2161
+ [
2162
+ "d",
2163
+ "a"
2164
+ ],
2165
+ [
2166
+ "as",
2167
+ "t</w>"
2168
+ ],
2169
+ [
2170
+ "ti",
2171
+ "es</w>"
2172
+ ],
2173
+ [
2174
+ "l",
2175
+ "ar"
2176
+ ],
2177
+ [
2178
+ "s",
2179
+ "on</w>"
2180
+ ],
2181
+ [
2182
+ "w",
2183
+ "ar"
2184
+ ],
2185
+ [
2186
+ "sh",
2187
+ "o"
2188
+ ],
2189
+ [
2190
+ "k",
2191
+ "e"
2192
+ ],
2193
+ [
2194
+ "ch",
2195
+ "ar"
2196
+ ],
2197
+ [
2198
+ "be",
2199
+ "en</w>"
2200
+ ],
2201
+ [
2202
+ "ou",
2203
+ "r"
2204
+ ],
2205
+ [
2206
+ ",",
2207
+ "@</w>"
2208
+ ],
2209
+ [
2210
+ "@",
2211
+ ",@</w>"
2212
+ ],
2213
+ [
2214
+ "m",
2215
+ "an</w>"
2216
+ ],
2217
+ [
2218
+ "ne",
2219
+ "w</w>"
2220
+ ],
2221
+ [
2222
+ "k",
2223
+ "s</w>"
2224
+ ],
2225
+ [
2226
+ "m",
2227
+ "on"
2228
+ ],
2229
+ [
2230
+ "si",
2231
+ "on</w>"
2232
+ ],
2233
+ [
2234
+ "g",
2235
+ "en"
2236
+ ],
2237
+ [
2238
+ "or",
2239
+ "y</w>"
2240
+ ],
2241
+ [
2242
+ "ur",
2243
+ "ing</w>"
2244
+ ],
2245
+ [
2246
+ "a",
2247
+ "r</w>"
2248
+ ],
2249
+ [
2250
+ "g",
2251
+ "re"
2252
+ ],
2253
+ [
2254
+ "at",
2255
+ "er</w>"
2256
+ ],
2257
+ [
2258
+ "lo",
2259
+ "w"
2260
+ ],
2261
+ [
2262
+ "an",
2263
+ "t</w>"
2264
+ ],
2265
+ [
2266
+ "si",
2267
+ "g"
2268
+ ],
2269
+ [
2270
+ "el",
2271
+ "y</w>"
2272
+ ],
2273
+ [
2274
+ "f",
2275
+ "t</w>"
2276
+ ],
2277
+ [
2278
+ "con",
2279
+ "t"
2280
+ ],
2281
+ [
2282
+ "f",
2283
+ "u"
2284
+ ],
2285
+ [
2286
+ "r",
2287
+ "it"
2288
+ ],
2289
+ [
2290
+ "ag",
2291
+ "e</w>"
2292
+ ],
2293
+ [
2294
+ "ou",
2295
+ "s</w>"
2296
+ ],
2297
+ [
2298
+ "c",
2299
+ "re"
2300
+ ],
2301
+ [
2302
+ "c",
2303
+ "en"
2304
+ ],
2305
+ [
2306
+ "st",
2307
+ "e"
2308
+ ],
2309
+ [
2310
+ "e",
2311
+ "l</w>"
2312
+ ],
2313
+ [
2314
+ "du",
2315
+ "c"
2316
+ ],
2317
+ [
2318
+ "u",
2319
+ "s</w>"
2320
+ ],
2321
+ [
2322
+ "po",
2323
+ "li"
2324
+ ],
2325
+ [
2326
+ "tion",
2327
+ "al</w>"
2328
+ ],
2329
+ [
2330
+ "om",
2331
+ "e</w>"
2332
+ ],
2333
+ [
2334
+ "tim",
2335
+ "e</w>"
2336
+ ],
2337
+ [
2338
+ "t",
2339
+ "ra"
2340
+ ],
2341
+ [
2342
+ "al",
2343
+ "i"
2344
+ ],
2345
+ [
2346
+ "pla",
2347
+ "y"
2348
+ ],
2349
+ [
2350
+ "k",
2351
+ "ing</w>"
2352
+ ],
2353
+ [
2354
+ "sp",
2355
+ "e"
2356
+ ],
2357
+ [
2358
+ "ou",
2359
+ "r</w>"
2360
+ ],
2361
+ [
2362
+ "o",
2363
+ "c"
2364
+ ],
2365
+ [
2366
+ "it",
2367
+ "ed</w>"
2368
+ ],
2369
+ [
2370
+ "fi",
2371
+ "l"
2372
+ ],
2373
+ [
2374
+ "ai",
2375
+ "r"
2376
+ ],
2377
+ [
2378
+ "b",
2379
+ "ri"
2380
+ ],
2381
+ [
2382
+ "al",
2383
+ "s</w>"
2384
+ ],
2385
+ [
2386
+ "e",
2387
+ "v"
2388
+ ],
2389
+ [
2390
+ "o",
2391
+ "o"
2392
+ ],
2393
+ [
2394
+ "ar",
2395
+ "i"
2396
+ ],
2397
+ [
2398
+ "in",
2399
+ "ter"
2400
+ ],
2401
+ [
2402
+ "ti",
2403
+ "c"
2404
+ ],
2405
+ [
2406
+ "un",
2407
+ "i"
2408
+ ],
2409
+ [
2410
+ "g",
2411
+ "ra"
2412
+ ],
2413
+ [
2414
+ "la",
2415
+ "r</w>"
2416
+ ],
2417
+ [
2418
+ "se",
2419
+ "as"
2420
+ ],
2421
+ [
2422
+ "d",
2423
+ "uring</w>"
2424
+ ],
2425
+ [
2426
+ "st",
2427
+ "ru"
2428
+ ],
2429
+ [
2430
+ "re",
2431
+ "s</w>"
2432
+ ],
2433
+ [
2434
+ "n",
2435
+ "or"
2436
+ ],
2437
+ [
2438
+ "p",
2439
+ "p"
2440
+ ],
2441
+ [
2442
+ "j",
2443
+ "o"
2444
+ ],
2445
+ [
2446
+ "th",
2447
+ "ou"
2448
+ ],
2449
+ [
2450
+ "em",
2451
+ "ber</w>"
2452
+ ],
2453
+ [
2454
+ "l",
2455
+ "and</w>"
2456
+ ],
2457
+ [
2458
+ "or",
2459
+ "d"
2460
+ ],
2461
+ [
2462
+ "c",
2463
+ "k</w>"
2464
+ ],
2465
+ [
2466
+ "it",
2467
+ "e</w>"
2468
+ ],
2469
+ [
2470
+ "inc",
2471
+ "lu"
2472
+ ],
2473
+ [
2474
+ "an",
2475
+ "ce</w>"
2476
+ ],
2477
+ [
2478
+ "st",
2479
+ "r"
2480
+ ],
2481
+ [
2482
+ "p",
2483
+ "ri"
2484
+ ],
2485
+ [
2486
+ "ur",
2487
+ "e</w>"
2488
+ ],
2489
+ [
2490
+ "ti",
2491
+ "ve</w>"
2492
+ ],
2493
+ [
2494
+ "at",
2495
+ "t"
2496
+ ],
2497
+ [
2498
+ "re",
2499
+ "e</w>"
2500
+ ],
2501
+ [
2502
+ "ac",
2503
+ "k</w>"
2504
+ ],
2505
+ [
2506
+ "co",
2507
+ "l"
2508
+ ],
2509
+ [
2510
+ "cu",
2511
+ "l"
2512
+ ],
2513
+ [
2514
+ "mor",
2515
+ "e</w>"
2516
+ ],
2517
+ [
2518
+ "b",
2519
+ "li"
2520
+ ],
2521
+ [
2522
+ "g",
2523
+ "ro"
2524
+ ],
2525
+ [
2526
+ "as",
2527
+ "ed</w>"
2528
+ ],
2529
+ [
2530
+ "p",
2531
+ "s</w>"
2532
+ ],
2533
+ [
2534
+ "th",
2535
+ "an</w>"
2536
+ ],
2537
+ [
2538
+ "for",
2539
+ "m"
2540
+ ],
2541
+ [
2542
+ "y",
2543
+ "p"
2544
+ ],
2545
+ [
2546
+ "com",
2547
+ "p"
2548
+ ],
2549
+ [
2550
+ "rec",
2551
+ "or"
2552
+ ],
2553
+ [
2554
+ "c",
2555
+ "or"
2556
+ ],
2557
+ [
2558
+ "el",
2559
+ "l</w>"
2560
+ ],
2561
+ [
2562
+ "mo",
2563
+ "st</w>"
2564
+ ],
2565
+ [
2566
+ "at",
2567
+ "es</w>"
2568
+ ],
2569
+ [
2570
+ "in",
2571
+ "s</w>"
2572
+ ],
2573
+ [
2574
+ "in",
2575
+ "ed</w>"
2576
+ ],
2577
+ [
2578
+ "c",
2579
+ "hi"
2580
+ ],
2581
+ [
2582
+ "pu",
2583
+ "bli"
2584
+ ],
2585
+ [
2586
+ "wa",
2587
+ "y</w>"
2588
+ ],
2589
+ [
2590
+ "e",
2591
+ "t</w>"
2592
+ ],
2593
+ [
2594
+ "c",
2595
+ "ar"
2596
+ ],
2597
+ [
2598
+ "l",
2599
+ "es</w>"
2600
+ ],
2601
+ [
2602
+ "a",
2603
+ "d</w>"
2604
+ ],
2605
+ [
2606
+ "c",
2607
+ "es</w>"
2608
+ ],
2609
+ [
2610
+ "s",
2611
+ "ch"
2612
+ ],
2613
+ [
2614
+ "spe",
2615
+ "ci"
2616
+ ],
2617
+ [
2618
+ "on",
2619
+ "s</w>"
2620
+ ],
2621
+ [
2622
+ "en",
2623
+ "ce</w>"
2624
+ ],
2625
+ [
2626
+ "al",
2627
+ "bu"
2628
+ ],
2629
+ [
2630
+ "v",
2631
+ "es</w>"
2632
+ ],
2633
+ [
2634
+ "ea",
2635
+ "r</w>"
2636
+ ],
2637
+ [
2638
+ "re",
2639
+ "n"
2640
+ ],
2641
+ [
2642
+ "ch",
2643
+ "a"
2644
+ ],
2645
+ [
2646
+ "shi",
2647
+ "p</w>"
2648
+ ],
2649
+ [
2650
+ "j",
2651
+ "u"
2652
+ ],
2653
+ [
2654
+ "oun",
2655
+ "d</w>"
2656
+ ],
2657
+ [
2658
+ "ol",
2659
+ "d</w>"
2660
+ ],
2661
+ [
2662
+ "k",
2663
+ "ed</w>"
2664
+ ],
2665
+ [
2666
+ "an",
2667
+ "d"
2668
+ ],
2669
+ [
2670
+ "ac",
2671
+ "e</w>"
2672
+ ],
2673
+ [
2674
+ "seas",
2675
+ "on</w>"
2676
+ ],
2677
+ [
2678
+ "s",
2679
+ "el"
2680
+ ],
2681
+ [
2682
+ "ab",
2683
+ "le</w>"
2684
+ ],
2685
+ [
2686
+ "in",
2687
+ "di"
2688
+ ],
2689
+ [
2690
+ "p",
2691
+ "h"
2692
+ ],
2693
+ [
2694
+ "t",
2695
+ "ri"
2696
+ ],
2697
+ [
2698
+ "e",
2699
+ "i"
2700
+ ],
2701
+ [
2702
+ "c",
2703
+ "ity</w>"
2704
+ ],
2705
+ [
2706
+ "ca",
2707
+ "u"
2708
+ ],
2709
+ [
2710
+ "m",
2711
+ "il"
2712
+ ],
2713
+ [
2714
+ "b",
2715
+ "i"
2716
+ ],
2717
+ [
2718
+ "t",
2719
+ "ly</w>"
2720
+ ],
2721
+ [
2722
+ "in",
2723
+ "to</w>"
2724
+ ],
2725
+ [
2726
+ "c",
2727
+ "l"
2728
+ ],
2729
+ [
2730
+ "r",
2731
+ "ed</w>"
2732
+ ],
2733
+ [
2734
+ "l",
2735
+ "s</w>"
2736
+ ],
2737
+ [
2738
+ "s",
2739
+ "ou"
2740
+ ],
2741
+ [
2742
+ "as",
2743
+ "e</w>"
2744
+ ],
2745
+ [
2746
+ "ing",
2747
+ "s</w>"
2748
+ ],
2749
+ [
2750
+ "v",
2751
+ "ing</w>"
2752
+ ],
2753
+ [
2754
+ "ac",
2755
+ "h"
2756
+ ],
2757
+ [
2758
+ "s",
2759
+ "y"
2760
+ ],
2761
+ [
2762
+ "wh",
2763
+ "en</w>"
2764
+ ],
2765
+ [
2766
+ "o",
2767
+ "lo"
2768
+ ],
2769
+ [
2770
+ "o",
2771
+ "ver</w>"
2772
+ ],
2773
+ [
2774
+ "hi",
2775
+ "st"
2776
+ ],
2777
+ [
2778
+ "thou",
2779
+ "gh</w>"
2780
+ ],
2781
+ [
2782
+ "en",
2783
+ "d</w>"
2784
+ ],
2785
+ [
2786
+ "ti",
2787
+ "c</w>"
2788
+ ],
2789
+ [
2790
+ "di",
2791
+ "s"
2792
+ ],
2793
+ [
2794
+ "se",
2795
+ "con"
2796
+ ],
2797
+ [
2798
+ "c",
2799
+ "an"
2800
+ ],
2801
+ [
2802
+ "s",
2803
+ "ur"
2804
+ ],
2805
+ [
2806
+ "on",
2807
+ "ly</w>"
2808
+ ],
2809
+ [
2810
+ "ma",
2811
+ "y</w>"
2812
+ ],
2813
+ [
2814
+ "ord",
2815
+ "an</w>"
2816
+ ],
2817
+ [
2818
+ "c",
2819
+ "oun"
2820
+ ],
2821
+ [
2822
+ "j",
2823
+ "ordan</w>"
2824
+ ],
2825
+ [
2826
+ "m",
2827
+ "s</w>"
2828
+ ],
2829
+ [
2830
+ "an",
2831
+ "s</w>"
2832
+ ],
2833
+ [
2834
+ "albu",
2835
+ "m</w>"
2836
+ ],
2837
+ [
2838
+ "er",
2839
+ "n</w>"
2840
+ ],
2841
+ [
2842
+ "b",
2843
+ "le</w>"
2844
+ ],
2845
+ [
2846
+ "r",
2847
+ "e</w>"
2848
+ ],
2849
+ [
2850
+ "w",
2851
+ "n"
2852
+ ],
2853
+ [
2854
+ "ac",
2855
+ "h</w>"
2856
+ ],
2857
+ [
2858
+ "am",
2859
+ "es</w>"
2860
+ ],
2861
+ [
2862
+ "o",
2863
+ "k</w>"
2864
+ ],
2865
+ [
2866
+ "y",
2867
+ "s</w>"
2868
+ ],
2869
+ [
2870
+ "u",
2871
+ "p</w>"
2872
+ ],
2873
+ [
2874
+ "th",
2875
+ "ere</w>"
2876
+ ],
2877
+ [
2878
+ "su",
2879
+ "b"
2880
+ ],
2881
+ [
2882
+ "e",
2883
+ "g"
2884
+ ],
2885
+ [
2886
+ "n",
2887
+ "um"
2888
+ ],
2889
+ [
2890
+ "man",
2891
+ "y</w>"
2892
+ ],
2893
+ [
2894
+ "th",
2895
+ "ree</w>"
2896
+ ],
2897
+ [
2898
+ "g",
2899
+ "in"
2900
+ ],
2901
+ [
2902
+ "re",
2903
+ "le"
2904
+ ],
2905
+ [
2906
+ "sh",
2907
+ "ed</w>"
2908
+ ],
2909
+ [
2910
+ "ag",
2911
+ "a"
2912
+ ],
2913
+ [
2914
+ "g",
2915
+ "al"
2916
+ ],
2917
+ [
2918
+ "k",
2919
+ "no"
2920
+ ],
2921
+ [
2922
+ "o",
2923
+ "d</w>"
2924
+ ],
2925
+ [
2926
+ "whi",
2927
+ "le</w>"
2928
+ ],
2929
+ [
2930
+ "y",
2931
+ "ear</w>"
2932
+ ],
2933
+ [
2934
+ "or",
2935
+ "s</w>"
2936
+ ],
2937
+ [
2938
+ "n",
2939
+ "ing</w>"
2940
+ ],
2941
+ [
2942
+ "p",
2943
+ "a"
2944
+ ],
2945
+ [
2946
+ "l",
2947
+ "ater</w>"
2948
+ ],
2949
+ [
2950
+ "v",
2951
+ "e"
2952
+ ],
2953
+ [
2954
+ "n",
2955
+ "o</w>"
2956
+ ],
2957
+ [
2958
+ "th",
2959
+ "rou"
2960
+ ],
2961
+ [
2962
+ "y",
2963
+ "ing</w>"
2964
+ ],
2965
+ [
2966
+ "em",
2967
+ "p"
2968
+ ],
2969
+ [
2970
+ "a",
2971
+ "tions</w>"
2972
+ ],
2973
+ [
2974
+ "i",
2975
+ "c</w>"
2976
+ ],
2977
+ [
2978
+ "vi",
2979
+ "e"
2980
+ ],
2981
+ [
2982
+ "wh",
2983
+ "e"
2984
+ ],
2985
+ [
2986
+ "s",
2987
+ "si"
2988
+ ],
2989
+ [
2990
+ "c",
2991
+ "ame</w>"
2992
+ ],
2993
+ [
2994
+ "si",
2995
+ "c</w>"
2996
+ ],
2997
+ [
2998
+ "f",
2999
+ "a"
3000
+ ],
3001
+ [
3002
+ "be",
3003
+ "t"
3004
+ ],
3005
+ [
3006
+ "wa",
3007
+ "r</w>"
3008
+ ],
3009
+ [
3010
+ "b",
3011
+ "ro"
3012
+ ],
3013
+ [
3014
+ "w",
3015
+ "ould</w>"
3016
+ ],
3017
+ [
3018
+ "s",
3019
+ "ome</w>"
3020
+ ],
3021
+ [
3022
+ "l",
3023
+ "l</w>"
3024
+ ],
3025
+ [
3026
+ "de",
3027
+ "v"
3028
+ ],
3029
+ [
3030
+ "ic",
3031
+ "al</w>"
3032
+ ],
3033
+ [
3034
+ "s",
3035
+ "k"
3036
+ ],
3037
+ [
3038
+ "pro",
3039
+ "duc"
3040
+ ],
3041
+ [
3042
+ "por",
3043
+ "t</w>"
3044
+ ],
3045
+ [
3046
+ "sc",
3047
+ "ri"
3048
+ ],
3049
+ [
3050
+ "bu",
3051
+ "il"
3052
+ ],
3053
+ [
3054
+ "b",
3055
+ "ar"
3056
+ ],
3057
+ [
3058
+ "g",
3059
+ "ame</w>"
3060
+ ],
3061
+ [
3062
+ "fil",
3063
+ "m</w>"
3064
+ ],
3065
+ [
3066
+ "b",
3067
+ "a"
3068
+ ],
3069
+ [
3070
+ "th",
3071
+ "o"
3072
+ ],
3073
+ [
3074
+ "lo",
3075
+ "c"
3076
+ ],
3077
+ [
3078
+ "be",
3079
+ "ing</w>"
3080
+ ],
3081
+ [
3082
+ "the",
3083
+ "se</w>"
3084
+ ],
3085
+ [
3086
+ "ab",
3087
+ "out</w>"
3088
+ ],
3089
+ [
3090
+ "so",
3091
+ "ci"
3092
+ ],
3093
+ [
3094
+ "s",
3095
+ "ing</w>"
3096
+ ],
3097
+ [
3098
+ "l",
3099
+ "an"
3100
+ ],
3101
+ [
3102
+ "t",
3103
+ "re"
3104
+ ],
3105
+ [
3106
+ "t",
3107
+ "en</w>"
3108
+ ],
3109
+ [
3110
+ "w",
3111
+ "rit"
3112
+ ],
3113
+ [
3114
+ "f",
3115
+ "ol"
3116
+ ],
3117
+ [
3118
+ "ar",
3119
+ "d</w>"
3120
+ ],
3121
+ [
3122
+ "u",
3123
+ "e</w>"
3124
+ ],
3125
+ [
3126
+ "ea",
3127
+ "m</w>"
3128
+ ],
3129
+ [
3130
+ "st",
3131
+ "s</w>"
3132
+ ],
3133
+ [
3134
+ "hi",
3135
+ "m</w>"
3136
+ ],
3137
+ [
3138
+ "ap",
3139
+ "p"
3140
+ ],
3141
+ [
3142
+ "g",
3143
+ "er"
3144
+ ],
3145
+ [
3146
+ "the",
3147
+ "m</w>"
3148
+ ],
3149
+ [
3150
+ "stru",
3151
+ "c"
3152
+ ],
3153
+ [
3154
+ "of",
3155
+ "fi"
3156
+ ],
3157
+ [
3158
+ "m",
3159
+ "y</w>"
3160
+ ],
3161
+ [
3162
+ "an",
3163
+ "i"
3164
+ ],
3165
+ [
3166
+ "da",
3167
+ "y</w>"
3168
+ ],
3169
+ [
3170
+ "d",
3171
+ "y</w>"
3172
+ ],
3173
+ [
3174
+ "h",
3175
+ "e"
3176
+ ],
3177
+ [
3178
+ "u",
3179
+ "m</w>"
3180
+ ],
3181
+ [
3182
+ "st",
3183
+ "ri"
3184
+ ],
3185
+ [
3186
+ "st",
3187
+ "u"
3188
+ ],
3189
+ [
3190
+ "el",
3191
+ "e"
3192
+ ],
3193
+ [
3194
+ "whe",
3195
+ "el"
3196
+ ],
3197
+ [
3198
+ "c",
3199
+ "ra"
3200
+ ],
3201
+ [
3202
+ "secon",
3203
+ "d</w>"
3204
+ ],
3205
+ [
3206
+ "on",
3207
+ "g"
3208
+ ],
3209
+ [
3210
+ "si",
3211
+ "de</w>"
3212
+ ],
3213
+ [
3214
+ "su",
3215
+ "ch</w>"
3216
+ ],
3217
+ [
3218
+ "t",
3219
+ "eam</w>"
3220
+ ],
3221
+ [
3222
+ "at",
3223
+ "ing</w>"
3224
+ ],
3225
+ [
3226
+ "c",
3227
+ "an</w>"
3228
+ ],
3229
+ [
3230
+ "f",
3231
+ "ac"
3232
+ ],
3233
+ [
3234
+ "m",
3235
+ "is"
3236
+ ],
3237
+ [
3238
+ "wheel",
3239
+ "er</w>"
3240
+ ],
3241
+ [
3242
+ "d",
3243
+ "en"
3244
+ ],
3245
+ [
3246
+ "m",
3247
+ "e</w>"
3248
+ ],
3249
+ [
3250
+ "c",
3251
+ "ri"
3252
+ ],
3253
+ [
3254
+ "ch",
3255
+ "ri"
3256
+ ],
3257
+ [
3258
+ "we",
3259
+ "en</w>"
3260
+ ],
3261
+ [
3262
+ "cha",
3263
+ "e"
3264
+ ],
3265
+ [
3266
+ "g",
3267
+ "a"
3268
+ ],
3269
+ [
3270
+ "l",
3271
+ "ing</w>"
3272
+ ],
3273
+ [
3274
+ "s",
3275
+ "es</w>"
3276
+ ],
3277
+ [
3278
+ "bet",
3279
+ "ween</w>"
3280
+ ],
3281
+ [
3282
+ "m",
3283
+ "at"
3284
+ ],
3285
+ [
3286
+ "v",
3287
+ "est"
3288
+ ],
3289
+ [
3290
+ "po",
3291
+ "in"
3292
+ ],
3293
+ [
3294
+ "gen",
3295
+ "er"
3296
+ ],
3297
+ [
3298
+ "c",
3299
+ "al"
3300
+ ],
3301
+ [
3302
+ "w",
3303
+ "il"
3304
+ ],
3305
+ [
3306
+ "ti",
3307
+ "sh</w>"
3308
+ ],
3309
+ [
3310
+ "ar",
3311
+ "chae"
3312
+ ],
3313
+ [
3314
+ "ear",
3315
+ "s</w>"
3316
+ ],
3317
+ [
3318
+ "archae",
3319
+ "olo"
3320
+ ],
3321
+ [
3322
+ "j",
3323
+ "ec"
3324
+ ],
3325
+ [
3326
+ "t",
3327
+ "al</w>"
3328
+ ],
3329
+ [
3330
+ "un",
3331
+ "d</w>"
3332
+ ],
3333
+ [
3334
+ "s",
3335
+ "in"
3336
+ ],
3337
+ [
3338
+ "v",
3339
+ "en"
3340
+ ],
3341
+ [
3342
+ "ma",
3343
+ "de</w>"
3344
+ ],
3345
+ [
3346
+ "su",
3347
+ "l"
3348
+ ],
3349
+ [
3350
+ "tur",
3351
+ "e</w>"
3352
+ ],
3353
+ [
3354
+ "o",
3355
+ "per"
3356
+ ],
3357
+ [
3358
+ "v",
3359
+ "en</w>"
3360
+ ],
3361
+ [
3362
+ "w",
3363
+ "s</w>"
3364
+ ],
3365
+ [
3366
+ "wh",
3367
+ "ere</w>"
3368
+ ],
3369
+ [
3370
+ "r",
3371
+ "on"
3372
+ ],
3373
+ [
3374
+ "con",
3375
+ "si"
3376
+ ],
3377
+ [
3378
+ "f",
3379
+ "our</w>"
3380
+ ],
3381
+ [
3382
+ "t",
3383
+ "on</w>"
3384
+ ],
3385
+ [
3386
+ "o",
3387
+ "b"
3388
+ ],
3389
+ [
3390
+ "w",
3391
+ "er</w>"
3392
+ ],
3393
+ [
3394
+ "se",
3395
+ "ver"
3396
+ ],
3397
+ [
3398
+ "un",
3399
+ "der</w>"
3400
+ ],
3401
+ [
3402
+ "wor",
3403
+ "k</w>"
3404
+ ],
3405
+ [
3406
+ "am",
3407
+ "er"
3408
+ ],
3409
+ [
3410
+ "ca",
3411
+ "p"
3412
+ ],
3413
+ [
3414
+ "na",
3415
+ "tional</w>"
3416
+ ],
3417
+ [
3418
+ "wi",
3419
+ "th"
3420
+ ],
3421
+ [
3422
+ "for",
3423
+ "e</w>"
3424
+ ],
3425
+ [
3426
+ "th",
3427
+ "en</w>"
3428
+ ],
3429
+ [
3430
+ "al",
3431
+ "though</w>"
3432
+ ],
3433
+ [
3434
+ "s",
3435
+ "m"
3436
+ ],
3437
+ [
3438
+ "on",
3439
+ "y</w>"
3440
+ ],
3441
+ [
3442
+ "el",
3443
+ "d</w>"
3444
+ ],
3445
+ [
3446
+ "ch",
3447
+ "ur"
3448
+ ],
3449
+ [
3450
+ "bri",
3451
+ "tish</w>"
3452
+ ],
3453
+ [
3454
+ "gal",
3455
+ "vest"
3456
+ ],
3457
+ [
3458
+ "bo",
3459
+ "th</w>"
3460
+ ],
3461
+ [
3462
+ "b",
3463
+ "er"
3464
+ ],
3465
+ [
3466
+ "st",
3467
+ "ed</w>"
3468
+ ],
3469
+ [
3470
+ "di",
3471
+ "rec"
3472
+ ],
3473
+ [
3474
+ "galvest",
3475
+ "on</w>"
3476
+ ],
3477
+ [
3478
+ "f",
3479
+ "e</w>"
3480
+ ],
3481
+ [
3482
+ "w",
3483
+ "ell</w>"
3484
+ ],
3485
+ [
3486
+ "d",
3487
+ "re"
3488
+ ],
3489
+ [
3490
+ "y",
3491
+ "or"
3492
+ ],
3493
+ [
3494
+ "no",
3495
+ "v"
3496
+ ],
3497
+ [
3498
+ "l",
3499
+ "it"
3500
+ ],
3501
+ [
3502
+ "t",
3503
+ "ro"
3504
+ ],
3505
+ [
3506
+ "de",
3507
+ "scri"
3508
+ ],
3509
+ [
3510
+ "ca",
3511
+ "tion</w>"
3512
+ ],
3513
+ [
3514
+ "ai",
3515
+ "d</w>"
3516
+ ],
3517
+ [
3518
+ "tr",
3519
+ "an"
3520
+ ],
3521
+ [
3522
+ "in",
3523
+ "i"
3524
+ ],
3525
+ [
3526
+ "st",
3527
+ "ate</w>"
3528
+ ],
3529
+ [
3530
+ "per",
3531
+ "i"
3532
+ ],
3533
+ [
3534
+ "d",
3535
+ "es</w>"
3536
+ ],
3537
+ [
3538
+ "e",
3539
+ "st</w>"
3540
+ ],
3541
+ [
3542
+ "h",
3543
+ "ea"
3544
+ ],
3545
+ [
3546
+ "p",
3547
+ "en"
3548
+ ],
3549
+ [
3550
+ "y",
3551
+ "ears</w>"
3552
+ ],
3553
+ [
3554
+ "wor",
3555
+ "ld</w>"
3556
+ ],
3557
+ [
3558
+ "i",
3559
+ "es</w>"
3560
+ ],
3561
+ [
3562
+ "u",
3563
+ "sed</w>"
3564
+ ],
3565
+ [
3566
+ "go",
3567
+ "ds</w>"
3568
+ ],
3569
+ [
3570
+ "t",
3571
+ "ers</w>"
3572
+ ],
3573
+ [
3574
+ "di",
3575
+ "f"
3576
+ ],
3577
+ [
3578
+ "fol",
3579
+ "low"
3580
+ ],
3581
+ [
3582
+ "a",
3583
+ "re"
3584
+ ],
3585
+ [
3586
+ "e",
3587
+ "s"
3588
+ ],
3589
+ [
3590
+ "g",
3591
+ "an</w>"
3592
+ ],
3593
+ [
3594
+ "st",
3595
+ "ar"
3596
+ ],
3597
+ [
3598
+ "li",
3599
+ "ke</w>"
3600
+ ],
3601
+ [
3602
+ "ear",
3603
+ "ly</w>"
3604
+ ],
3605
+ [
3606
+ "m",
3607
+ "en"
3608
+ ],
3609
+ [
3610
+ "s",
3611
+ "ing"
3612
+ ],
3613
+ [
3614
+ "b",
3615
+ "or"
3616
+ ],
3617
+ [
3618
+ "t",
3619
+ "or</w>"
3620
+ ],
3621
+ [
3622
+ "mu",
3623
+ "sic</w>"
3624
+ ],
3625
+ [
3626
+ "cl",
3627
+ "as"
3628
+ ],
3629
+ [
3630
+ "sever",
3631
+ "al</w>"
3632
+ ],
3633
+ [
3634
+ "un",
3635
+ "ited</w>"
3636
+ ],
3637
+ [
3638
+ "num",
3639
+ "ber</w>"
3640
+ ],
3641
+ [
3642
+ "chur",
3643
+ "ch</w>"
3644
+ ],
3645
+ [
3646
+ "yor",
3647
+ "k</w>"
3648
+ ],
3649
+ [
3650
+ "c",
3651
+ "ur"
3652
+ ],
3653
+ [
3654
+ "c",
3655
+ "lo"
3656
+ ],
3657
+ [
3658
+ "an",
3659
+ "g"
3660
+ ],
3661
+ [
3662
+ "re",
3663
+ "sp"
3664
+ ],
3665
+ [
3666
+ "am",
3667
+ "i"
3668
+ ],
3669
+ [
3670
+ "m",
3671
+ "em"
3672
+ ],
3673
+ [
3674
+ "c",
3675
+ "lu"
3676
+ ],
3677
+ [
3678
+ "par",
3679
+ "t</w>"
3680
+ ],
3681
+ [
3682
+ "c",
3683
+ "ed</w>"
3684
+ ],
3685
+ [
3686
+ "c",
3687
+ "er"
3688
+ ],
3689
+ [
3690
+ "j",
3691
+ "e"
3692
+ ],
3693
+ [
3694
+ "t",
3695
+ "ru"
3696
+ ],
3697
+ [
3698
+ "en",
3699
+ "g"
3700
+ ],
3701
+ [
3702
+ "be",
3703
+ "fore</w>"
3704
+ ],
3705
+ [
3706
+ "kno",
3707
+ "wn</w>"
3708
+ ],
3709
+ [
3710
+ "amer",
3711
+ "ic"
3712
+ ],
3713
+ [
3714
+ "l",
3715
+ "ong</w>"
3716
+ ],
3717
+ [
3718
+ "n",
3719
+ "am"
3720
+ ],
3721
+ [
3722
+ "st",
3723
+ "an"
3724
+ ],
3725
+ [
3726
+ "st",
3727
+ "er</w>"
3728
+ ],
3729
+ [
3730
+ "al",
3731
+ "e</w>"
3732
+ ]
3733
+ ]
3734
+ }
3735
+ }
aimv2_text_model/Aimv2TextModel/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<start_of_text>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<end_of_text>",
6
+ "errors": "replace",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 25,
10
+ "pad_token": "<end_of_text>",
11
+ "processor_class": "CLIPProcessor",
12
+ "tokenizer_class": "CLIPTokenizer",
13
+ "unk_token": "<end_of_text>",
14
+ "use_fast": true
15
+ }
aimv2_vision_model/Aimv2VisionModel/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Aimv2VisionModel"
4
+ ],
5
+ "attention_dropout": 0.1,
6
+ "dropout": 0.1,
7
+ "dtype": "float32",
8
+ "hidden_act": "silu",
9
+ "hidden_size": 32,
10
+ "image_size": 30,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 37,
13
+ "is_native": false,
14
+ "mlp_bias": false,
15
+ "model_type": "aimv2_vision_model",
16
+ "num_attention_heads": 4,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 2,
19
+ "patch_size": 2,
20
+ "projection_dim": 32,
21
+ "qkv_bias": false,
22
+ "rms_norm_eps": 1e-05,
23
+ "transformers_version": "5.15.0.dev0",
24
+ "use_head": true
25
+ }
aimv2_vision_model/Aimv2VisionModel/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74d3d31e39b1c509c3b7d55c0f6128b82f0d4f616f13fe5aa8947e827bc818b8
3
+ size 107672
aimv2_vision_model/Aimv2VisionModel/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 30,
4
+ "width": 30
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 30
26
+ }
27
+ }
aimv2_vision_model/Aimv2VisionModel/tokenizer.json ADDED
@@ -0,0 +1,3735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<start_of_text>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<end_of_text>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": {
26
+ "type": "Sequence",
27
+ "normalizers": [
28
+ {
29
+ "type": "NFC"
30
+ },
31
+ {
32
+ "type": "Replace",
33
+ "pattern": {
34
+ "Regex": "\\s+"
35
+ },
36
+ "content": " "
37
+ },
38
+ {
39
+ "type": "Lowercase"
40
+ }
41
+ ]
42
+ },
43
+ "pre_tokenizer": {
44
+ "type": "Sequence",
45
+ "pretokenizers": [
46
+ {
47
+ "type": "Split",
48
+ "pattern": {
49
+ "Regex": "<\\|startoftext\\|>|<\\|endoftext\\|>|'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
50
+ },
51
+ "behavior": "Removed",
52
+ "invert": true
53
+ },
54
+ {
55
+ "type": "ByteLevel",
56
+ "add_prefix_space": false,
57
+ "trim_offsets": true,
58
+ "use_regex": true
59
+ }
60
+ ]
61
+ },
62
+ "post_processor": {
63
+ "type": "RobertaProcessing",
64
+ "sep": [
65
+ "<end_of_text>",
66
+ 1
67
+ ],
68
+ "cls": [
69
+ "<start_of_text>",
70
+ 0
71
+ ],
72
+ "trim_offsets": false,
73
+ "add_prefix_space": false
74
+ },
75
+ "decoder": {
76
+ "type": "ByteLevel",
77
+ "add_prefix_space": true,
78
+ "trim_offsets": true,
79
+ "use_regex": true
80
+ },
81
+ "model": {
82
+ "type": "BPE",
83
+ "dropout": null,
84
+ "unk_token": "<end_of_text>",
85
+ "continuing_subword_prefix": "",
86
+ "end_of_word_suffix": "</w>",
87
+ "fuse_unk": false,
88
+ "byte_fallback": false,
89
+ "ignore_merges": false,
90
+ "vocab": {
91
+ "<start_of_text>": 0,
92
+ "<end_of_text>": 1,
93
+ "!": 2,
94
+ "\"": 3,
95
+ "#": 4,
96
+ "$": 5,
97
+ "%": 6,
98
+ "&": 7,
99
+ "'": 8,
100
+ "(": 9,
101
+ ")": 10,
102
+ "*": 11,
103
+ "+": 12,
104
+ ",": 13,
105
+ "-": 14,
106
+ ".": 15,
107
+ "/": 16,
108
+ "0": 17,
109
+ "1": 18,
110
+ "2": 19,
111
+ "3": 20,
112
+ "4": 21,
113
+ "5": 22,
114
+ "6": 23,
115
+ "7": 24,
116
+ "8": 25,
117
+ "9": 26,
118
+ ":": 27,
119
+ ";": 28,
120
+ "<": 29,
121
+ "=": 30,
122
+ ">": 31,
123
+ "?": 32,
124
+ "@": 33,
125
+ "A": 34,
126
+ "B": 35,
127
+ "C": 36,
128
+ "D": 37,
129
+ "E": 38,
130
+ "F": 39,
131
+ "G": 40,
132
+ "H": 41,
133
+ "I": 42,
134
+ "J": 43,
135
+ "K": 44,
136
+ "L": 45,
137
+ "M": 46,
138
+ "N": 47,
139
+ "O": 48,
140
+ "P": 49,
141
+ "Q": 50,
142
+ "R": 51,
143
+ "S": 52,
144
+ "T": 53,
145
+ "U": 54,
146
+ "V": 55,
147
+ "W": 56,
148
+ "X": 57,
149
+ "Y": 58,
150
+ "Z": 59,
151
+ "[": 60,
152
+ "\\": 61,
153
+ "]": 62,
154
+ "^": 63,
155
+ "_": 64,
156
+ "`": 65,
157
+ "a": 66,
158
+ "b": 67,
159
+ "c": 68,
160
+ "d": 69,
161
+ "e": 70,
162
+ "f": 71,
163
+ "g": 72,
164
+ "h": 73,
165
+ "i": 74,
166
+ "j": 75,
167
+ "k": 76,
168
+ "l": 77,
169
+ "m": 78,
170
+ "n": 79,
171
+ "o": 80,
172
+ "p": 81,
173
+ "q": 82,
174
+ "r": 83,
175
+ "s": 84,
176
+ "t": 85,
177
+ "u": 86,
178
+ "v": 87,
179
+ "w": 88,
180
+ "x": 89,
181
+ "y": 90,
182
+ "z": 91,
183
+ "{": 92,
184
+ "|": 93,
185
+ "}": 94,
186
+ "~": 95,
187
+ "¡": 96,
188
+ "¢": 97,
189
+ "£": 98,
190
+ "¤": 99,
191
+ "¥": 100,
192
+ "¦": 101,
193
+ "§": 102,
194
+ "¨": 103,
195
+ "©": 104,
196
+ "ª": 105,
197
+ "«": 106,
198
+ "¬": 107,
199
+ "®": 108,
200
+ "¯": 109,
201
+ "°": 110,
202
+ "±": 111,
203
+ "²": 112,
204
+ "³": 113,
205
+ "´": 114,
206
+ "µ": 115,
207
+ "¶": 116,
208
+ "·": 117,
209
+ "¸": 118,
210
+ "¹": 119,
211
+ "º": 120,
212
+ "»": 121,
213
+ "¼": 122,
214
+ "½": 123,
215
+ "¾": 124,
216
+ "¿": 125,
217
+ "À": 126,
218
+ "Á": 127,
219
+ "Â": 128,
220
+ "Ã": 129,
221
+ "Ä": 130,
222
+ "Å": 131,
223
+ "Æ": 132,
224
+ "Ç": 133,
225
+ "È": 134,
226
+ "É": 135,
227
+ "Ê": 136,
228
+ "Ë": 137,
229
+ "Ì": 138,
230
+ "Í": 139,
231
+ "Î": 140,
232
+ "Ï": 141,
233
+ "Ð": 142,
234
+ "Ñ": 143,
235
+ "Ò": 144,
236
+ "Ó": 145,
237
+ "Ô": 146,
238
+ "Õ": 147,
239
+ "Ö": 148,
240
+ "×": 149,
241
+ "Ø": 150,
242
+ "Ù": 151,
243
+ "Ú": 152,
244
+ "Û": 153,
245
+ "Ü": 154,
246
+ "Ý": 155,
247
+ "Þ": 156,
248
+ "ß": 157,
249
+ "à": 158,
250
+ "á": 159,
251
+ "â": 160,
252
+ "ã": 161,
253
+ "ä": 162,
254
+ "å": 163,
255
+ "æ": 164,
256
+ "ç": 165,
257
+ "è": 166,
258
+ "é": 167,
259
+ "ê": 168,
260
+ "ë": 169,
261
+ "ì": 170,
262
+ "í": 171,
263
+ "î": 172,
264
+ "ï": 173,
265
+ "ð": 174,
266
+ "ñ": 175,
267
+ "ò": 176,
268
+ "ó": 177,
269
+ "ô": 178,
270
+ "õ": 179,
271
+ "ö": 180,
272
+ "÷": 181,
273
+ "ø": 182,
274
+ "ù": 183,
275
+ "ú": 184,
276
+ "û": 185,
277
+ "ü": 186,
278
+ "ý": 187,
279
+ "þ": 188,
280
+ "ÿ": 189,
281
+ "Ā": 190,
282
+ "ā": 191,
283
+ "Ă": 192,
284
+ "ă": 193,
285
+ "Ą": 194,
286
+ "ą": 195,
287
+ "Ć": 196,
288
+ "ć": 197,
289
+ "Ĉ": 198,
290
+ "ĉ": 199,
291
+ "Ċ": 200,
292
+ "ċ": 201,
293
+ "Č": 202,
294
+ "č": 203,
295
+ "Ď": 204,
296
+ "ď": 205,
297
+ "Đ": 206,
298
+ "đ": 207,
299
+ "Ē": 208,
300
+ "ē": 209,
301
+ "Ĕ": 210,
302
+ "ĕ": 211,
303
+ "Ė": 212,
304
+ "ė": 213,
305
+ "Ę": 214,
306
+ "ę": 215,
307
+ "Ě": 216,
308
+ "ě": 217,
309
+ "Ĝ": 218,
310
+ "ĝ": 219,
311
+ "Ğ": 220,
312
+ "ğ": 221,
313
+ "Ġ": 222,
314
+ "ġ": 223,
315
+ "Ģ": 224,
316
+ "ģ": 225,
317
+ "Ĥ": 226,
318
+ "ĥ": 227,
319
+ "Ħ": 228,
320
+ "ħ": 229,
321
+ "Ĩ": 230,
322
+ "ĩ": 231,
323
+ "Ī": 232,
324
+ "ī": 233,
325
+ "Ĭ": 234,
326
+ "ĭ": 235,
327
+ "Į": 236,
328
+ "į": 237,
329
+ "İ": 238,
330
+ "ı": 239,
331
+ "IJ": 240,
332
+ "ij": 241,
333
+ "Ĵ": 242,
334
+ "ĵ": 243,
335
+ "Ķ": 244,
336
+ "ķ": 245,
337
+ "ĸ": 246,
338
+ "Ĺ": 247,
339
+ "ĺ": 248,
340
+ "Ļ": 249,
341
+ "ļ": 250,
342
+ "Ľ": 251,
343
+ "ľ": 252,
344
+ "Ŀ": 253,
345
+ "ŀ": 254,
346
+ "Ł": 255,
347
+ "ł": 256,
348
+ "Ń": 257,
349
+ "y</w>": 258,
350
+ "s</w>": 259,
351
+ "d</w>": 260,
352
+ "r</w>": 261,
353
+ "l</w>": 262,
354
+ "z</w>": 263,
355
+ "£</w>": 264,
356
+ "h</w>": 265,
357
+ "f</w>": 266,
358
+ "t</w>": 267,
359
+ "b</w>": 268,
360
+ "e</w>": 269,
361
+ "c</w>": 270,
362
+ "g</w>": 271,
363
+ "n</w>": 272,
364
+ "m</w>": 273,
365
+ "¯</w>": 274,
366
+ "i</w>": 275,
367
+ "k</w>": 276,
368
+ "w</w>": 277,
369
+ "a</w>": 278,
370
+ "p</w>": 279,
371
+ "u</w>": 280,
372
+ "o</w>": 281,
373
+ "j</w>": 282,
374
+ "x</w>": 283,
375
+ "¢</w>": 284,
376
+ "ĩ</w>": 285,
377
+ "©</w>": 286,
378
+ "$</w>": 287,
379
+ "v</w>": 288,
380
+ "1</w>": 289,
381
+ "±</w>": 290,
382
+ ")</w>": 291,
383
+ "Ĵ</w>": 292,
384
+ "`</w>": 293,
385
+ "ķ</w>": 294,
386
+ "<</w>": 295,
387
+ "¡</w>": 296,
388
+ "º</w>": 297,
389
+ "´</w>": 298,
390
+ "=</w>": 299,
391
+ "½</w>": 300,
392
+ "'</w>": 301,
393
+ ":</w>": 302,
394
+ "¤</w>": 303,
395
+ "]</w>": 304,
396
+ ";</w>": 305,
397
+ "7</w>": 306,
398
+ "Ķ</w>": 307,
399
+ ".</w>": 308,
400
+ "ĭ</w>": 309,
401
+ "Ļ</w>": 310,
402
+ "Ľ</w>": 311,
403
+ "Ń</w>": 312,
404
+ "&</w>": 313,
405
+ "q</w>": 314,
406
+ "Į</w>": 315,
407
+ "¹</w>": 316,
408
+ "Ĥ</w>": 317,
409
+ "ļ</w>": 318,
410
+ "§</w>": 319,
411
+ "¦</w>": 320,
412
+ "6</w>": 321,
413
+ "2</w>": 322,
414
+ "ª</w>": 323,
415
+ "/</w>": 324,
416
+ "Ī</w>": 325,
417
+ "Ĺ</w>": 326,
418
+ "#</w>": 327,
419
+ "ī</w>": 328,
420
+ "@</w>": 329,
421
+ "9</w>": 330,
422
+ "İ</w>": 331,
423
+ "ģ</w>": 332,
424
+ "ĵ</w>": 333,
425
+ "4</w>": 334,
426
+ "ľ</w>": 335,
427
+ "·</w>": 336,
428
+ "Ħ</w>": 337,
429
+ "!</w>": 338,
430
+ "+</w>": 339,
431
+ "²</w>": 340,
432
+ "></w>": 341,
433
+ "į</w>": 342,
434
+ ",</w>": 343,
435
+ "¾</w>": 344,
436
+ "µ</w>": 345,
437
+ "0</w>": 346,
438
+ "?</w>": 347,
439
+ "[</w>": 348,
440
+ "%</w>": 349,
441
+ "8</w>": 350,
442
+ "*</w>": 351,
443
+ "\"</w>": 352,
444
+ "~</w>": 353,
445
+ "¶</w>": 354,
446
+ "ŀ</w>": 355,
447
+ "Ĭ</w>": 356,
448
+ "ħ</w>": 357,
449
+ "Ŀ</w>": 358,
450
+ "^</w>": 359,
451
+ "ĺ</w>": 360,
452
+ "5</w>": 361,
453
+ "-</w>": 362,
454
+ "°</w>": 363,
455
+ "3</w>": 364,
456
+ "IJ</w>": 365,
457
+ "(</w>": 366,
458
+ "¨</w>": 367,
459
+ "³</w>": 368,
460
+ "ł</w>": 369,
461
+ "th": 370,
462
+ "the</w>": 371,
463
+ "in": 372,
464
+ "an": 373,
465
+ "ed</w>": 374,
466
+ "er": 375,
467
+ "re": 376,
468
+ "ti": 377,
469
+ "ar": 378,
470
+ "or": 379,
471
+ "on": 380,
472
+ "of</w>": 381,
473
+ "en": 382,
474
+ "and</w>": 383,
475
+ "er</w>": 384,
476
+ "on</w>": 385,
477
+ "in</w>": 386,
478
+ "st": 387,
479
+ "al": 388,
480
+ "ing</w>": 389,
481
+ "it": 390,
482
+ "ro": 391,
483
+ "as</w>": 392,
484
+ "to</w>": 393,
485
+ "at": 394,
486
+ "es</w>": 395,
487
+ "hi": 396,
488
+ "ou": 397,
489
+ "al</w>": 398,
490
+ "an</w>": 399,
491
+ "ac": 400,
492
+ "at</w>": 401,
493
+ "li": 402,
494
+ "si": 403,
495
+ "ri": 404,
496
+ "el": 405,
497
+ "or</w>": 406,
498
+ "as": 407,
499
+ "de": 408,
500
+ "ur": 409,
501
+ "co": 410,
502
+ "am": 411,
503
+ "di": 412,
504
+ "ch": 413,
505
+ "was</w>": 414,
506
+ "tion</w>": 415,
507
+ "le": 416,
508
+ "st</w>": 417,
509
+ "ly</w>": 418,
510
+ "se": 419,
511
+ "lo": 420,
512
+ "un": 421,
513
+ "-@</w>": 422,
514
+ "@-@</w>": 423,
515
+ "is</w>": 424,
516
+ "be": 425,
517
+ "fi": 426,
518
+ "en</w>": 427,
519
+ "la": 428,
520
+ "ra": 429,
521
+ "le</w>": 430,
522
+ "con": 431,
523
+ "sh": 432,
524
+ "po": 433,
525
+ "that</w>": 434,
526
+ "wit": 435,
527
+ "vi": 436,
528
+ "for</w>": 437,
529
+ "with</w>": 438,
530
+ "ch</w>": 439,
531
+ "em": 440,
532
+ "ma": 441,
533
+ "'s</w>": 442,
534
+ "su": 443,
535
+ "ts</w>": 444,
536
+ "ve</w>": 445,
537
+ "by</w>": 446,
538
+ "ent</w>": 447,
539
+ "the": 448,
540
+ "ha": 449,
541
+ "ci": 450,
542
+ "pro": 451,
543
+ "ere</w>": 452,
544
+ "com": 453,
545
+ "ag": 454,
546
+ "ce</w>": 455,
547
+ "bu": 456,
548
+ "il": 457,
549
+ "no": 458,
550
+ "wh": 459,
551
+ "is": 460,
552
+ "sp": 461,
553
+ "ne": 462,
554
+ "ol": 463,
555
+ "ca": 464,
556
+ "ted</w>": 465,
557
+ "it</w>": 466,
558
+ "ers</w>": 467,
559
+ "tion": 468,
560
+ "he</w>": 469,
561
+ "se</w>": 470,
562
+ "gh": 471,
563
+ "for": 472,
564
+ "his</w>": 473,
565
+ "ru": 474,
566
+ "th</w>": 475,
567
+ "ver": 476,
568
+ "ad": 477,
569
+ "to": 478,
570
+ "mo": 479,
571
+ "ex": 480,
572
+ "fro": 481,
573
+ "from</w>": 482,
574
+ "ab": 483,
575
+ "whi": 484,
576
+ "per": 485,
577
+ "cu": 486,
578
+ "ea": 487,
579
+ "ds</w>": 488,
580
+ "were</w>": 489,
581
+ "ic": 490,
582
+ "om": 491,
583
+ "ap": 492,
584
+ "ity</w>": 493,
585
+ "ation</w>": 494,
586
+ "ter</w>": 495,
587
+ "pre": 496,
588
+ "oun": 497,
589
+ "ai": 498,
590
+ "fe": 499,
591
+ "lu": 500,
592
+ "ter": 501,
593
+ "ated</w>": 502,
594
+ "de</w>": 503,
595
+ "du": 504,
596
+ "go": 505,
597
+ "bo": 506,
598
+ "all</w>": 507,
599
+ "we": 508,
600
+ "ate</w>": 509,
601
+ "tim": 510,
602
+ "rec": 511,
603
+ "are</w>": 512,
604
+ "qu": 513,
605
+ "ther</w>": 514,
606
+ "man": 515,
607
+ "ding</w>": 516,
608
+ "me": 517,
609
+ "op": 518,
610
+ "gu": 519,
611
+ "par": 520,
612
+ "tr": 521,
613
+ "one</w>": 522,
614
+ "which</w>": 523,
615
+ "gi": 524,
616
+ "ec": 525,
617
+ "âĢ": 526,
618
+ "ded</w>": 527,
619
+ "ss</w>": 528,
620
+ "por": 529,
621
+ "ame</w>": 530,
622
+ "had</w>": 531,
623
+ "wor": 532,
624
+ "af": 533,
625
+ "der": 534,
626
+ "ver</w>": 535,
627
+ "ing": 536,
628
+ "sc": 537,
629
+ "ear": 538,
630
+ "be</w>": 539,
631
+ "ho": 540,
632
+ "so</w>": 541,
633
+ "tions</w>": 542,
634
+ "ta": 543,
635
+ "ber</w>": 544,
636
+ "ld</w>": 545,
637
+ "wa": 546,
638
+ "mu": 547,
639
+ "ni": 548,
640
+ "sed</w>": 549,
641
+ "mar": 550,
642
+ "tur": 551,
643
+ "ally</w>": 552,
644
+ "of": 553,
645
+ "pu": 554,
646
+ "ght</w>": 555,
647
+ "shi": 556,
648
+ "mi": 557,
649
+ "tw": 558,
650
+ "est": 559,
651
+ "out</w>": 560,
652
+ "its</w>": 561,
653
+ "gh</w>": 562,
654
+ "fir": 563,
655
+ "her</w>": 564,
656
+ "ir</w>": 565,
657
+ "um": 566,
658
+ "ce": 567,
659
+ "pla": 568,
660
+ "this</w>": 569,
661
+ "wn</w>": 570,
662
+ "au": 571,
663
+ "rou": 572,
664
+ "pl": 573,
665
+ "she</w>": 574,
666
+ "âĢĵ</w>": 575,
667
+ "ke</w>": 576,
668
+ "inc": 577,
669
+ "im": 578,
670
+ "also</w>": 579,
671
+ "der</w>": 580,
672
+ "ge</w>": 581,
673
+ "na": 582,
674
+ "ine</w>": 583,
675
+ "their</w>": 584,
676
+ "ong</w>": 585,
677
+ "pe": 586,
678
+ "ser": 587,
679
+ "ved</w>": 588,
680
+ "ary</w>": 589,
681
+ "sen": 590,
682
+ "ment</w>": 591,
683
+ "fin": 592,
684
+ "has</w>": 593,
685
+ "ting</w>": 594,
686
+ "do": 595,
687
+ "sh</w>": 596,
688
+ "not</w>": 597,
689
+ "te</w>": 598,
690
+ "ran": 599,
691
+ "sa": 600,
692
+ "mor": 601,
693
+ "ori": 602,
694
+ "min": 603,
695
+ "led</w>": 604,
696
+ ".@</w>": 605,
697
+ "@.@</w>": 606,
698
+ "but</w>": 607,
699
+ "after</w>": 608,
700
+ "two</w>": 609,
701
+ "first</w>": 610,
702
+ "sti": 611,
703
+ "so": 612,
704
+ "ir": 613,
705
+ "fer": 614,
706
+ "other</w>": 615,
707
+ "ty</w>": 616,
708
+ "ents</w>": 617,
709
+ "they</w>": 618,
710
+ "comm": 619,
711
+ "tu": 620,
712
+ "wi": 621,
713
+ "ge": 622,
714
+ "te": 623,
715
+ "have</w>": 624,
716
+ "ned</w>": 625,
717
+ "ten": 626,
718
+ "ss": 627,
719
+ "ould</w>": 628,
720
+ "who</w>": 629,
721
+ "pi": 630,
722
+ "da": 631,
723
+ "ast</w>": 632,
724
+ "ties</w>": 633,
725
+ "lar": 634,
726
+ "son</w>": 635,
727
+ "war": 636,
728
+ "sho": 637,
729
+ "ke": 638,
730
+ "char": 639,
731
+ "been</w>": 640,
732
+ "our": 641,
733
+ ",@</w>": 642,
734
+ "@,@</w>": 643,
735
+ "man</w>": 644,
736
+ "new</w>": 645,
737
+ "ks</w>": 646,
738
+ "mon": 647,
739
+ "sion</w>": 648,
740
+ "gen": 649,
741
+ "ory</w>": 650,
742
+ "uring</w>": 651,
743
+ "ar</w>": 652,
744
+ "gre": 653,
745
+ "ater</w>": 654,
746
+ "low": 655,
747
+ "ant</w>": 656,
748
+ "sig": 657,
749
+ "ely</w>": 658,
750
+ "ft</w>": 659,
751
+ "cont": 660,
752
+ "fu": 661,
753
+ "rit": 662,
754
+ "age</w>": 663,
755
+ "ous</w>": 664,
756
+ "cre": 665,
757
+ "cen": 666,
758
+ "ste": 667,
759
+ "el</w>": 668,
760
+ "duc": 669,
761
+ "us</w>": 670,
762
+ "poli": 671,
763
+ "tional</w>": 672,
764
+ "ome</w>": 673,
765
+ "time</w>": 674,
766
+ "tra": 675,
767
+ "ali": 676,
768
+ "play": 677,
769
+ "king</w>": 678,
770
+ "spe": 679,
771
+ "our</w>": 680,
772
+ "oc": 681,
773
+ "ited</w>": 682,
774
+ "fil": 683,
775
+ "air": 684,
776
+ "bri": 685,
777
+ "als</w>": 686,
778
+ "ev": 687,
779
+ "oo": 688,
780
+ "ari": 689,
781
+ "inter": 690,
782
+ "tic": 691,
783
+ "uni": 692,
784
+ "gra": 693,
785
+ "lar</w>": 694,
786
+ "seas": 695,
787
+ "during</w>": 696,
788
+ "stru": 697,
789
+ "res</w>": 698,
790
+ "nor": 699,
791
+ "pp": 700,
792
+ "jo": 701,
793
+ "thou": 702,
794
+ "ember</w>": 703,
795
+ "land</w>": 704,
796
+ "ord": 705,
797
+ "ck</w>": 706,
798
+ "ite</w>": 707,
799
+ "inclu": 708,
800
+ "ance</w>": 709,
801
+ "str": 710,
802
+ "pri": 711,
803
+ "ure</w>": 712,
804
+ "tive</w>": 713,
805
+ "att": 714,
806
+ "ree</w>": 715,
807
+ "ack</w>": 716,
808
+ "col": 717,
809
+ "cul": 718,
810
+ "more</w>": 719,
811
+ "bli": 720,
812
+ "gro": 721,
813
+ "ased</w>": 722,
814
+ "ps</w>": 723,
815
+ "than</w>": 724,
816
+ "form": 725,
817
+ "yp": 726,
818
+ "comp": 727,
819
+ "recor": 728,
820
+ "cor": 729,
821
+ "ell</w>": 730,
822
+ "most</w>": 731,
823
+ "ates</w>": 732,
824
+ "ins</w>": 733,
825
+ "ined</w>": 734,
826
+ "chi": 735,
827
+ "publi": 736,
828
+ "way</w>": 737,
829
+ "et</w>": 738,
830
+ "car": 739,
831
+ "les</w>": 740,
832
+ "ad</w>": 741,
833
+ "ces</w>": 742,
834
+ "sch": 743,
835
+ "speci": 744,
836
+ "ons</w>": 745,
837
+ "ence</w>": 746,
838
+ "albu": 747,
839
+ "ves</w>": 748,
840
+ "ear</w>": 749,
841
+ "ren": 750,
842
+ "cha": 751,
843
+ "ship</w>": 752,
844
+ "ju": 753,
845
+ "ound</w>": 754,
846
+ "old</w>": 755,
847
+ "ked</w>": 756,
848
+ "and": 757,
849
+ "ace</w>": 758,
850
+ "season</w>": 759,
851
+ "sel": 760,
852
+ "able</w>": 761,
853
+ "indi": 762,
854
+ "ph": 763,
855
+ "tri": 764,
856
+ "ei": 765,
857
+ "city</w>": 766,
858
+ "cau": 767,
859
+ "mil": 768,
860
+ "bi": 769,
861
+ "tly</w>": 770,
862
+ "into</w>": 771,
863
+ "cl": 772,
864
+ "red</w>": 773,
865
+ "ls</w>": 774,
866
+ "sou": 775,
867
+ "ase</w>": 776,
868
+ "ings</w>": 777,
869
+ "ving</w>": 778,
870
+ "ach": 779,
871
+ "sy": 780,
872
+ "when</w>": 781,
873
+ "olo": 782,
874
+ "over</w>": 783,
875
+ "hist": 784,
876
+ "though</w>": 785,
877
+ "end</w>": 786,
878
+ "tic</w>": 787,
879
+ "dis": 788,
880
+ "secon": 789,
881
+ "can": 790,
882
+ "sur": 791,
883
+ "only</w>": 792,
884
+ "may</w>": 793,
885
+ "ordan</w>": 794,
886
+ "coun": 795,
887
+ "jordan</w>": 796,
888
+ "ms</w>": 797,
889
+ "ans</w>": 798,
890
+ "album</w>": 799,
891
+ "ern</w>": 800,
892
+ "ble</w>": 801,
893
+ "re</w>": 802,
894
+ "wn": 803,
895
+ "ach</w>": 804,
896
+ "ames</w>": 805,
897
+ "ok</w>": 806,
898
+ "ys</w>": 807,
899
+ "up</w>": 808,
900
+ "there</w>": 809,
901
+ "sub": 810,
902
+ "eg": 811,
903
+ "num": 812,
904
+ "many</w>": 813,
905
+ "three</w>": 814,
906
+ "gin": 815,
907
+ "rele": 816,
908
+ "shed</w>": 817,
909
+ "aga": 818,
910
+ "gal": 819,
911
+ "kno": 820,
912
+ "od</w>": 821,
913
+ "while</w>": 822,
914
+ "year</w>": 823,
915
+ "ors</w>": 824,
916
+ "ning</w>": 825,
917
+ "pa": 826,
918
+ "later</w>": 827,
919
+ "ve": 828,
920
+ "no</w>": 829,
921
+ "throu": 830,
922
+ "ying</w>": 831,
923
+ "emp": 832,
924
+ "ations</w>": 833,
925
+ "ic</w>": 834,
926
+ "vie": 835,
927
+ "whe": 836,
928
+ "ssi": 837,
929
+ "came</w>": 838,
930
+ "sic</w>": 839,
931
+ "fa": 840,
932
+ "bet": 841,
933
+ "war</w>": 842,
934
+ "bro": 843,
935
+ "would</w>": 844,
936
+ "some</w>": 845,
937
+ "ll</w>": 846,
938
+ "dev": 847,
939
+ "ical</w>": 848,
940
+ "sk": 849,
941
+ "produc": 850,
942
+ "port</w>": 851,
943
+ "scri": 852,
944
+ "buil": 853,
945
+ "bar": 854,
946
+ "game</w>": 855,
947
+ "film</w>": 856,
948
+ "ba": 857,
949
+ "tho": 858,
950
+ "loc": 859,
951
+ "being</w>": 860,
952
+ "these</w>": 861,
953
+ "about</w>": 862,
954
+ "soci": 863,
955
+ "sing</w>": 864,
956
+ "lan": 865,
957
+ "tre": 866,
958
+ "ten</w>": 867,
959
+ "writ": 868,
960
+ "fol": 869,
961
+ "ard</w>": 870,
962
+ "ue</w>": 871,
963
+ "eam</w>": 872,
964
+ "sts</w>": 873,
965
+ "him</w>": 874,
966
+ "app": 875,
967
+ "ger": 876,
968
+ "them</w>": 877,
969
+ "struc": 878,
970
+ "offi": 879,
971
+ "my</w>": 880,
972
+ "ani": 881,
973
+ "day</w>": 882,
974
+ "dy</w>": 883,
975
+ "he": 884,
976
+ "um</w>": 885,
977
+ "stri": 886,
978
+ "stu": 887,
979
+ "ele": 888,
980
+ "wheel": 889,
981
+ "cra": 890,
982
+ "second</w>": 891,
983
+ "ong": 892,
984
+ "side</w>": 893,
985
+ "such</w>": 894,
986
+ "team</w>": 895,
987
+ "ating</w>": 896,
988
+ "can</w>": 897,
989
+ "fac": 898,
990
+ "mis": 899,
991
+ "wheeler</w>": 900,
992
+ "den": 901,
993
+ "me</w>": 902,
994
+ "cri": 903,
995
+ "chri": 904,
996
+ "ween</w>": 905,
997
+ "chae": 906,
998
+ "ga": 907,
999
+ "ling</w>": 908,
1000
+ "ses</w>": 909,
1001
+ "between</w>": 910,
1002
+ "mat": 911,
1003
+ "vest": 912,
1004
+ "poin": 913,
1005
+ "gener": 914,
1006
+ "cal": 915,
1007
+ "wil": 916,
1008
+ "tish</w>": 917,
1009
+ "archae": 918,
1010
+ "ears</w>": 919,
1011
+ "archaeolo": 920,
1012
+ "jec": 921,
1013
+ "tal</w>": 922,
1014
+ "und</w>": 923,
1015
+ "sin": 924,
1016
+ "ven": 925,
1017
+ "made</w>": 926,
1018
+ "sul": 927,
1019
+ "ture</w>": 928,
1020
+ "oper": 929,
1021
+ "ven</w>": 930,
1022
+ "ws</w>": 931,
1023
+ "where</w>": 932,
1024
+ "ron": 933,
1025
+ "consi": 934,
1026
+ "four</w>": 935,
1027
+ "ton</w>": 936,
1028
+ "ob": 937,
1029
+ "wer</w>": 938,
1030
+ "sever": 939,
1031
+ "under</w>": 940,
1032
+ "work</w>": 941,
1033
+ "amer": 942,
1034
+ "cap": 943,
1035
+ "national</w>": 944,
1036
+ "with": 945,
1037
+ "fore</w>": 946,
1038
+ "then</w>": 947,
1039
+ "although</w>": 948,
1040
+ "sm": 949,
1041
+ "ony</w>": 950,
1042
+ "eld</w>": 951,
1043
+ "chur": 952,
1044
+ "british</w>": 953,
1045
+ "galvest": 954,
1046
+ "both</w>": 955,
1047
+ "ber": 956,
1048
+ "sted</w>": 957,
1049
+ "direc": 958,
1050
+ "galveston</w>": 959,
1051
+ "fe</w>": 960,
1052
+ "well</w>": 961,
1053
+ "dre": 962,
1054
+ "yor": 963,
1055
+ "nov": 964,
1056
+ "lit": 965,
1057
+ "tro": 966,
1058
+ "descri": 967,
1059
+ "cation</w>": 968,
1060
+ "aid</w>": 969,
1061
+ "tran": 970,
1062
+ "ini": 971,
1063
+ "state</w>": 972,
1064
+ "peri": 973,
1065
+ "des</w>": 974,
1066
+ "est</w>": 975,
1067
+ "hea": 976,
1068
+ "pen": 977,
1069
+ "years</w>": 978,
1070
+ "world</w>": 979,
1071
+ "ies</w>": 980,
1072
+ "used</w>": 981,
1073
+ "gods</w>": 982,
1074
+ "ters</w>": 983,
1075
+ "dif": 984,
1076
+ "follow": 985,
1077
+ "are": 986,
1078
+ "es": 987,
1079
+ "gan</w>": 988,
1080
+ "star": 989,
1081
+ "like</w>": 990,
1082
+ "early</w>": 991,
1083
+ "men": 992,
1084
+ "sing": 993,
1085
+ "bor": 994,
1086
+ "tor</w>": 995,
1087
+ "music</w>": 996,
1088
+ "clas": 997,
1089
+ "several</w>": 998,
1090
+ "united</w>": 999,
1091
+ "number</w>": 1000,
1092
+ "church</w>": 1001,
1093
+ "york</w>": 1002,
1094
+ "cur": 1003,
1095
+ "clo": 1004,
1096
+ "ang": 1005,
1097
+ "resp": 1006,
1098
+ "ami": 1007,
1099
+ "mem": 1008,
1100
+ "clu": 1009,
1101
+ "part</w>": 1010,
1102
+ "ced</w>": 1011,
1103
+ "cer": 1012,
1104
+ "je": 1013,
1105
+ "tru": 1014,
1106
+ "eng": 1015,
1107
+ "before</w>": 1016,
1108
+ "known</w>": 1017,
1109
+ "americ": 1018,
1110
+ "long</w>": 1019,
1111
+ "nam": 1020,
1112
+ "stan": 1021,
1113
+ "ster</w>": 1022,
1114
+ "ale</w>": 1023
1115
+ },
1116
+ "merges": [
1117
+ [
1118
+ "t",
1119
+ "h"
1120
+ ],
1121
+ [
1122
+ "th",
1123
+ "e</w>"
1124
+ ],
1125
+ [
1126
+ "i",
1127
+ "n"
1128
+ ],
1129
+ [
1130
+ "a",
1131
+ "n"
1132
+ ],
1133
+ [
1134
+ "e",
1135
+ "d</w>"
1136
+ ],
1137
+ [
1138
+ "e",
1139
+ "r"
1140
+ ],
1141
+ [
1142
+ "r",
1143
+ "e"
1144
+ ],
1145
+ [
1146
+ "t",
1147
+ "i"
1148
+ ],
1149
+ [
1150
+ "a",
1151
+ "r"
1152
+ ],
1153
+ [
1154
+ "o",
1155
+ "r"
1156
+ ],
1157
+ [
1158
+ "o",
1159
+ "n"
1160
+ ],
1161
+ [
1162
+ "o",
1163
+ "f</w>"
1164
+ ],
1165
+ [
1166
+ "e",
1167
+ "n"
1168
+ ],
1169
+ [
1170
+ "an",
1171
+ "d</w>"
1172
+ ],
1173
+ [
1174
+ "e",
1175
+ "r</w>"
1176
+ ],
1177
+ [
1178
+ "o",
1179
+ "n</w>"
1180
+ ],
1181
+ [
1182
+ "i",
1183
+ "n</w>"
1184
+ ],
1185
+ [
1186
+ "s",
1187
+ "t"
1188
+ ],
1189
+ [
1190
+ "a",
1191
+ "l"
1192
+ ],
1193
+ [
1194
+ "in",
1195
+ "g</w>"
1196
+ ],
1197
+ [
1198
+ "i",
1199
+ "t"
1200
+ ],
1201
+ [
1202
+ "r",
1203
+ "o"
1204
+ ],
1205
+ [
1206
+ "a",
1207
+ "s</w>"
1208
+ ],
1209
+ [
1210
+ "t",
1211
+ "o</w>"
1212
+ ],
1213
+ [
1214
+ "a",
1215
+ "t"
1216
+ ],
1217
+ [
1218
+ "e",
1219
+ "s</w>"
1220
+ ],
1221
+ [
1222
+ "h",
1223
+ "i"
1224
+ ],
1225
+ [
1226
+ "o",
1227
+ "u"
1228
+ ],
1229
+ [
1230
+ "a",
1231
+ "l</w>"
1232
+ ],
1233
+ [
1234
+ "a",
1235
+ "n</w>"
1236
+ ],
1237
+ [
1238
+ "a",
1239
+ "c"
1240
+ ],
1241
+ [
1242
+ "a",
1243
+ "t</w>"
1244
+ ],
1245
+ [
1246
+ "l",
1247
+ "i"
1248
+ ],
1249
+ [
1250
+ "s",
1251
+ "i"
1252
+ ],
1253
+ [
1254
+ "r",
1255
+ "i"
1256
+ ],
1257
+ [
1258
+ "e",
1259
+ "l"
1260
+ ],
1261
+ [
1262
+ "o",
1263
+ "r</w>"
1264
+ ],
1265
+ [
1266
+ "a",
1267
+ "s"
1268
+ ],
1269
+ [
1270
+ "d",
1271
+ "e"
1272
+ ],
1273
+ [
1274
+ "u",
1275
+ "r"
1276
+ ],
1277
+ [
1278
+ "c",
1279
+ "o"
1280
+ ],
1281
+ [
1282
+ "a",
1283
+ "m"
1284
+ ],
1285
+ [
1286
+ "d",
1287
+ "i"
1288
+ ],
1289
+ [
1290
+ "c",
1291
+ "h"
1292
+ ],
1293
+ [
1294
+ "w",
1295
+ "as</w>"
1296
+ ],
1297
+ [
1298
+ "ti",
1299
+ "on</w>"
1300
+ ],
1301
+ [
1302
+ "l",
1303
+ "e"
1304
+ ],
1305
+ [
1306
+ "s",
1307
+ "t</w>"
1308
+ ],
1309
+ [
1310
+ "l",
1311
+ "y</w>"
1312
+ ],
1313
+ [
1314
+ "s",
1315
+ "e"
1316
+ ],
1317
+ [
1318
+ "l",
1319
+ "o"
1320
+ ],
1321
+ [
1322
+ "u",
1323
+ "n"
1324
+ ],
1325
+ [
1326
+ "-",
1327
+ "@</w>"
1328
+ ],
1329
+ [
1330
+ "@",
1331
+ "-@</w>"
1332
+ ],
1333
+ [
1334
+ "i",
1335
+ "s</w>"
1336
+ ],
1337
+ [
1338
+ "b",
1339
+ "e"
1340
+ ],
1341
+ [
1342
+ "f",
1343
+ "i"
1344
+ ],
1345
+ [
1346
+ "e",
1347
+ "n</w>"
1348
+ ],
1349
+ [
1350
+ "l",
1351
+ "a"
1352
+ ],
1353
+ [
1354
+ "r",
1355
+ "a"
1356
+ ],
1357
+ [
1358
+ "l",
1359
+ "e</w>"
1360
+ ],
1361
+ [
1362
+ "c",
1363
+ "on"
1364
+ ],
1365
+ [
1366
+ "s",
1367
+ "h"
1368
+ ],
1369
+ [
1370
+ "p",
1371
+ "o"
1372
+ ],
1373
+ [
1374
+ "th",
1375
+ "at</w>"
1376
+ ],
1377
+ [
1378
+ "w",
1379
+ "it"
1380
+ ],
1381
+ [
1382
+ "v",
1383
+ "i"
1384
+ ],
1385
+ [
1386
+ "f",
1387
+ "or</w>"
1388
+ ],
1389
+ [
1390
+ "wit",
1391
+ "h</w>"
1392
+ ],
1393
+ [
1394
+ "c",
1395
+ "h</w>"
1396
+ ],
1397
+ [
1398
+ "e",
1399
+ "m"
1400
+ ],
1401
+ [
1402
+ "m",
1403
+ "a"
1404
+ ],
1405
+ [
1406
+ "'",
1407
+ "s</w>"
1408
+ ],
1409
+ [
1410
+ "s",
1411
+ "u"
1412
+ ],
1413
+ [
1414
+ "t",
1415
+ "s</w>"
1416
+ ],
1417
+ [
1418
+ "v",
1419
+ "e</w>"
1420
+ ],
1421
+ [
1422
+ "b",
1423
+ "y</w>"
1424
+ ],
1425
+ [
1426
+ "en",
1427
+ "t</w>"
1428
+ ],
1429
+ [
1430
+ "th",
1431
+ "e"
1432
+ ],
1433
+ [
1434
+ "h",
1435
+ "a"
1436
+ ],
1437
+ [
1438
+ "c",
1439
+ "i"
1440
+ ],
1441
+ [
1442
+ "p",
1443
+ "ro"
1444
+ ],
1445
+ [
1446
+ "er",
1447
+ "e</w>"
1448
+ ],
1449
+ [
1450
+ "co",
1451
+ "m"
1452
+ ],
1453
+ [
1454
+ "a",
1455
+ "g"
1456
+ ],
1457
+ [
1458
+ "c",
1459
+ "e</w>"
1460
+ ],
1461
+ [
1462
+ "b",
1463
+ "u"
1464
+ ],
1465
+ [
1466
+ "i",
1467
+ "l"
1468
+ ],
1469
+ [
1470
+ "n",
1471
+ "o"
1472
+ ],
1473
+ [
1474
+ "w",
1475
+ "h"
1476
+ ],
1477
+ [
1478
+ "i",
1479
+ "s"
1480
+ ],
1481
+ [
1482
+ "s",
1483
+ "p"
1484
+ ],
1485
+ [
1486
+ "n",
1487
+ "e"
1488
+ ],
1489
+ [
1490
+ "o",
1491
+ "l"
1492
+ ],
1493
+ [
1494
+ "c",
1495
+ "a"
1496
+ ],
1497
+ [
1498
+ "t",
1499
+ "ed</w>"
1500
+ ],
1501
+ [
1502
+ "i",
1503
+ "t</w>"
1504
+ ],
1505
+ [
1506
+ "er",
1507
+ "s</w>"
1508
+ ],
1509
+ [
1510
+ "ti",
1511
+ "on"
1512
+ ],
1513
+ [
1514
+ "h",
1515
+ "e</w>"
1516
+ ],
1517
+ [
1518
+ "s",
1519
+ "e</w>"
1520
+ ],
1521
+ [
1522
+ "g",
1523
+ "h"
1524
+ ],
1525
+ [
1526
+ "f",
1527
+ "or"
1528
+ ],
1529
+ [
1530
+ "hi",
1531
+ "s</w>"
1532
+ ],
1533
+ [
1534
+ "r",
1535
+ "u"
1536
+ ],
1537
+ [
1538
+ "t",
1539
+ "h</w>"
1540
+ ],
1541
+ [
1542
+ "v",
1543
+ "er"
1544
+ ],
1545
+ [
1546
+ "a",
1547
+ "d"
1548
+ ],
1549
+ [
1550
+ "t",
1551
+ "o"
1552
+ ],
1553
+ [
1554
+ "m",
1555
+ "o"
1556
+ ],
1557
+ [
1558
+ "e",
1559
+ "x"
1560
+ ],
1561
+ [
1562
+ "f",
1563
+ "ro"
1564
+ ],
1565
+ [
1566
+ "fro",
1567
+ "m</w>"
1568
+ ],
1569
+ [
1570
+ "a",
1571
+ "b"
1572
+ ],
1573
+ [
1574
+ "w",
1575
+ "hi"
1576
+ ],
1577
+ [
1578
+ "p",
1579
+ "er"
1580
+ ],
1581
+ [
1582
+ "c",
1583
+ "u"
1584
+ ],
1585
+ [
1586
+ "e",
1587
+ "a"
1588
+ ],
1589
+ [
1590
+ "d",
1591
+ "s</w>"
1592
+ ],
1593
+ [
1594
+ "w",
1595
+ "ere</w>"
1596
+ ],
1597
+ [
1598
+ "i",
1599
+ "c"
1600
+ ],
1601
+ [
1602
+ "o",
1603
+ "m"
1604
+ ],
1605
+ [
1606
+ "a",
1607
+ "p"
1608
+ ],
1609
+ [
1610
+ "it",
1611
+ "y</w>"
1612
+ ],
1613
+ [
1614
+ "a",
1615
+ "tion</w>"
1616
+ ],
1617
+ [
1618
+ "t",
1619
+ "er</w>"
1620
+ ],
1621
+ [
1622
+ "p",
1623
+ "re"
1624
+ ],
1625
+ [
1626
+ "ou",
1627
+ "n"
1628
+ ],
1629
+ [
1630
+ "a",
1631
+ "i"
1632
+ ],
1633
+ [
1634
+ "f",
1635
+ "e"
1636
+ ],
1637
+ [
1638
+ "l",
1639
+ "u"
1640
+ ],
1641
+ [
1642
+ "t",
1643
+ "er"
1644
+ ],
1645
+ [
1646
+ "at",
1647
+ "ed</w>"
1648
+ ],
1649
+ [
1650
+ "d",
1651
+ "e</w>"
1652
+ ],
1653
+ [
1654
+ "d",
1655
+ "u"
1656
+ ],
1657
+ [
1658
+ "g",
1659
+ "o"
1660
+ ],
1661
+ [
1662
+ "b",
1663
+ "o"
1664
+ ],
1665
+ [
1666
+ "al",
1667
+ "l</w>"
1668
+ ],
1669
+ [
1670
+ "w",
1671
+ "e"
1672
+ ],
1673
+ [
1674
+ "at",
1675
+ "e</w>"
1676
+ ],
1677
+ [
1678
+ "ti",
1679
+ "m"
1680
+ ],
1681
+ [
1682
+ "re",
1683
+ "c"
1684
+ ],
1685
+ [
1686
+ "ar",
1687
+ "e</w>"
1688
+ ],
1689
+ [
1690
+ "q",
1691
+ "u"
1692
+ ],
1693
+ [
1694
+ "th",
1695
+ "er</w>"
1696
+ ],
1697
+ [
1698
+ "m",
1699
+ "an"
1700
+ ],
1701
+ [
1702
+ "d",
1703
+ "ing</w>"
1704
+ ],
1705
+ [
1706
+ "m",
1707
+ "e"
1708
+ ],
1709
+ [
1710
+ "o",
1711
+ "p"
1712
+ ],
1713
+ [
1714
+ "g",
1715
+ "u"
1716
+ ],
1717
+ [
1718
+ "p",
1719
+ "ar"
1720
+ ],
1721
+ [
1722
+ "t",
1723
+ "r"
1724
+ ],
1725
+ [
1726
+ "on",
1727
+ "e</w>"
1728
+ ],
1729
+ [
1730
+ "whi",
1731
+ "ch</w>"
1732
+ ],
1733
+ [
1734
+ "g",
1735
+ "i"
1736
+ ],
1737
+ [
1738
+ "e",
1739
+ "c"
1740
+ ],
1741
+ [
1742
+ "â",
1743
+ "Ģ"
1744
+ ],
1745
+ [
1746
+ "d",
1747
+ "ed</w>"
1748
+ ],
1749
+ [
1750
+ "s",
1751
+ "s</w>"
1752
+ ],
1753
+ [
1754
+ "p",
1755
+ "or"
1756
+ ],
1757
+ [
1758
+ "am",
1759
+ "e</w>"
1760
+ ],
1761
+ [
1762
+ "ha",
1763
+ "d</w>"
1764
+ ],
1765
+ [
1766
+ "w",
1767
+ "or"
1768
+ ],
1769
+ [
1770
+ "a",
1771
+ "f"
1772
+ ],
1773
+ [
1774
+ "d",
1775
+ "er"
1776
+ ],
1777
+ [
1778
+ "v",
1779
+ "er</w>"
1780
+ ],
1781
+ [
1782
+ "in",
1783
+ "g"
1784
+ ],
1785
+ [
1786
+ "s",
1787
+ "c"
1788
+ ],
1789
+ [
1790
+ "e",
1791
+ "ar"
1792
+ ],
1793
+ [
1794
+ "b",
1795
+ "e</w>"
1796
+ ],
1797
+ [
1798
+ "h",
1799
+ "o"
1800
+ ],
1801
+ [
1802
+ "s",
1803
+ "o</w>"
1804
+ ],
1805
+ [
1806
+ "tion",
1807
+ "s</w>"
1808
+ ],
1809
+ [
1810
+ "t",
1811
+ "a"
1812
+ ],
1813
+ [
1814
+ "b",
1815
+ "er</w>"
1816
+ ],
1817
+ [
1818
+ "l",
1819
+ "d</w>"
1820
+ ],
1821
+ [
1822
+ "w",
1823
+ "a"
1824
+ ],
1825
+ [
1826
+ "m",
1827
+ "u"
1828
+ ],
1829
+ [
1830
+ "n",
1831
+ "i"
1832
+ ],
1833
+ [
1834
+ "s",
1835
+ "ed</w>"
1836
+ ],
1837
+ [
1838
+ "m",
1839
+ "ar"
1840
+ ],
1841
+ [
1842
+ "t",
1843
+ "ur"
1844
+ ],
1845
+ [
1846
+ "al",
1847
+ "ly</w>"
1848
+ ],
1849
+ [
1850
+ "o",
1851
+ "f"
1852
+ ],
1853
+ [
1854
+ "p",
1855
+ "u"
1856
+ ],
1857
+ [
1858
+ "gh",
1859
+ "t</w>"
1860
+ ],
1861
+ [
1862
+ "s",
1863
+ "hi"
1864
+ ],
1865
+ [
1866
+ "m",
1867
+ "i"
1868
+ ],
1869
+ [
1870
+ "t",
1871
+ "w"
1872
+ ],
1873
+ [
1874
+ "e",
1875
+ "st"
1876
+ ],
1877
+ [
1878
+ "ou",
1879
+ "t</w>"
1880
+ ],
1881
+ [
1882
+ "it",
1883
+ "s</w>"
1884
+ ],
1885
+ [
1886
+ "g",
1887
+ "h</w>"
1888
+ ],
1889
+ [
1890
+ "fi",
1891
+ "r"
1892
+ ],
1893
+ [
1894
+ "h",
1895
+ "er</w>"
1896
+ ],
1897
+ [
1898
+ "i",
1899
+ "r</w>"
1900
+ ],
1901
+ [
1902
+ "u",
1903
+ "m"
1904
+ ],
1905
+ [
1906
+ "c",
1907
+ "e"
1908
+ ],
1909
+ [
1910
+ "p",
1911
+ "la"
1912
+ ],
1913
+ [
1914
+ "th",
1915
+ "is</w>"
1916
+ ],
1917
+ [
1918
+ "w",
1919
+ "n</w>"
1920
+ ],
1921
+ [
1922
+ "a",
1923
+ "u"
1924
+ ],
1925
+ [
1926
+ "ro",
1927
+ "u"
1928
+ ],
1929
+ [
1930
+ "p",
1931
+ "l"
1932
+ ],
1933
+ [
1934
+ "sh",
1935
+ "e</w>"
1936
+ ],
1937
+ [
1938
+ "âĢ",
1939
+ "ĵ</w>"
1940
+ ],
1941
+ [
1942
+ "k",
1943
+ "e</w>"
1944
+ ],
1945
+ [
1946
+ "in",
1947
+ "c"
1948
+ ],
1949
+ [
1950
+ "i",
1951
+ "m"
1952
+ ],
1953
+ [
1954
+ "al",
1955
+ "so</w>"
1956
+ ],
1957
+ [
1958
+ "d",
1959
+ "er</w>"
1960
+ ],
1961
+ [
1962
+ "g",
1963
+ "e</w>"
1964
+ ],
1965
+ [
1966
+ "n",
1967
+ "a"
1968
+ ],
1969
+ [
1970
+ "in",
1971
+ "e</w>"
1972
+ ],
1973
+ [
1974
+ "the",
1975
+ "ir</w>"
1976
+ ],
1977
+ [
1978
+ "on",
1979
+ "g</w>"
1980
+ ],
1981
+ [
1982
+ "p",
1983
+ "e"
1984
+ ],
1985
+ [
1986
+ "s",
1987
+ "er"
1988
+ ],
1989
+ [
1990
+ "v",
1991
+ "ed</w>"
1992
+ ],
1993
+ [
1994
+ "ar",
1995
+ "y</w>"
1996
+ ],
1997
+ [
1998
+ "s",
1999
+ "en"
2000
+ ],
2001
+ [
2002
+ "m",
2003
+ "ent</w>"
2004
+ ],
2005
+ [
2006
+ "f",
2007
+ "in"
2008
+ ],
2009
+ [
2010
+ "h",
2011
+ "as</w>"
2012
+ ],
2013
+ [
2014
+ "t",
2015
+ "ing</w>"
2016
+ ],
2017
+ [
2018
+ "d",
2019
+ "o"
2020
+ ],
2021
+ [
2022
+ "s",
2023
+ "h</w>"
2024
+ ],
2025
+ [
2026
+ "no",
2027
+ "t</w>"
2028
+ ],
2029
+ [
2030
+ "t",
2031
+ "e</w>"
2032
+ ],
2033
+ [
2034
+ "r",
2035
+ "an"
2036
+ ],
2037
+ [
2038
+ "s",
2039
+ "a"
2040
+ ],
2041
+ [
2042
+ "m",
2043
+ "or"
2044
+ ],
2045
+ [
2046
+ "or",
2047
+ "i"
2048
+ ],
2049
+ [
2050
+ "m",
2051
+ "in"
2052
+ ],
2053
+ [
2054
+ "l",
2055
+ "ed</w>"
2056
+ ],
2057
+ [
2058
+ ".",
2059
+ "@</w>"
2060
+ ],
2061
+ [
2062
+ "@",
2063
+ ".@</w>"
2064
+ ],
2065
+ [
2066
+ "bu",
2067
+ "t</w>"
2068
+ ],
2069
+ [
2070
+ "af",
2071
+ "ter</w>"
2072
+ ],
2073
+ [
2074
+ "tw",
2075
+ "o</w>"
2076
+ ],
2077
+ [
2078
+ "fir",
2079
+ "st</w>"
2080
+ ],
2081
+ [
2082
+ "s",
2083
+ "ti"
2084
+ ],
2085
+ [
2086
+ "s",
2087
+ "o"
2088
+ ],
2089
+ [
2090
+ "i",
2091
+ "r"
2092
+ ],
2093
+ [
2094
+ "f",
2095
+ "er"
2096
+ ],
2097
+ [
2098
+ "o",
2099
+ "ther</w>"
2100
+ ],
2101
+ [
2102
+ "t",
2103
+ "y</w>"
2104
+ ],
2105
+ [
2106
+ "en",
2107
+ "ts</w>"
2108
+ ],
2109
+ [
2110
+ "the",
2111
+ "y</w>"
2112
+ ],
2113
+ [
2114
+ "com",
2115
+ "m"
2116
+ ],
2117
+ [
2118
+ "t",
2119
+ "u"
2120
+ ],
2121
+ [
2122
+ "w",
2123
+ "i"
2124
+ ],
2125
+ [
2126
+ "g",
2127
+ "e"
2128
+ ],
2129
+ [
2130
+ "t",
2131
+ "e"
2132
+ ],
2133
+ [
2134
+ "ha",
2135
+ "ve</w>"
2136
+ ],
2137
+ [
2138
+ "n",
2139
+ "ed</w>"
2140
+ ],
2141
+ [
2142
+ "t",
2143
+ "en"
2144
+ ],
2145
+ [
2146
+ "s",
2147
+ "s"
2148
+ ],
2149
+ [
2150
+ "ou",
2151
+ "ld</w>"
2152
+ ],
2153
+ [
2154
+ "wh",
2155
+ "o</w>"
2156
+ ],
2157
+ [
2158
+ "p",
2159
+ "i"
2160
+ ],
2161
+ [
2162
+ "d",
2163
+ "a"
2164
+ ],
2165
+ [
2166
+ "as",
2167
+ "t</w>"
2168
+ ],
2169
+ [
2170
+ "ti",
2171
+ "es</w>"
2172
+ ],
2173
+ [
2174
+ "l",
2175
+ "ar"
2176
+ ],
2177
+ [
2178
+ "s",
2179
+ "on</w>"
2180
+ ],
2181
+ [
2182
+ "w",
2183
+ "ar"
2184
+ ],
2185
+ [
2186
+ "sh",
2187
+ "o"
2188
+ ],
2189
+ [
2190
+ "k",
2191
+ "e"
2192
+ ],
2193
+ [
2194
+ "ch",
2195
+ "ar"
2196
+ ],
2197
+ [
2198
+ "be",
2199
+ "en</w>"
2200
+ ],
2201
+ [
2202
+ "ou",
2203
+ "r"
2204
+ ],
2205
+ [
2206
+ ",",
2207
+ "@</w>"
2208
+ ],
2209
+ [
2210
+ "@",
2211
+ ",@</w>"
2212
+ ],
2213
+ [
2214
+ "m",
2215
+ "an</w>"
2216
+ ],
2217
+ [
2218
+ "ne",
2219
+ "w</w>"
2220
+ ],
2221
+ [
2222
+ "k",
2223
+ "s</w>"
2224
+ ],
2225
+ [
2226
+ "m",
2227
+ "on"
2228
+ ],
2229
+ [
2230
+ "si",
2231
+ "on</w>"
2232
+ ],
2233
+ [
2234
+ "g",
2235
+ "en"
2236
+ ],
2237
+ [
2238
+ "or",
2239
+ "y</w>"
2240
+ ],
2241
+ [
2242
+ "ur",
2243
+ "ing</w>"
2244
+ ],
2245
+ [
2246
+ "a",
2247
+ "r</w>"
2248
+ ],
2249
+ [
2250
+ "g",
2251
+ "re"
2252
+ ],
2253
+ [
2254
+ "at",
2255
+ "er</w>"
2256
+ ],
2257
+ [
2258
+ "lo",
2259
+ "w"
2260
+ ],
2261
+ [
2262
+ "an",
2263
+ "t</w>"
2264
+ ],
2265
+ [
2266
+ "si",
2267
+ "g"
2268
+ ],
2269
+ [
2270
+ "el",
2271
+ "y</w>"
2272
+ ],
2273
+ [
2274
+ "f",
2275
+ "t</w>"
2276
+ ],
2277
+ [
2278
+ "con",
2279
+ "t"
2280
+ ],
2281
+ [
2282
+ "f",
2283
+ "u"
2284
+ ],
2285
+ [
2286
+ "r",
2287
+ "it"
2288
+ ],
2289
+ [
2290
+ "ag",
2291
+ "e</w>"
2292
+ ],
2293
+ [
2294
+ "ou",
2295
+ "s</w>"
2296
+ ],
2297
+ [
2298
+ "c",
2299
+ "re"
2300
+ ],
2301
+ [
2302
+ "c",
2303
+ "en"
2304
+ ],
2305
+ [
2306
+ "st",
2307
+ "e"
2308
+ ],
2309
+ [
2310
+ "e",
2311
+ "l</w>"
2312
+ ],
2313
+ [
2314
+ "du",
2315
+ "c"
2316
+ ],
2317
+ [
2318
+ "u",
2319
+ "s</w>"
2320
+ ],
2321
+ [
2322
+ "po",
2323
+ "li"
2324
+ ],
2325
+ [
2326
+ "tion",
2327
+ "al</w>"
2328
+ ],
2329
+ [
2330
+ "om",
2331
+ "e</w>"
2332
+ ],
2333
+ [
2334
+ "tim",
2335
+ "e</w>"
2336
+ ],
2337
+ [
2338
+ "t",
2339
+ "ra"
2340
+ ],
2341
+ [
2342
+ "al",
2343
+ "i"
2344
+ ],
2345
+ [
2346
+ "pla",
2347
+ "y"
2348
+ ],
2349
+ [
2350
+ "k",
2351
+ "ing</w>"
2352
+ ],
2353
+ [
2354
+ "sp",
2355
+ "e"
2356
+ ],
2357
+ [
2358
+ "ou",
2359
+ "r</w>"
2360
+ ],
2361
+ [
2362
+ "o",
2363
+ "c"
2364
+ ],
2365
+ [
2366
+ "it",
2367
+ "ed</w>"
2368
+ ],
2369
+ [
2370
+ "fi",
2371
+ "l"
2372
+ ],
2373
+ [
2374
+ "ai",
2375
+ "r"
2376
+ ],
2377
+ [
2378
+ "b",
2379
+ "ri"
2380
+ ],
2381
+ [
2382
+ "al",
2383
+ "s</w>"
2384
+ ],
2385
+ [
2386
+ "e",
2387
+ "v"
2388
+ ],
2389
+ [
2390
+ "o",
2391
+ "o"
2392
+ ],
2393
+ [
2394
+ "ar",
2395
+ "i"
2396
+ ],
2397
+ [
2398
+ "in",
2399
+ "ter"
2400
+ ],
2401
+ [
2402
+ "ti",
2403
+ "c"
2404
+ ],
2405
+ [
2406
+ "un",
2407
+ "i"
2408
+ ],
2409
+ [
2410
+ "g",
2411
+ "ra"
2412
+ ],
2413
+ [
2414
+ "la",
2415
+ "r</w>"
2416
+ ],
2417
+ [
2418
+ "se",
2419
+ "as"
2420
+ ],
2421
+ [
2422
+ "d",
2423
+ "uring</w>"
2424
+ ],
2425
+ [
2426
+ "st",
2427
+ "ru"
2428
+ ],
2429
+ [
2430
+ "re",
2431
+ "s</w>"
2432
+ ],
2433
+ [
2434
+ "n",
2435
+ "or"
2436
+ ],
2437
+ [
2438
+ "p",
2439
+ "p"
2440
+ ],
2441
+ [
2442
+ "j",
2443
+ "o"
2444
+ ],
2445
+ [
2446
+ "th",
2447
+ "ou"
2448
+ ],
2449
+ [
2450
+ "em",
2451
+ "ber</w>"
2452
+ ],
2453
+ [
2454
+ "l",
2455
+ "and</w>"
2456
+ ],
2457
+ [
2458
+ "or",
2459
+ "d"
2460
+ ],
2461
+ [
2462
+ "c",
2463
+ "k</w>"
2464
+ ],
2465
+ [
2466
+ "it",
2467
+ "e</w>"
2468
+ ],
2469
+ [
2470
+ "inc",
2471
+ "lu"
2472
+ ],
2473
+ [
2474
+ "an",
2475
+ "ce</w>"
2476
+ ],
2477
+ [
2478
+ "st",
2479
+ "r"
2480
+ ],
2481
+ [
2482
+ "p",
2483
+ "ri"
2484
+ ],
2485
+ [
2486
+ "ur",
2487
+ "e</w>"
2488
+ ],
2489
+ [
2490
+ "ti",
2491
+ "ve</w>"
2492
+ ],
2493
+ [
2494
+ "at",
2495
+ "t"
2496
+ ],
2497
+ [
2498
+ "re",
2499
+ "e</w>"
2500
+ ],
2501
+ [
2502
+ "ac",
2503
+ "k</w>"
2504
+ ],
2505
+ [
2506
+ "co",
2507
+ "l"
2508
+ ],
2509
+ [
2510
+ "cu",
2511
+ "l"
2512
+ ],
2513
+ [
2514
+ "mor",
2515
+ "e</w>"
2516
+ ],
2517
+ [
2518
+ "b",
2519
+ "li"
2520
+ ],
2521
+ [
2522
+ "g",
2523
+ "ro"
2524
+ ],
2525
+ [
2526
+ "as",
2527
+ "ed</w>"
2528
+ ],
2529
+ [
2530
+ "p",
2531
+ "s</w>"
2532
+ ],
2533
+ [
2534
+ "th",
2535
+ "an</w>"
2536
+ ],
2537
+ [
2538
+ "for",
2539
+ "m"
2540
+ ],
2541
+ [
2542
+ "y",
2543
+ "p"
2544
+ ],
2545
+ [
2546
+ "com",
2547
+ "p"
2548
+ ],
2549
+ [
2550
+ "rec",
2551
+ "or"
2552
+ ],
2553
+ [
2554
+ "c",
2555
+ "or"
2556
+ ],
2557
+ [
2558
+ "el",
2559
+ "l</w>"
2560
+ ],
2561
+ [
2562
+ "mo",
2563
+ "st</w>"
2564
+ ],
2565
+ [
2566
+ "at",
2567
+ "es</w>"
2568
+ ],
2569
+ [
2570
+ "in",
2571
+ "s</w>"
2572
+ ],
2573
+ [
2574
+ "in",
2575
+ "ed</w>"
2576
+ ],
2577
+ [
2578
+ "c",
2579
+ "hi"
2580
+ ],
2581
+ [
2582
+ "pu",
2583
+ "bli"
2584
+ ],
2585
+ [
2586
+ "wa",
2587
+ "y</w>"
2588
+ ],
2589
+ [
2590
+ "e",
2591
+ "t</w>"
2592
+ ],
2593
+ [
2594
+ "c",
2595
+ "ar"
2596
+ ],
2597
+ [
2598
+ "l",
2599
+ "es</w>"
2600
+ ],
2601
+ [
2602
+ "a",
2603
+ "d</w>"
2604
+ ],
2605
+ [
2606
+ "c",
2607
+ "es</w>"
2608
+ ],
2609
+ [
2610
+ "s",
2611
+ "ch"
2612
+ ],
2613
+ [
2614
+ "spe",
2615
+ "ci"
2616
+ ],
2617
+ [
2618
+ "on",
2619
+ "s</w>"
2620
+ ],
2621
+ [
2622
+ "en",
2623
+ "ce</w>"
2624
+ ],
2625
+ [
2626
+ "al",
2627
+ "bu"
2628
+ ],
2629
+ [
2630
+ "v",
2631
+ "es</w>"
2632
+ ],
2633
+ [
2634
+ "ea",
2635
+ "r</w>"
2636
+ ],
2637
+ [
2638
+ "re",
2639
+ "n"
2640
+ ],
2641
+ [
2642
+ "ch",
2643
+ "a"
2644
+ ],
2645
+ [
2646
+ "shi",
2647
+ "p</w>"
2648
+ ],
2649
+ [
2650
+ "j",
2651
+ "u"
2652
+ ],
2653
+ [
2654
+ "oun",
2655
+ "d</w>"
2656
+ ],
2657
+ [
2658
+ "ol",
2659
+ "d</w>"
2660
+ ],
2661
+ [
2662
+ "k",
2663
+ "ed</w>"
2664
+ ],
2665
+ [
2666
+ "an",
2667
+ "d"
2668
+ ],
2669
+ [
2670
+ "ac",
2671
+ "e</w>"
2672
+ ],
2673
+ [
2674
+ "seas",
2675
+ "on</w>"
2676
+ ],
2677
+ [
2678
+ "s",
2679
+ "el"
2680
+ ],
2681
+ [
2682
+ "ab",
2683
+ "le</w>"
2684
+ ],
2685
+ [
2686
+ "in",
2687
+ "di"
2688
+ ],
2689
+ [
2690
+ "p",
2691
+ "h"
2692
+ ],
2693
+ [
2694
+ "t",
2695
+ "ri"
2696
+ ],
2697
+ [
2698
+ "e",
2699
+ "i"
2700
+ ],
2701
+ [
2702
+ "c",
2703
+ "ity</w>"
2704
+ ],
2705
+ [
2706
+ "ca",
2707
+ "u"
2708
+ ],
2709
+ [
2710
+ "m",
2711
+ "il"
2712
+ ],
2713
+ [
2714
+ "b",
2715
+ "i"
2716
+ ],
2717
+ [
2718
+ "t",
2719
+ "ly</w>"
2720
+ ],
2721
+ [
2722
+ "in",
2723
+ "to</w>"
2724
+ ],
2725
+ [
2726
+ "c",
2727
+ "l"
2728
+ ],
2729
+ [
2730
+ "r",
2731
+ "ed</w>"
2732
+ ],
2733
+ [
2734
+ "l",
2735
+ "s</w>"
2736
+ ],
2737
+ [
2738
+ "s",
2739
+ "ou"
2740
+ ],
2741
+ [
2742
+ "as",
2743
+ "e</w>"
2744
+ ],
2745
+ [
2746
+ "ing",
2747
+ "s</w>"
2748
+ ],
2749
+ [
2750
+ "v",
2751
+ "ing</w>"
2752
+ ],
2753
+ [
2754
+ "ac",
2755
+ "h"
2756
+ ],
2757
+ [
2758
+ "s",
2759
+ "y"
2760
+ ],
2761
+ [
2762
+ "wh",
2763
+ "en</w>"
2764
+ ],
2765
+ [
2766
+ "o",
2767
+ "lo"
2768
+ ],
2769
+ [
2770
+ "o",
2771
+ "ver</w>"
2772
+ ],
2773
+ [
2774
+ "hi",
2775
+ "st"
2776
+ ],
2777
+ [
2778
+ "thou",
2779
+ "gh</w>"
2780
+ ],
2781
+ [
2782
+ "en",
2783
+ "d</w>"
2784
+ ],
2785
+ [
2786
+ "ti",
2787
+ "c</w>"
2788
+ ],
2789
+ [
2790
+ "di",
2791
+ "s"
2792
+ ],
2793
+ [
2794
+ "se",
2795
+ "con"
2796
+ ],
2797
+ [
2798
+ "c",
2799
+ "an"
2800
+ ],
2801
+ [
2802
+ "s",
2803
+ "ur"
2804
+ ],
2805
+ [
2806
+ "on",
2807
+ "ly</w>"
2808
+ ],
2809
+ [
2810
+ "ma",
2811
+ "y</w>"
2812
+ ],
2813
+ [
2814
+ "ord",
2815
+ "an</w>"
2816
+ ],
2817
+ [
2818
+ "c",
2819
+ "oun"
2820
+ ],
2821
+ [
2822
+ "j",
2823
+ "ordan</w>"
2824
+ ],
2825
+ [
2826
+ "m",
2827
+ "s</w>"
2828
+ ],
2829
+ [
2830
+ "an",
2831
+ "s</w>"
2832
+ ],
2833
+ [
2834
+ "albu",
2835
+ "m</w>"
2836
+ ],
2837
+ [
2838
+ "er",
2839
+ "n</w>"
2840
+ ],
2841
+ [
2842
+ "b",
2843
+ "le</w>"
2844
+ ],
2845
+ [
2846
+ "r",
2847
+ "e</w>"
2848
+ ],
2849
+ [
2850
+ "w",
2851
+ "n"
2852
+ ],
2853
+ [
2854
+ "ac",
2855
+ "h</w>"
2856
+ ],
2857
+ [
2858
+ "am",
2859
+ "es</w>"
2860
+ ],
2861
+ [
2862
+ "o",
2863
+ "k</w>"
2864
+ ],
2865
+ [
2866
+ "y",
2867
+ "s</w>"
2868
+ ],
2869
+ [
2870
+ "u",
2871
+ "p</w>"
2872
+ ],
2873
+ [
2874
+ "th",
2875
+ "ere</w>"
2876
+ ],
2877
+ [
2878
+ "su",
2879
+ "b"
2880
+ ],
2881
+ [
2882
+ "e",
2883
+ "g"
2884
+ ],
2885
+ [
2886
+ "n",
2887
+ "um"
2888
+ ],
2889
+ [
2890
+ "man",
2891
+ "y</w>"
2892
+ ],
2893
+ [
2894
+ "th",
2895
+ "ree</w>"
2896
+ ],
2897
+ [
2898
+ "g",
2899
+ "in"
2900
+ ],
2901
+ [
2902
+ "re",
2903
+ "le"
2904
+ ],
2905
+ [
2906
+ "sh",
2907
+ "ed</w>"
2908
+ ],
2909
+ [
2910
+ "ag",
2911
+ "a"
2912
+ ],
2913
+ [
2914
+ "g",
2915
+ "al"
2916
+ ],
2917
+ [
2918
+ "k",
2919
+ "no"
2920
+ ],
2921
+ [
2922
+ "o",
2923
+ "d</w>"
2924
+ ],
2925
+ [
2926
+ "whi",
2927
+ "le</w>"
2928
+ ],
2929
+ [
2930
+ "y",
2931
+ "ear</w>"
2932
+ ],
2933
+ [
2934
+ "or",
2935
+ "s</w>"
2936
+ ],
2937
+ [
2938
+ "n",
2939
+ "ing</w>"
2940
+ ],
2941
+ [
2942
+ "p",
2943
+ "a"
2944
+ ],
2945
+ [
2946
+ "l",
2947
+ "ater</w>"
2948
+ ],
2949
+ [
2950
+ "v",
2951
+ "e"
2952
+ ],
2953
+ [
2954
+ "n",
2955
+ "o</w>"
2956
+ ],
2957
+ [
2958
+ "th",
2959
+ "rou"
2960
+ ],
2961
+ [
2962
+ "y",
2963
+ "ing</w>"
2964
+ ],
2965
+ [
2966
+ "em",
2967
+ "p"
2968
+ ],
2969
+ [
2970
+ "a",
2971
+ "tions</w>"
2972
+ ],
2973
+ [
2974
+ "i",
2975
+ "c</w>"
2976
+ ],
2977
+ [
2978
+ "vi",
2979
+ "e"
2980
+ ],
2981
+ [
2982
+ "wh",
2983
+ "e"
2984
+ ],
2985
+ [
2986
+ "s",
2987
+ "si"
2988
+ ],
2989
+ [
2990
+ "c",
2991
+ "ame</w>"
2992
+ ],
2993
+ [
2994
+ "si",
2995
+ "c</w>"
2996
+ ],
2997
+ [
2998
+ "f",
2999
+ "a"
3000
+ ],
3001
+ [
3002
+ "be",
3003
+ "t"
3004
+ ],
3005
+ [
3006
+ "wa",
3007
+ "r</w>"
3008
+ ],
3009
+ [
3010
+ "b",
3011
+ "ro"
3012
+ ],
3013
+ [
3014
+ "w",
3015
+ "ould</w>"
3016
+ ],
3017
+ [
3018
+ "s",
3019
+ "ome</w>"
3020
+ ],
3021
+ [
3022
+ "l",
3023
+ "l</w>"
3024
+ ],
3025
+ [
3026
+ "de",
3027
+ "v"
3028
+ ],
3029
+ [
3030
+ "ic",
3031
+ "al</w>"
3032
+ ],
3033
+ [
3034
+ "s",
3035
+ "k"
3036
+ ],
3037
+ [
3038
+ "pro",
3039
+ "duc"
3040
+ ],
3041
+ [
3042
+ "por",
3043
+ "t</w>"
3044
+ ],
3045
+ [
3046
+ "sc",
3047
+ "ri"
3048
+ ],
3049
+ [
3050
+ "bu",
3051
+ "il"
3052
+ ],
3053
+ [
3054
+ "b",
3055
+ "ar"
3056
+ ],
3057
+ [
3058
+ "g",
3059
+ "ame</w>"
3060
+ ],
3061
+ [
3062
+ "fil",
3063
+ "m</w>"
3064
+ ],
3065
+ [
3066
+ "b",
3067
+ "a"
3068
+ ],
3069
+ [
3070
+ "th",
3071
+ "o"
3072
+ ],
3073
+ [
3074
+ "lo",
3075
+ "c"
3076
+ ],
3077
+ [
3078
+ "be",
3079
+ "ing</w>"
3080
+ ],
3081
+ [
3082
+ "the",
3083
+ "se</w>"
3084
+ ],
3085
+ [
3086
+ "ab",
3087
+ "out</w>"
3088
+ ],
3089
+ [
3090
+ "so",
3091
+ "ci"
3092
+ ],
3093
+ [
3094
+ "s",
3095
+ "ing</w>"
3096
+ ],
3097
+ [
3098
+ "l",
3099
+ "an"
3100
+ ],
3101
+ [
3102
+ "t",
3103
+ "re"
3104
+ ],
3105
+ [
3106
+ "t",
3107
+ "en</w>"
3108
+ ],
3109
+ [
3110
+ "w",
3111
+ "rit"
3112
+ ],
3113
+ [
3114
+ "f",
3115
+ "ol"
3116
+ ],
3117
+ [
3118
+ "ar",
3119
+ "d</w>"
3120
+ ],
3121
+ [
3122
+ "u",
3123
+ "e</w>"
3124
+ ],
3125
+ [
3126
+ "ea",
3127
+ "m</w>"
3128
+ ],
3129
+ [
3130
+ "st",
3131
+ "s</w>"
3132
+ ],
3133
+ [
3134
+ "hi",
3135
+ "m</w>"
3136
+ ],
3137
+ [
3138
+ "ap",
3139
+ "p"
3140
+ ],
3141
+ [
3142
+ "g",
3143
+ "er"
3144
+ ],
3145
+ [
3146
+ "the",
3147
+ "m</w>"
3148
+ ],
3149
+ [
3150
+ "stru",
3151
+ "c"
3152
+ ],
3153
+ [
3154
+ "of",
3155
+ "fi"
3156
+ ],
3157
+ [
3158
+ "m",
3159
+ "y</w>"
3160
+ ],
3161
+ [
3162
+ "an",
3163
+ "i"
3164
+ ],
3165
+ [
3166
+ "da",
3167
+ "y</w>"
3168
+ ],
3169
+ [
3170
+ "d",
3171
+ "y</w>"
3172
+ ],
3173
+ [
3174
+ "h",
3175
+ "e"
3176
+ ],
3177
+ [
3178
+ "u",
3179
+ "m</w>"
3180
+ ],
3181
+ [
3182
+ "st",
3183
+ "ri"
3184
+ ],
3185
+ [
3186
+ "st",
3187
+ "u"
3188
+ ],
3189
+ [
3190
+ "el",
3191
+ "e"
3192
+ ],
3193
+ [
3194
+ "whe",
3195
+ "el"
3196
+ ],
3197
+ [
3198
+ "c",
3199
+ "ra"
3200
+ ],
3201
+ [
3202
+ "secon",
3203
+ "d</w>"
3204
+ ],
3205
+ [
3206
+ "on",
3207
+ "g"
3208
+ ],
3209
+ [
3210
+ "si",
3211
+ "de</w>"
3212
+ ],
3213
+ [
3214
+ "su",
3215
+ "ch</w>"
3216
+ ],
3217
+ [
3218
+ "t",
3219
+ "eam</w>"
3220
+ ],
3221
+ [
3222
+ "at",
3223
+ "ing</w>"
3224
+ ],
3225
+ [
3226
+ "c",
3227
+ "an</w>"
3228
+ ],
3229
+ [
3230
+ "f",
3231
+ "ac"
3232
+ ],
3233
+ [
3234
+ "m",
3235
+ "is"
3236
+ ],
3237
+ [
3238
+ "wheel",
3239
+ "er</w>"
3240
+ ],
3241
+ [
3242
+ "d",
3243
+ "en"
3244
+ ],
3245
+ [
3246
+ "m",
3247
+ "e</w>"
3248
+ ],
3249
+ [
3250
+ "c",
3251
+ "ri"
3252
+ ],
3253
+ [
3254
+ "ch",
3255
+ "ri"
3256
+ ],
3257
+ [
3258
+ "we",
3259
+ "en</w>"
3260
+ ],
3261
+ [
3262
+ "cha",
3263
+ "e"
3264
+ ],
3265
+ [
3266
+ "g",
3267
+ "a"
3268
+ ],
3269
+ [
3270
+ "l",
3271
+ "ing</w>"
3272
+ ],
3273
+ [
3274
+ "s",
3275
+ "es</w>"
3276
+ ],
3277
+ [
3278
+ "bet",
3279
+ "ween</w>"
3280
+ ],
3281
+ [
3282
+ "m",
3283
+ "at"
3284
+ ],
3285
+ [
3286
+ "v",
3287
+ "est"
3288
+ ],
3289
+ [
3290
+ "po",
3291
+ "in"
3292
+ ],
3293
+ [
3294
+ "gen",
3295
+ "er"
3296
+ ],
3297
+ [
3298
+ "c",
3299
+ "al"
3300
+ ],
3301
+ [
3302
+ "w",
3303
+ "il"
3304
+ ],
3305
+ [
3306
+ "ti",
3307
+ "sh</w>"
3308
+ ],
3309
+ [
3310
+ "ar",
3311
+ "chae"
3312
+ ],
3313
+ [
3314
+ "ear",
3315
+ "s</w>"
3316
+ ],
3317
+ [
3318
+ "archae",
3319
+ "olo"
3320
+ ],
3321
+ [
3322
+ "j",
3323
+ "ec"
3324
+ ],
3325
+ [
3326
+ "t",
3327
+ "al</w>"
3328
+ ],
3329
+ [
3330
+ "un",
3331
+ "d</w>"
3332
+ ],
3333
+ [
3334
+ "s",
3335
+ "in"
3336
+ ],
3337
+ [
3338
+ "v",
3339
+ "en"
3340
+ ],
3341
+ [
3342
+ "ma",
3343
+ "de</w>"
3344
+ ],
3345
+ [
3346
+ "su",
3347
+ "l"
3348
+ ],
3349
+ [
3350
+ "tur",
3351
+ "e</w>"
3352
+ ],
3353
+ [
3354
+ "o",
3355
+ "per"
3356
+ ],
3357
+ [
3358
+ "v",
3359
+ "en</w>"
3360
+ ],
3361
+ [
3362
+ "w",
3363
+ "s</w>"
3364
+ ],
3365
+ [
3366
+ "wh",
3367
+ "ere</w>"
3368
+ ],
3369
+ [
3370
+ "r",
3371
+ "on"
3372
+ ],
3373
+ [
3374
+ "con",
3375
+ "si"
3376
+ ],
3377
+ [
3378
+ "f",
3379
+ "our</w>"
3380
+ ],
3381
+ [
3382
+ "t",
3383
+ "on</w>"
3384
+ ],
3385
+ [
3386
+ "o",
3387
+ "b"
3388
+ ],
3389
+ [
3390
+ "w",
3391
+ "er</w>"
3392
+ ],
3393
+ [
3394
+ "se",
3395
+ "ver"
3396
+ ],
3397
+ [
3398
+ "un",
3399
+ "der</w>"
3400
+ ],
3401
+ [
3402
+ "wor",
3403
+ "k</w>"
3404
+ ],
3405
+ [
3406
+ "am",
3407
+ "er"
3408
+ ],
3409
+ [
3410
+ "ca",
3411
+ "p"
3412
+ ],
3413
+ [
3414
+ "na",
3415
+ "tional</w>"
3416
+ ],
3417
+ [
3418
+ "wi",
3419
+ "th"
3420
+ ],
3421
+ [
3422
+ "for",
3423
+ "e</w>"
3424
+ ],
3425
+ [
3426
+ "th",
3427
+ "en</w>"
3428
+ ],
3429
+ [
3430
+ "al",
3431
+ "though</w>"
3432
+ ],
3433
+ [
3434
+ "s",
3435
+ "m"
3436
+ ],
3437
+ [
3438
+ "on",
3439
+ "y</w>"
3440
+ ],
3441
+ [
3442
+ "el",
3443
+ "d</w>"
3444
+ ],
3445
+ [
3446
+ "ch",
3447
+ "ur"
3448
+ ],
3449
+ [
3450
+ "bri",
3451
+ "tish</w>"
3452
+ ],
3453
+ [
3454
+ "gal",
3455
+ "vest"
3456
+ ],
3457
+ [
3458
+ "bo",
3459
+ "th</w>"
3460
+ ],
3461
+ [
3462
+ "b",
3463
+ "er"
3464
+ ],
3465
+ [
3466
+ "st",
3467
+ "ed</w>"
3468
+ ],
3469
+ [
3470
+ "di",
3471
+ "rec"
3472
+ ],
3473
+ [
3474
+ "galvest",
3475
+ "on</w>"
3476
+ ],
3477
+ [
3478
+ "f",
3479
+ "e</w>"
3480
+ ],
3481
+ [
3482
+ "w",
3483
+ "ell</w>"
3484
+ ],
3485
+ [
3486
+ "d",
3487
+ "re"
3488
+ ],
3489
+ [
3490
+ "y",
3491
+ "or"
3492
+ ],
3493
+ [
3494
+ "no",
3495
+ "v"
3496
+ ],
3497
+ [
3498
+ "l",
3499
+ "it"
3500
+ ],
3501
+ [
3502
+ "t",
3503
+ "ro"
3504
+ ],
3505
+ [
3506
+ "de",
3507
+ "scri"
3508
+ ],
3509
+ [
3510
+ "ca",
3511
+ "tion</w>"
3512
+ ],
3513
+ [
3514
+ "ai",
3515
+ "d</w>"
3516
+ ],
3517
+ [
3518
+ "tr",
3519
+ "an"
3520
+ ],
3521
+ [
3522
+ "in",
3523
+ "i"
3524
+ ],
3525
+ [
3526
+ "st",
3527
+ "ate</w>"
3528
+ ],
3529
+ [
3530
+ "per",
3531
+ "i"
3532
+ ],
3533
+ [
3534
+ "d",
3535
+ "es</w>"
3536
+ ],
3537
+ [
3538
+ "e",
3539
+ "st</w>"
3540
+ ],
3541
+ [
3542
+ "h",
3543
+ "ea"
3544
+ ],
3545
+ [
3546
+ "p",
3547
+ "en"
3548
+ ],
3549
+ [
3550
+ "y",
3551
+ "ears</w>"
3552
+ ],
3553
+ [
3554
+ "wor",
3555
+ "ld</w>"
3556
+ ],
3557
+ [
3558
+ "i",
3559
+ "es</w>"
3560
+ ],
3561
+ [
3562
+ "u",
3563
+ "sed</w>"
3564
+ ],
3565
+ [
3566
+ "go",
3567
+ "ds</w>"
3568
+ ],
3569
+ [
3570
+ "t",
3571
+ "ers</w>"
3572
+ ],
3573
+ [
3574
+ "di",
3575
+ "f"
3576
+ ],
3577
+ [
3578
+ "fol",
3579
+ "low"
3580
+ ],
3581
+ [
3582
+ "a",
3583
+ "re"
3584
+ ],
3585
+ [
3586
+ "e",
3587
+ "s"
3588
+ ],
3589
+ [
3590
+ "g",
3591
+ "an</w>"
3592
+ ],
3593
+ [
3594
+ "st",
3595
+ "ar"
3596
+ ],
3597
+ [
3598
+ "li",
3599
+ "ke</w>"
3600
+ ],
3601
+ [
3602
+ "ear",
3603
+ "ly</w>"
3604
+ ],
3605
+ [
3606
+ "m",
3607
+ "en"
3608
+ ],
3609
+ [
3610
+ "s",
3611
+ "ing"
3612
+ ],
3613
+ [
3614
+ "b",
3615
+ "or"
3616
+ ],
3617
+ [
3618
+ "t",
3619
+ "or</w>"
3620
+ ],
3621
+ [
3622
+ "mu",
3623
+ "sic</w>"
3624
+ ],
3625
+ [
3626
+ "cl",
3627
+ "as"
3628
+ ],
3629
+ [
3630
+ "sever",
3631
+ "al</w>"
3632
+ ],
3633
+ [
3634
+ "un",
3635
+ "ited</w>"
3636
+ ],
3637
+ [
3638
+ "num",
3639
+ "ber</w>"
3640
+ ],
3641
+ [
3642
+ "chur",
3643
+ "ch</w>"
3644
+ ],
3645
+ [
3646
+ "yor",
3647
+ "k</w>"
3648
+ ],
3649
+ [
3650
+ "c",
3651
+ "ur"
3652
+ ],
3653
+ [
3654
+ "c",
3655
+ "lo"
3656
+ ],
3657
+ [
3658
+ "an",
3659
+ "g"
3660
+ ],
3661
+ [
3662
+ "re",
3663
+ "sp"
3664
+ ],
3665
+ [
3666
+ "am",
3667
+ "i"
3668
+ ],
3669
+ [
3670
+ "m",
3671
+ "em"
3672
+ ],
3673
+ [
3674
+ "c",
3675
+ "lu"
3676
+ ],
3677
+ [
3678
+ "par",
3679
+ "t</w>"
3680
+ ],
3681
+ [
3682
+ "c",
3683
+ "ed</w>"
3684
+ ],
3685
+ [
3686
+ "c",
3687
+ "er"
3688
+ ],
3689
+ [
3690
+ "j",
3691
+ "e"
3692
+ ],
3693
+ [
3694
+ "t",
3695
+ "ru"
3696
+ ],
3697
+ [
3698
+ "en",
3699
+ "g"
3700
+ ],
3701
+ [
3702
+ "be",
3703
+ "fore</w>"
3704
+ ],
3705
+ [
3706
+ "kno",
3707
+ "wn</w>"
3708
+ ],
3709
+ [
3710
+ "amer",
3711
+ "ic"
3712
+ ],
3713
+ [
3714
+ "l",
3715
+ "ong</w>"
3716
+ ],
3717
+ [
3718
+ "n",
3719
+ "am"
3720
+ ],
3721
+ [
3722
+ "st",
3723
+ "an"
3724
+ ],
3725
+ [
3726
+ "st",
3727
+ "er</w>"
3728
+ ],
3729
+ [
3730
+ "al",
3731
+ "e</w>"
3732
+ ]
3733
+ ]
3734
+ }
3735
+ }
aimv2_vision_model/Aimv2VisionModel/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<start_of_text>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<end_of_text>",
6
+ "errors": "replace",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 77,
10
+ "pad_token": "<end_of_text>",
11
+ "processor_class": "CLIPProcessor",
12
+ "tokenizer_class": "CLIPTokenizer",
13
+ "unk_token": "<end_of_text>",
14
+ "use_fast": true
15
+ }
albert/AlbertForMaskedLM/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "dtype": "float32",
9
+ "embedding_size": 8,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 20,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 8,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_groups": 2,
22
+ "num_hidden_layers": 2,
23
+ "pad_token_id": 0,
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.15.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 1024
28
+ }
albert/AlbertForMaskedLM/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de036786b31e619d8c53fe1208cb04bc25104625c7a84b78197e1192491b55b
3
+ size 58544
albert/AlbertForMaskedLM/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
albert/AlbertForMaskedLM/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "[SEP]",
8
+ "is_local": true,
9
+ "keep_accents": false,
10
+ "local_files_only": false,
11
+ "mask_token": "[MASK]",
12
+ "model_max_length": 8,
13
+ "pad_token": "<pad>",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "AlbertTokenizer",
16
+ "trim_offsets": true,
17
+ "unk_token": "<unk>"
18
+ }
albert/AlbertForMultipleChoice/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForMultipleChoice"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "dtype": "float32",
9
+ "embedding_size": 8,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 20,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 8,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_groups": 2,
22
+ "num_hidden_layers": 2,
23
+ "pad_token_id": 0,
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.15.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 1024
28
+ }
albert/AlbertForMultipleChoice/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2741fb6684b2b93b7f670ef2b33f49c2cb1778c24d2a4bf9c7bea94f34ca54c
3
+ size 54892
albert/AlbertForMultipleChoice/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
albert/AlbertForMultipleChoice/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "[SEP]",
8
+ "is_local": true,
9
+ "keep_accents": false,
10
+ "local_files_only": false,
11
+ "mask_token": "[MASK]",
12
+ "model_max_length": 8,
13
+ "pad_token": "<pad>",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "AlbertTokenizer",
16
+ "trim_offsets": true,
17
+ "unk_token": "<unk>"
18
+ }
albert/AlbertForPreTraining/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "dtype": "float32",
9
+ "embedding_size": 8,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 20,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 8,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_groups": 2,
22
+ "num_hidden_layers": 2,
23
+ "pad_token_id": 0,
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.15.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 1024
28
+ }
albert/AlbertForPreTraining/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63d439622da7233718f34785fe9712390b7f972b902a9b001f83e7bf5545618
3
+ size 60112
albert/AlbertForPreTraining/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
albert/AlbertForPreTraining/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "[SEP]",
8
+ "is_local": true,
9
+ "keep_accents": false,
10
+ "local_files_only": false,
11
+ "mask_token": "[MASK]",
12
+ "model_max_length": 8,
13
+ "pad_token": "<pad>",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "AlbertTokenizer",
16
+ "trim_offsets": true,
17
+ "unk_token": "<unk>"
18
+ }
albert/AlbertForQuestionAnswering/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForQuestionAnswering"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "dtype": "float32",
9
+ "embedding_size": 8,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 20,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 8,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_groups": 2,
22
+ "num_hidden_layers": 2,
23
+ "pad_token_id": 0,
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.15.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 1024
28
+ }
albert/AlbertForQuestionAnswering/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b485b6b156b7bef49016e17b1205d20cc4251883d41945a184c574f9fa41f87
3
+ size 53704
albert/AlbertForQuestionAnswering/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
albert/AlbertForQuestionAnswering/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "[SEP]",
8
+ "is_local": true,
9
+ "keep_accents": false,
10
+ "local_files_only": false,
11
+ "mask_token": "[MASK]",
12
+ "model_max_length": 8,
13
+ "pad_token": "<pad>",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "AlbertTokenizer",
16
+ "trim_offsets": true,
17
+ "unk_token": "<unk>"
18
+ }
albert/AlbertForSequenceClassification/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "dtype": "float32",
9
+ "embedding_size": 8,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 16,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 20,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 8,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_groups": 2,
22
+ "num_hidden_layers": 2,
23
+ "pad_token_id": 0,
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.15.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 1024
28
+ }
albert/AlbertForSequenceClassification/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5acf421f10992202436467664af0fda55393f4bd1a9936a9221972efc9b5e122
3
+ size 54960
albert/AlbertForSequenceClassification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff