hf-transformers-bot commited on
Commit
4ef8685
1 Parent(s): bcb1a4c

Upload tiny models for BloomForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "architectures": [
4
+ "BloomForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_dropout": 0.1,
12
+ "hidden_size": 32,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "is_decoder": true,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_epsilon": 1e-05,
26
+ "model_type": "bloom",
27
+ "n_head": 4,
28
+ "n_layer": 5,
29
+ "n_positions": 512,
30
+ "pad_token_id": 3,
31
+ "pretraining_tp": 1,
32
+ "seq_length": 7,
33
+ "slow_but_exact": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.28.0.dev0",
36
+ "type_vocab_size": 16,
37
+ "use_cache": true,
38
+ "vocab_size": 1024
39
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.28.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ae8617780404cacddd13543967667230b8eb556579702aea5234c686347e0a
3
+ size 406260
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,1938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<unk>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<pad>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Sequence",
46
+ "pretokenizers": [
47
+ {
48
+ "type": "Split",
49
+ "pattern": {
50
+ "Regex": " ?[^(\\s|[.,!?…。,、।۔،])]+"
51
+ },
52
+ "behavior": "Isolated",
53
+ "invert": false
54
+ },
55
+ {
56
+ "type": "ByteLevel",
57
+ "add_prefix_space": false,
58
+ "trim_offsets": true,
59
+ "use_regex": false
60
+ }
61
+ ]
62
+ },
63
+ "post_processor": {
64
+ "type": "ByteLevel",
65
+ "add_prefix_space": true,
66
+ "trim_offsets": false,
67
+ "use_regex": false
68
+ },
69
+ "decoder": {
70
+ "type": "ByteLevel",
71
+ "add_prefix_space": true,
72
+ "trim_offsets": true,
73
+ "use_regex": false
74
+ },
75
+ "model": {
76
+ "type": "BPE",
77
+ "dropout": null,
78
+ "unk_token": null,
79
+ "continuing_subword_prefix": null,
80
+ "end_of_word_suffix": null,
81
+ "fuse_unk": false,
82
+ "vocab": {
83
+ "<unk>": 0,
84
+ "<s>": 1,
85
+ "</s>": 2,
86
+ "<pad>": 3,
87
+ "!": 4,
88
+ "\"": 5,
89
+ "#": 6,
90
+ "$": 7,
91
+ "%": 8,
92
+ "&": 9,
93
+ "'": 10,
94
+ "(": 11,
95
+ ")": 12,
96
+ "*": 13,
97
+ "+": 14,
98
+ ",": 15,
99
+ "-": 16,
100
+ ".": 17,
101
+ "/": 18,
102
+ "0": 19,
103
+ "1": 20,
104
+ "2": 21,
105
+ "3": 22,
106
+ "4": 23,
107
+ "5": 24,
108
+ "6": 25,
109
+ "7": 26,
110
+ "8": 27,
111
+ "9": 28,
112
+ ":": 29,
113
+ ";": 30,
114
+ "<": 31,
115
+ "=": 32,
116
+ ">": 33,
117
+ "?": 34,
118
+ "@": 35,
119
+ "A": 36,
120
+ "B": 37,
121
+ "C": 38,
122
+ "D": 39,
123
+ "E": 40,
124
+ "F": 41,
125
+ "G": 42,
126
+ "H": 43,
127
+ "I": 44,
128
+ "J": 45,
129
+ "K": 46,
130
+ "L": 47,
131
+ "M": 48,
132
+ "N": 49,
133
+ "O": 50,
134
+ "P": 51,
135
+ "Q": 52,
136
+ "R": 53,
137
+ "S": 54,
138
+ "T": 55,
139
+ "U": 56,
140
+ "V": 57,
141
+ "W": 58,
142
+ "X": 59,
143
+ "Y": 60,
144
+ "Z": 61,
145
+ "[": 62,
146
+ "\\": 63,
147
+ "]": 64,
148
+ "^": 65,
149
+ "_": 66,
150
+ "`": 67,
151
+ "a": 68,
152
+ "b": 69,
153
+ "c": 70,
154
+ "d": 71,
155
+ "e": 72,
156
+ "f": 73,
157
+ "g": 74,
158
+ "h": 75,
159
+ "i": 76,
160
+ "j": 77,
161
+ "k": 78,
162
+ "l": 79,
163
+ "m": 80,
164
+ "n": 81,
165
+ "o": 82,
166
+ "p": 83,
167
+ "q": 84,
168
+ "r": 85,
169
+ "s": 86,
170
+ "t": 87,
171
+ "u": 88,
172
+ "v": 89,
173
+ "w": 90,
174
+ "x": 91,
175
+ "y": 92,
176
+ "z": 93,
177
+ "|": 94,
178
+ "}": 95,
179
+ "~": 96,
180
+ "¡": 97,
181
+ "¢": 98,
182
+ "£": 99,
183
+ "¤": 100,
184
+ "¥": 101,
185
+ "¦": 102,
186
+ "§": 103,
187
+ "¨": 104,
188
+ "©": 105,
189
+ "ª": 106,
190
+ "«": 107,
191
+ "¬": 108,
192
+ "®": 109,
193
+ "¯": 110,
194
+ "°": 111,
195
+ "±": 112,
196
+ "²": 113,
197
+ "³": 114,
198
+ "´": 115,
199
+ "µ": 116,
200
+ "¶": 117,
201
+ "·": 118,
202
+ "¸": 119,
203
+ "¹": 120,
204
+ "º": 121,
205
+ "»": 122,
206
+ "¼": 123,
207
+ "½": 124,
208
+ "¾": 125,
209
+ "¿": 126,
210
+ "Â": 127,
211
+ "Ã": 128,
212
+ "Ä": 129,
213
+ "Å": 130,
214
+ "Æ": 131,
215
+ "Ç": 132,
216
+ "È": 133,
217
+ "É": 134,
218
+ "Ê": 135,
219
+ "Ë": 136,
220
+ "Ì": 137,
221
+ "Í": 138,
222
+ "Î": 139,
223
+ "Ï": 140,
224
+ "Ð": 141,
225
+ "Ñ": 142,
226
+ "Ö": 143,
227
+ "×": 144,
228
+ "Ø": 145,
229
+ "Ù": 146,
230
+ "Ü": 147,
231
+ "à": 148,
232
+ "á": 149,
233
+ "â": 150,
234
+ "ã": 151,
235
+ "ä": 152,
236
+ "å": 153,
237
+ "æ": 154,
238
+ "ç": 155,
239
+ "è": 156,
240
+ "é": 157,
241
+ "ë": 158,
242
+ "ì": 159,
243
+ "ï": 160,
244
+ "Ċ": 161,
245
+ "Ġ": 162,
246
+ "Ģ": 163,
247
+ "ģ": 164,
248
+ "Ĥ": 165,
249
+ "ĥ": 166,
250
+ "Ħ": 167,
251
+ "ħ": 168,
252
+ "Ĩ": 169,
253
+ "ĩ": 170,
254
+ "Ī": 171,
255
+ "ī": 172,
256
+ "Ĭ": 173,
257
+ "ĭ": 174,
258
+ "Į": 175,
259
+ "į": 176,
260
+ "İ": 177,
261
+ "ı": 178,
262
+ "IJ": 179,
263
+ "ij": 180,
264
+ "Ĵ": 181,
265
+ "ĵ": 182,
266
+ "Ķ": 183,
267
+ "ķ": 184,
268
+ "ĸ": 185,
269
+ "Ĺ": 186,
270
+ "ĺ": 187,
271
+ "Ļ": 188,
272
+ "ļ": 189,
273
+ "Ľ": 190,
274
+ "ľ": 191,
275
+ "Ŀ": 192,
276
+ "ŀ": 193,
277
+ "Ł": 194,
278
+ "ł": 195,
279
+ "Ń": 196,
280
+ "Ġt": 197,
281
+ "he": 198,
282
+ "Ġa": 199,
283
+ "in": 200,
284
+ "Ġthe": 201,
285
+ "er": 202,
286
+ "on": 203,
287
+ "Ġ,": 204,
288
+ "re": 205,
289
+ "Ġs": 206,
290
+ "ed": 207,
291
+ "Ġo": 208,
292
+ "Ġw": 209,
293
+ "nd": 210,
294
+ "at": 211,
295
+ "Ġ.": 212,
296
+ "or": 213,
297
+ "it": 214,
298
+ "Ġc": 215,
299
+ "en": 216,
300
+ "Ġf": 217,
301
+ "is": 218,
302
+ "es": 219,
303
+ "ar": 220,
304
+ "Ġof": 221,
305
+ "Ġb": 222,
306
+ "an": 223,
307
+ "Ġin": 224,
308
+ "al": 225,
309
+ "ing": 226,
310
+ "Ġp": 227,
311
+ "Ġand": 228,
312
+ "as": 229,
313
+ "Ġto": 230,
314
+ "ro": 231,
315
+ "ic": 232,
316
+ "Ġm": 233,
317
+ "Ġd": 234,
318
+ "Ġh": 235,
319
+ "ion": 236,
320
+ "le": 237,
321
+ "ou": 238,
322
+ "ĠT": 239,
323
+ "Ġre": 240,
324
+ "Ġ=": 241,
325
+ "Ġ\"": 242,
326
+ "ĠA": 243,
327
+ "ĠS": 244,
328
+ "ent": 245,
329
+ "il": 246,
330
+ "Ġth": 247,
331
+ "Ġ1": 248,
332
+ "st": 249,
333
+ "ĠC": 250,
334
+ "el": 251,
335
+ "om": 252,
336
+ "Ġl": 253,
337
+ "am": 254,
338
+ "ĠĊ": 255,
339
+ "Ġe": 256,
340
+ "Ġn": 257,
341
+ "Ġ@": 258,
342
+ "ad": 259,
343
+ "ac": 260,
344
+ "Ġwas": 261,
345
+ "ĠM": 262,
346
+ "ur": 263,
347
+ "ĠThe": 264,
348
+ "ec": 265,
349
+ "Ġon": 266,
350
+ "ly": 267,
351
+ "ĠB": 268,
352
+ "ĠI": 269,
353
+ "Ġg": 270,
354
+ "Ġ'": 271,
355
+ "et": 272,
356
+ "ol": 273,
357
+ "id": 274,
358
+ "iv": 275,
359
+ "im": 276,
360
+ "Ġfor": 277,
361
+ "ir": 278,
362
+ "-@": 279,
363
+ "Ġ@-@": 280,
364
+ "ig": 281,
365
+ "ot": 282,
366
+ "ter": 283,
367
+ "Ġas": 284,
368
+ "ĠH": 285,
369
+ "us": 286,
370
+ "ow": 287,
371
+ "Ġst": 288,
372
+ "ut": 289,
373
+ "ith": 290,
374
+ "ay": 291,
375
+ "Ġ2": 292,
376
+ "ĠP": 293,
377
+ "ation": 294,
378
+ "ver": 295,
379
+ "Ġbe": 296,
380
+ "Ġ.ĠĊ": 297,
381
+ "her": 298,
382
+ "Ġthat": 299,
383
+ "Ġwith": 300,
384
+ "Ġ's": 301,
385
+ "ĠR": 302,
386
+ "ce": 303,
387
+ "th": 304,
388
+ "ĠD": 305,
389
+ "Ġis": 306,
390
+ "un": 307,
391
+ "em": 308,
392
+ "ĠF": 309,
393
+ "Ġwh": 310,
394
+ "ul": 311,
395
+ "Ġby": 312,
396
+ "Ġal": 313,
397
+ "ch": 314,
398
+ "Ġ)": 315,
399
+ "Ġ(": 316,
400
+ "ĠW": 317,
401
+ "Ġcon": 318,
402
+ "ra": 319,
403
+ "ĠG": 320,
404
+ "os": 321,
405
+ "ĠL": 322,
406
+ "ĠN": 323,
407
+ "Ġat": 324,
408
+ "ers": 325,
409
+ "ct": 326,
410
+ "Ġit": 327,
411
+ "Ġ19": 328,
412
+ "rom": 329,
413
+ "and": 330,
414
+ "Ġan": 331,
415
+ "um": 332,
416
+ "est": 333,
417
+ "ĠJ": 334,
418
+ "ag": 335,
419
+ "Ġhe": 336,
420
+ "00": 337,
421
+ "ist": 338,
422
+ "ain": 339,
423
+ "od": 340,
424
+ "av": 341,
425
+ "ri": 342,
426
+ "ĠE": 343,
427
+ "ĠO": 344,
428
+ "Ġfrom": 345,
429
+ "Ġcom": 346,
430
+ "Ġhis": 347,
431
+ "op": 348,
432
+ "Ġpro": 349,
433
+ "res": 350,
434
+ "ies": 351,
435
+ "if": 352,
436
+ "Ġv": 353,
437
+ "ort": 354,
438
+ "ere": 355,
439
+ "ill": 356,
440
+ "ld": 357,
441
+ "Ġde": 358,
442
+ "pp": 359,
443
+ "Ġsu": 360,
444
+ "ore": 361,
445
+ "ĠIn": 362,
446
+ "Ġr": 363,
447
+ "Ġse": 364,
448
+ "Ġwere": 365,
449
+ "ew": 366,
450
+ "ong": 367,
451
+ "igh": 368,
452
+ "ard": 369,
453
+ "ate": 370,
454
+ "all": 371,
455
+ "art": 372,
456
+ "ak": 373,
457
+ "ich": 374,
458
+ "Ġch": 375,
459
+ "Ġor": 376,
460
+ "ab": 377,
461
+ "ant": 378,
462
+ "ud": 379,
463
+ "oc": 380,
464
+ "ber": 381,
465
+ "Ġex": 382,
466
+ "gh": 383,
467
+ "ity": 384,
468
+ "ated": 385,
469
+ "pt": 386,
470
+ "ess": 387,
471
+ "ear": 388,
472
+ "ĠK": 389,
473
+ "Ġpl": 390,
474
+ "ame": 391,
475
+ "qu": 392,
476
+ "ive": 393,
477
+ "rou": 394,
478
+ "Ġare": 395,
479
+ "Ġâ": 396,
480
+ "Ġsh": 397,
481
+ "Ġk": 398,
482
+ "ack": 399,
483
+ "ect": 400,
484
+ "ĠâĢ": 401,
485
+ "ĠU": 402,
486
+ "Ġhad": 403,
487
+ "se": 404,
488
+ "Ġwhich": 405,
489
+ "red": 406,
490
+ "ov": 407,
491
+ "ĠSt": 408,
492
+ "ast": 409,
493
+ "Ġsp": 410,
494
+ "ian": 411,
495
+ "Ġy": 412,
496
+ "ment": 413,
497
+ "Ġle": 414,
498
+ "Ġnot": 415,
499
+ "ge": 416,
500
+ "ord": 417,
501
+ "rit": 418,
502
+ "ip": 419,
503
+ "ine": 420,
504
+ "ell": 421,
505
+ "ally": 422,
506
+ "our": 423,
507
+ "ost": 424,
508
+ "ight": 425,
509
+ "ther": 426,
510
+ "ap": 427,
511
+ "Ġu": 428,
512
+ "ish": 429,
513
+ "ĠCh": 430,
514
+ "oun": 431,
515
+ "ia": 432,
516
+ "Ġ3": 433,
517
+ "ave": 434,
518
+ "ary": 435,
519
+ "ust": 436,
520
+ "og": 437,
521
+ "Ġ200": 438,
522
+ "Ġun": 439,
523
+ "ous": 440,
524
+ "irst": 441,
525
+ "ĠV": 442,
526
+ "cc": 443,
527
+ "Ġinc": 444,
528
+ "Ġ;": 445,
529
+ "Ġcomp": 446,
530
+ "ru": 447,
531
+ "ions": 448,
532
+ "Ġtheir": 449,
533
+ "Ġbut": 450,
534
+ "ide": 451,
535
+ "ure": 452,
536
+ "so": 453,
537
+ "Ġcont": 454,
538
+ "Ġint": 455,
539
+ "fter": 456,
540
+ "ical": 457,
541
+ "ial": 458,
542
+ "Ġar": 459,
543
+ "Ġfirst": 460,
544
+ "ould": 461,
545
+ "Ġits": 462,
546
+ "hed": 463,
547
+ "Ġ��Ģĵ": 464,
548
+ "Ġwhe": 465,
549
+ "wo": 466,
550
+ "out": 467,
551
+ "ub": 468,
552
+ "Ġ20": 469,
553
+ "ff": 470,
554
+ "Ġ:": 471,
555
+ "ue": 472,
556
+ "Ġher": 473,
557
+ "own": 474,
558
+ "ok": 475,
559
+ "Ġalso": 476,
560
+ "Ġcl": 477,
561
+ "per": 478,
562
+ "ign": 479,
563
+ "ater": 480,
564
+ "ran": 481,
565
+ "orm": 482,
566
+ "ie": 483,
567
+ "ome": 484,
568
+ "ork": 485,
569
+ "ass": 486,
570
+ "ire": 487,
571
+ "end": 488,
572
+ "Ġres": 489,
573
+ "Ġab": 490,
574
+ "Ġad": 491,
575
+ "Ġus": 492,
576
+ "ry": 493,
577
+ "Ġrec": 494,
578
+ "Ġhave": 495,
579
+ "age": 496,
580
+ "ĠHe": 497,
581
+ "Ġ4": 498,
582
+ "Ġro": 499,
583
+ "mer": 500,
584
+ "Ġone": 501,
585
+ "ond": 502,
586
+ "low": 503,
587
+ "Ġhas": 504,
588
+ "ĠTh": 505,
589
+ "du": 506,
590
+ "Ġ5": 507,
591
+ "Ġper": 508,
592
+ "Ġbeen": 509,
593
+ "ime": 510,
594
+ "Ġtwo": 511,
595
+ "ence": 512,
596
+ "land": 513,
597
+ "Ġ18": 514,
598
+ "ult": 515,
599
+ "ree": 516,
600
+ "ough": 517,
601
+ "ile": 518,
602
+ "Ġwho": 519,
603
+ "ĠAl": 520,
604
+ "Ġsc": 521,
605
+ "uring": 522,
606
+ "pl": 523,
607
+ "ory": 524,
608
+ "ition": 525,
609
+ "ric": 526,
610
+ "ations": 527,
611
+ "Ġdis": 528,
612
+ "Ġthis": 529,
613
+ "Ġbec": 530,
614
+ "Ġapp": 531,
615
+ "iz": 532,
616
+ "ĠIt": 533,
617
+ "are": 534,
618
+ "ach": 535,
619
+ "lud": 536,
620
+ "ade": 537,
621
+ "Ġplay": 538,
622
+ "Ġj": 539,
623
+ "Ġman": 540,
624
+ "act": 541,
625
+ "ely": 542,
626
+ "Ġpart": 543,
627
+ "Ġdes": 544,
628
+ "Ġag": 545,
629
+ "Ġthey": 546,
630
+ "Ġyear": 547,
631
+ "ount": 548,
632
+ "Ġ201": 549,
633
+ "Ġover": 550,
634
+ "Ġother": 551,
635
+ "ound": 552,
636
+ "Ġafter": 553,
637
+ "ib": 554,
638
+ "over": 555,
639
+ "Ġser": 556,
640
+ "Ġen": 557,
641
+ "Ġoff": 558,
642
+ "Ġim": 559,
643
+ "ction": 560,
644
+ "ĠY": 561,
645
+ "ke": 562,
646
+ "ite": 563,
647
+ "te": 564,
648
+ "urn": 565,
649
+ "Ġinclud": 566,
650
+ "ress": 567,
651
+ "ance": 568,
652
+ "ang": 569,
653
+ "Ġatt": 570,
654
+ "ice": 571,
655
+ "ace": 572,
656
+ "ark": 573,
657
+ "Ġout": 574,
658
+ "wn": 575,
659
+ "ph": 576,
660
+ "ember": 577,
661
+ "Ġ)Ġ,": 578,
662
+ "Ġpre": 579,
663
+ "Ġup": 580,
664
+ "ens": 581,
665
+ "man": 582,
666
+ "Ġev": 583,
667
+ "Ġtime": 584,
668
+ "nder": 585,
669
+ "rough": 586,
670
+ "ced": 587,
671
+ "Ġfin": 588,
672
+ "Ġinto": 589,
673
+ "one": 590,
674
+ "port": 591,
675
+ "round": 592,
676
+ "we": 593,
677
+ "ren": 594,
678
+ "les": 595,
679
+ "int": 596,
680
+ "ĠOn": 597,
681
+ "vel": 598,
682
+ "Ġcomm": 599,
683
+ "Ġshe": 600,
684
+ "ason": 601,
685
+ "amp": 602,
686
+ "Ġte": 603,
687
+ "Ġwould": 604,
688
+ "ward": 605,
689
+ "Ġmore": 606,
690
+ "Ġ6": 607,
691
+ "ied": 608,
692
+ "ose": 609,
693
+ "rib": 610,
694
+ "ĠUn": 611,
695
+ "Ġall": 612,
696
+ "ings": 613,
697
+ "tern": 614,
698
+ "ces": 615,
699
+ "able": 616,
700
+ "Ġwe": 617,
701
+ "ited": 618,
702
+ "ever": 619,
703
+ "ents": 620,
704
+ "Ġhim": 621,
705
+ "ased": 622,
706
+ "ors": 623,
707
+ "oy": 624,
708
+ "ood": 625,
709
+ "Ġcent": 626,
710
+ "ix": 627,
711
+ "ase": 628,
712
+ "ild": 629,
713
+ "ĠAn": 630,
714
+ "Ġ7": 631,
715
+ "Ġwork": 632,
716
+ "ates": 633,
717
+ "ious": 634,
718
+ "ath": 635,
719
+ "Ġpo": 636,
720
+ "rop": 637,
721
+ "old": 638,
722
+ "als": 639,
723
+ "iss": 640,
724
+ "ey": 641,
725
+ "ict": 642,
726
+ "Ġfe": 643,
727
+ "Ġthem": 644,
728
+ "gan": 645,
729
+ "Ġsec": 646,
730
+ "Ġbet": 647,
731
+ "Ġwhen": 648,
732
+ "Ġsong": 649,
733
+ "Ġrem": 650,
734
+ "ep": 651,
735
+ "form": 652,
736
+ "ail": 653,
737
+ "fer": 654,
738
+ "Ġear": 655,
739
+ "ubl": 656,
740
+ "aw": 657,
741
+ "Ġkn": 658,
742
+ "ake": 659,
743
+ "aus": 660,
744
+ "Ġmost": 661,
745
+ "Ġcons": 662,
746
+ "Ġduring": 663,
747
+ "ĠAs": 664,
748
+ "orth": 665,
749
+ "Ġnew": 666,
750
+ "ered": 667,
751
+ "ilm": 668,
752
+ "ved": 669,
753
+ "att": 670,
754
+ "Ġonly": 671,
755
+ "Ġ9": 672,
756
+ "Ġdec": 673,
757
+ "Ġ8": 674,
758
+ "ick": 675,
759
+ "Ġgame": 676,
760
+ "ons": 677,
761
+ "ug": 678,
762
+ "Ġtr": 679,
763
+ "ft": 680,
764
+ "oth": 681,
765
+ "ook": 682,
766
+ "ĠMar": 683,
767
+ "reat": 684,
768
+ "way": 685,
769
+ "Ġcan": 686,
770
+ "ollow": 687,
771
+ "outh": 688,
772
+ "ween": 689,
773
+ "ĠEn": 690,
774
+ "Ġ199": 691,
775
+ "ters": 692,
776
+ "Ġrel": 693,
777
+ "ind": 694,
778
+ "Ġabout": 695,
779
+ "Ġseason": 696,
780
+ "Ġagain": 697,
781
+ "ral": 698,
782
+ "Ġthree": 699,
783
+ "ational": 700,
784
+ "Ġunder": 701,
785
+ "ular": 702,
786
+ "Ġme": 703,
787
+ "Ġthan": 704,
788
+ "ĠCom": 705,
789
+ "ĠAr": 706,
790
+ "hip": 707,
791
+ "ob": 708,
792
+ "Ġne": 709,
793
+ "Ġbetween": 710,
794
+ "Ġfl": 711,
795
+ "hn": 712,
796
+ "ve": 713,
797
+ "Ġchar": 714,
798
+ "Ġcol": 715,
799
+ "Ġrecord": 716,
800
+ "iew": 717,
801
+ "ron": 718,
802
+ "fore": 719,
803
+ "Ġthrough": 720,
804
+ "ision": 721,
805
+ "orn": 722,
806
+ "Ġ00": 723,
807
+ "ock": 724,
808
+ "Ġver": 725,
809
+ "Ġlater": 726,
810
+ "Ġnum": 727,
811
+ "Ġend": 728,
812
+ "olog": 729,
813
+ "ames": 730,
814
+ "Ġpos": 731,
815
+ "Ġwrit": 732,
816
+ "Ġprodu": 733,
817
+ "Ġwhile": 734,
818
+ "Ġact": 735,
819
+ "Ġrele": 736,
820
+ "Ġfilm": 737,
821
+ "Ġ)Ġ.": 738,
822
+ "ished": 739,
823
+ "Ġpr": 740,
824
+ "ans": 741,
825
+ "Ġreg": 742,
826
+ "Ġform": 743,
827
+ "Ġass": 744,
828
+ "ĠSe": 745,
829
+ "ury": 746,
830
+ "ted": 747,
831
+ "ts": 748,
832
+ "Ġmade": 749,
833
+ "Ġsub": 750,
834
+ "Ġpe": 751,
835
+ "Ġso": 752,
836
+ "orld": 753,
837
+ "Ġret": 754,
838
+ "ĠNew": 755,
839
+ "Ġspec": 756,
840
+ "Ġacc": 757,
841
+ "Ġqu": 758,
842
+ "Ġwhere": 759,
843
+ "ener": 760,
844
+ "Ġmov": 761,
845
+ "hes": 762,
846
+ "meric": 763,
847
+ "ating": 764,
848
+ "Ġinter": 765,
849
+ "ĠLe": 766,
850
+ "ĠAmeric": 767,
851
+ "Ġra": 768,
852
+ "Ġsome": 769,
853
+ "Ġco": 770,
854
+ "Ġlar": 771,
855
+ "Ġbu": 772,
856
+ "Ġdef": 773,
857
+ "bum": 774,
858
+ "Ġac": 775,
859
+ "Ġmus": 776,
860
+ "Ġfollow": 777,
861
+ "ĠAt": 778,
862
+ "ins": 779,
863
+ "ived": 780,
864
+ "ific": 781,
865
+ "ual": 782,
866
+ "Ġam": 783,
867
+ "Ġsuch": 784,
868
+ "Ġsecond": 785,
869
+ "ike": 786,
870
+ "Ġfour": 787,
871
+ "Ġind": 788,
872
+ "ann": 789,
873
+ "hen": 790,
874
+ "Ġused": 791,
875
+ "ĠRe": 792,
876
+ "ics": 793,
877
+ "lect": 794,
878
+ "Ġday": 795,
879
+ "iel": 796,
880
+ "ily": 797,
881
+ "ĠThis": 798,
882
+ "Ġ0": 799,
883
+ "Ġpubl": 800,
884
+ "Ġcall": 801,
885
+ "ĠJo": 802,
886
+ "ll": 803,
887
+ "Ġalbum": 804,
888
+ "Ġ000": 805,
889
+ "rans": 806,
890
+ "Ġdo": 807,
891
+ "any": 808,
892
+ "Ġbefore": 809,
893
+ "ros": 810,
894
+ "ĠSh": 811,
895
+ "Ġsy": 812,
896
+ "aid": 813,
897
+ "ĠEng": 814,
898
+ "Ġbeing": 815,
899
+ "Ġ10": 816,
900
+ "uc": 817,
901
+ "Ġep": 818,
902
+ "Ġsupp": 819,
903
+ "Ġthere": 820,
904
+ "Ġyears": 821,
905
+ "ars": 822,
906
+ "owever": 823,
907
+ "Ġent": 824,
908
+ "ife": 825,
909
+ "Ġhigh": 826,
910
+ "Ġfound": 827,
911
+ "ird": 828,
912
+ "Ġno": 829,
913
+ "Ġset": 830,
914
+ "ines": 831,
915
+ "iver": 832,
916
+ "io": 833,
917
+ "other": 834,
918
+ "ject": 835,
919
+ "Ġsur": 836,
920
+ "aj": 837,
921
+ "ten": 838,
922
+ "Ġtra": 839,
923
+ "Ġ12": 840,
924
+ "ised": 841,
925
+ "ities": 842,
926
+ "velop": 843,
927
+ "Ġbl": 844,
928
+ "ale": 845,
929
+ "Ġseries": 846,
930
+ "Ġloc": 847,
931
+ "Ġnumber": 848,
932
+ "Ġpres": 849,
933
+ "ane": 850,
934
+ "ause": 851,
935
+ "ode": 852,
936
+ "ek": 853,
937
+ "ton": 854,
938
+ "ĠSc": 855,
939
+ "ier": 856,
940
+ "ise": 857,
941
+ "Ġsever": 858,
942
+ "ince": 859,
943
+ "Ġboth": 860,
944
+ "ank": 861,
945
+ "row": 862,
946
+ "irect": 863,
947
+ "son": 864,
948
+ "Ġthen": 865,
949
+ "ĠBrit": 866,
950
+ "iet": 867,
951
+ "Ġ16": 868,
952
+ "Ġepis": 869,
953
+ "Ġincluding": 870,
954
+ "its": 871,
955
+ "igin": 872,
956
+ "pr": 873,
957
+ "Ġ/": 874,
958
+ "Ġagainst": 875,
959
+ "Ġwell": 876,
960
+ "Ġbecame": 877,
961
+ "Ġexp": 878,
962
+ "Ġknown": 879,
963
+ "Ġtrans": 880,
964
+ "Ġcharac": 881,
965
+ "ĠâĢĶ": 882,
966
+ "ram": 883,
967
+ "Ġback": 884,
968
+ "Ġadd": 885,
969
+ "Ġpop": 886,
970
+ "Ġgo": 887,
971
+ "urch": 888,
972
+ "Ġdesc": 889,
973
+ "Ġsing": 890,
974
+ "ield": 891,
975
+ "Ġperform": 892,
976
+ "ained": 893,
977
+ "Ġrece": 894,
978
+ "ident": 895,
979
+ "Ġem": 896,
980
+ "ert": 897,
981
+ "ures": 898,
982
+ "Ġinv": 899,
983
+ "Ġdep": 900,
984
+ "Ġ198": 901,
985
+ "air": 902,
986
+ "ern": 903,
987
+ "ather": 904,
988
+ "ful": 905,
989
+ "ĠZ": 906,
990
+ "Ġmon": 907,
991
+ "Ġmany": 908,
992
+ "Ġmain": 909,
993
+ "Ġstud": 910,
994
+ "Ġlong": 911,
995
+ "inn": 912,
996
+ "though": 913,
997
+ "up": 914,
998
+ "ool": 915,
999
+ "ĠUnited": 916,
1000
+ "led": 917,
1001
+ "ement": 918,
1002
+ "Ġ15": 919,
1003
+ "ower": 920,
1004
+ "ĠJohn": 921,
1005
+ "Ġop": 922,
1006
+ "Ġ11": 923,
1007
+ "ined": 924,
1008
+ "Ġmet": 925,
1009
+ "ober": 926,
1010
+ "ley": 927,
1011
+ "Ġ17": 928,
1012
+ "Ġcentury": 929,
1013
+ "Ġteam": 930,
1014
+ "Ġest": 931,
1015
+ "ĠAfter": 932,
1016
+ "yl": 933,
1017
+ "Ġmin": 934,
1018
+ "uch": 935,
1019
+ "ute": 936,
1020
+ "Ġdevelop": 937,
1021
+ "ĠShe": 938,
1022
+ "0s": 939,
1023
+ "iam": 940,
1024
+ "Ġshow": 941,
1025
+ "elf": 942,
1026
+ "Ġrep": 943,
1027
+ "Ġconc": 944,
1028
+ "ative": 945,
1029
+ "Ġcre": 946,
1030
+ "overn": 947,
1031
+ "ared": 948,
1032
+ "Ġ194": 949,
1033
+ "Ġorigin": 950,
1034
+ "Ġsm": 951,
1035
+ "ivers": 952,
1036
+ "az": 953,
1037
+ "Ġlead": 954,
1038
+ "Ġseveral": 955,
1039
+ "ah": 956,
1040
+ "Ġob": 957,
1041
+ "Ġrev": 958,
1042
+ "Ġmill": 959,
1043
+ "erm": 960,
1044
+ "ually": 961,
1045
+ "oot": 962,
1046
+ "Ġbegan": 963,
1047
+ "Ġ196": 964,
1048
+ "ired": 965,
1049
+ "Ġdif": 966,
1050
+ "Ġcontin": 967,
1051
+ "Ġsign": 968,
1052
+ "ik": 969,
1053
+ "ĠInd": 970,
1054
+ "ments": 971,
1055
+ "ized": 972,
1056
+ "Ġ197": 973,
1057
+ "Ġdirect": 974,
1058
+ "au": 975,
1059
+ "Ġext": 976,
1060
+ "ross": 977,
1061
+ "emb": 978,
1062
+ "der": 979,
1063
+ "Ġpol": 980,
1064
+ "Ġmay": 981,
1065
+ "apt": 982,
1066
+ "els": 983,
1067
+ "ĠWh": 984,
1068
+ "Ġcomple": 985,
1069
+ "Ġart": 986,
1070
+ "ĠBr": 987,
1071
+ "ĠIs": 988,
1072
+ "une": 989,
1073
+ "til": 990,
1074
+ "Ġcrit": 991,
1075
+ "Ġhist": 992,
1076
+ "Ġearly": 993,
1077
+ "Ġcould": 994,
1078
+ "ĠCon": 995,
1079
+ "Ġdid": 996,
1080
+ "Ġbel": 997,
1081
+ "Ġcalled": 998,
1082
+ "ued": 999,
1083
+ "Ġnear": 1000,
1084
+ "Ġepisode": 1001,
1085
+ "yp": 1002,
1086
+ "Ġdescrib": 1003,
1087
+ "imes": 1004,
1088
+ "Ġbro": 1005,
1089
+ "roup": 1006,
1090
+ "ople": 1007,
1091
+ "Ġdown": 1008,
1092
+ "Ġrun": 1009,
1093
+ "aking": 1010,
1094
+ "Ġdisc": 1011,
1095
+ "Ġalong": 1012,
1096
+ "ccess": 1013,
1097
+ "ĠMay": 1014,
1098
+ "Ġfeat": 1015,
1099
+ "Ġinst": 1016,
1100
+ "ĠAmerican": 1017,
1101
+ "Ġsaid": 1018,
1102
+ "Ġdist": 1019,
1103
+ "Ġinf": 1020,
1104
+ "Ġimp": 1021,
1105
+ "ink": 1022,
1106
+ "Ġins": 1023
1107
+ },
1108
+ "merges": [
1109
+ "Ġ t",
1110
+ "h e",
1111
+ "Ġ a",
1112
+ "i n",
1113
+ "Ġt he",
1114
+ "e r",
1115
+ "o n",
1116
+ "Ġ ,",
1117
+ "r e",
1118
+ "Ġ s",
1119
+ "e d",
1120
+ "Ġ o",
1121
+ "Ġ w",
1122
+ "n d",
1123
+ "a t",
1124
+ "Ġ .",
1125
+ "o r",
1126
+ "i t",
1127
+ "Ġ c",
1128
+ "e n",
1129
+ "Ġ f",
1130
+ "i s",
1131
+ "e s",
1132
+ "a r",
1133
+ "Ġo f",
1134
+ "Ġ b",
1135
+ "a n",
1136
+ "Ġ in",
1137
+ "a l",
1138
+ "in g",
1139
+ "Ġ p",
1140
+ "Ġa nd",
1141
+ "a s",
1142
+ "Ġt o",
1143
+ "r o",
1144
+ "i c",
1145
+ "Ġ m",
1146
+ "Ġ d",
1147
+ "Ġ h",
1148
+ "i on",
1149
+ "l e",
1150
+ "o u",
1151
+ "Ġ T",
1152
+ "Ġ re",
1153
+ "Ġ =",
1154
+ "Ġ \"",
1155
+ "Ġ A",
1156
+ "Ġ S",
1157
+ "en t",
1158
+ "i l",
1159
+ "Ġt h",
1160
+ "Ġ 1",
1161
+ "s t",
1162
+ "Ġ C",
1163
+ "e l",
1164
+ "o m",
1165
+ "Ġ l",
1166
+ "a m",
1167
+ "Ġ Ċ",
1168
+ "Ġ e",
1169
+ "Ġ n",
1170
+ "Ġ @",
1171
+ "a d",
1172
+ "a c",
1173
+ "Ġw as",
1174
+ "Ġ M",
1175
+ "u r",
1176
+ "ĠT he",
1177
+ "e c",
1178
+ "Ġ on",
1179
+ "l y",
1180
+ "Ġ B",
1181
+ "Ġ I",
1182
+ "Ġ g",
1183
+ "Ġ '",
1184
+ "e t",
1185
+ "o l",
1186
+ "i d",
1187
+ "i v",
1188
+ "i m",
1189
+ "Ġf or",
1190
+ "i r",
1191
+ "- @",
1192
+ "Ġ@ -@",
1193
+ "i g",
1194
+ "o t",
1195
+ "t er",
1196
+ "Ġa s",
1197
+ "Ġ H",
1198
+ "u s",
1199
+ "o w",
1200
+ "Ġs t",
1201
+ "u t",
1202
+ "it h",
1203
+ "a y",
1204
+ "Ġ 2",
1205
+ "Ġ P",
1206
+ "at ion",
1207
+ "v er",
1208
+ "Ġb e",
1209
+ "Ġ. ĠĊ",
1210
+ "he r",
1211
+ "Ġth at",
1212
+ "Ġw ith",
1213
+ "Ġ' s",
1214
+ "Ġ R",
1215
+ "c e",
1216
+ "t h",
1217
+ "Ġ D",
1218
+ "Ġ is",
1219
+ "u n",
1220
+ "e m",
1221
+ "Ġ F",
1222
+ "Ġw h",
1223
+ "u l",
1224
+ "Ġb y",
1225
+ "Ġa l",
1226
+ "c h",
1227
+ "Ġ )",
1228
+ "Ġ (",
1229
+ "Ġ W",
1230
+ "Ġc on",
1231
+ "r a",
1232
+ "Ġ G",
1233
+ "o s",
1234
+ "Ġ L",
1235
+ "Ġ N",
1236
+ "Ġa t",
1237
+ "er s",
1238
+ "c t",
1239
+ "Ġ it",
1240
+ "Ġ1 9",
1241
+ "ro m",
1242
+ "a nd",
1243
+ "Ġa n",
1244
+ "u m",
1245
+ "es t",
1246
+ "Ġ J",
1247
+ "a g",
1248
+ "Ġ he",
1249
+ "0 0",
1250
+ "is t",
1251
+ "a in",
1252
+ "o d",
1253
+ "a v",
1254
+ "r i",
1255
+ "Ġ E",
1256
+ "Ġ O",
1257
+ "Ġf rom",
1258
+ "Ġc om",
1259
+ "Ġh is",
1260
+ "o p",
1261
+ "Ġp ro",
1262
+ "re s",
1263
+ "i es",
1264
+ "i f",
1265
+ "Ġ v",
1266
+ "or t",
1267
+ "er e",
1268
+ "il l",
1269
+ "l d",
1270
+ "Ġd e",
1271
+ "p p",
1272
+ "Ġs u",
1273
+ "o re",
1274
+ "ĠI n",
1275
+ "Ġ r",
1276
+ "Ġs e",
1277
+ "Ġw ere",
1278
+ "e w",
1279
+ "on g",
1280
+ "ig h",
1281
+ "ar d",
1282
+ "at e",
1283
+ "al l",
1284
+ "ar t",
1285
+ "a k",
1286
+ "ic h",
1287
+ "Ġc h",
1288
+ "Ġo r",
1289
+ "a b",
1290
+ "an t",
1291
+ "u d",
1292
+ "o c",
1293
+ "b er",
1294
+ "Ġe x",
1295
+ "g h",
1296
+ "it y",
1297
+ "at ed",
1298
+ "p t",
1299
+ "es s",
1300
+ "e ar",
1301
+ "Ġ K",
1302
+ "Ġp l",
1303
+ "am e",
1304
+ "q u",
1305
+ "iv e",
1306
+ "ro u",
1307
+ "Ġa re",
1308
+ "Ġ â",
1309
+ "Ġs h",
1310
+ "Ġ k",
1311
+ "ac k",
1312
+ "ec t",
1313
+ "Ġâ Ģ",
1314
+ "Ġ U",
1315
+ "Ġh ad",
1316
+ "s e",
1317
+ "Ġwh ich",
1318
+ "re d",
1319
+ "o v",
1320
+ "ĠS t",
1321
+ "as t",
1322
+ "Ġs p",
1323
+ "i an",
1324
+ "Ġ y",
1325
+ "m ent",
1326
+ "Ġ le",
1327
+ "Ġn ot",
1328
+ "g e",
1329
+ "or d",
1330
+ "r it",
1331
+ "i p",
1332
+ "in e",
1333
+ "el l",
1334
+ "al ly",
1335
+ "ou r",
1336
+ "o st",
1337
+ "igh t",
1338
+ "t her",
1339
+ "a p",
1340
+ "Ġ u",
1341
+ "is h",
1342
+ "ĠC h",
1343
+ "ou n",
1344
+ "i a",
1345
+ "Ġ 3",
1346
+ "av e",
1347
+ "ar y",
1348
+ "u st",
1349
+ "o g",
1350
+ "Ġ2 00",
1351
+ "Ġ un",
1352
+ "ou s",
1353
+ "ir st",
1354
+ "Ġ V",
1355
+ "c c",
1356
+ "Ġin c",
1357
+ "Ġ ;",
1358
+ "Ġcom p",
1359
+ "r u",
1360
+ "ion s",
1361
+ "Ġthe ir",
1362
+ "Ġb ut",
1363
+ "id e",
1364
+ "u re",
1365
+ "s o",
1366
+ "Ġcon t",
1367
+ "Ġin t",
1368
+ "f ter",
1369
+ "ic al",
1370
+ "i al",
1371
+ "Ġa r",
1372
+ "Ġf irst",
1373
+ "ou ld",
1374
+ "Ġit s",
1375
+ "he d",
1376
+ "ĠâĢ ĵ",
1377
+ "Ġw he",
1378
+ "w o",
1379
+ "ou t",
1380
+ "u b",
1381
+ "Ġ2 0",
1382
+ "f f",
1383
+ "Ġ :",
1384
+ "u e",
1385
+ "Ġ her",
1386
+ "ow n",
1387
+ "o k",
1388
+ "Ġal so",
1389
+ "Ġc l",
1390
+ "p er",
1391
+ "ig n",
1392
+ "at er",
1393
+ "r an",
1394
+ "or m",
1395
+ "i e",
1396
+ "om e",
1397
+ "or k",
1398
+ "as s",
1399
+ "i re",
1400
+ "e nd",
1401
+ "Ġre s",
1402
+ "Ġa b",
1403
+ "Ġa d",
1404
+ "Ġ us",
1405
+ "r y",
1406
+ "Ġre c",
1407
+ "Ġh ave",
1408
+ "ag e",
1409
+ "ĠH e",
1410
+ "Ġ 4",
1411
+ "Ġ ro",
1412
+ "m er",
1413
+ "Ġon e",
1414
+ "on d",
1415
+ "l ow",
1416
+ "Ġh as",
1417
+ "ĠT h",
1418
+ "d u",
1419
+ "Ġ 5",
1420
+ "Ġp er",
1421
+ "Ġbe en",
1422
+ "im e",
1423
+ "Ġt wo",
1424
+ "en ce",
1425
+ "l and",
1426
+ "Ġ1 8",
1427
+ "ul t",
1428
+ "re e",
1429
+ "ou gh",
1430
+ "i le",
1431
+ "Ġwh o",
1432
+ "ĠA l",
1433
+ "Ġs c",
1434
+ "ur ing",
1435
+ "p l",
1436
+ "or y",
1437
+ "it ion",
1438
+ "r ic",
1439
+ "ation s",
1440
+ "Ġd is",
1441
+ "Ġth is",
1442
+ "Ġb ec",
1443
+ "Ġa pp",
1444
+ "i z",
1445
+ "ĠI t",
1446
+ "a re",
1447
+ "ac h",
1448
+ "l ud",
1449
+ "ad e",
1450
+ "Ġpl ay",
1451
+ "Ġ j",
1452
+ "Ġm an",
1453
+ "ac t",
1454
+ "el y",
1455
+ "Ġp art",
1456
+ "Ġd es",
1457
+ "Ġa g",
1458
+ "Ġthe y",
1459
+ "Ġy ear",
1460
+ "oun t",
1461
+ "Ġ20 1",
1462
+ "Ġo ver",
1463
+ "Ġo ther",
1464
+ "ou nd",
1465
+ "Ġa fter",
1466
+ "i b",
1467
+ "o ver",
1468
+ "Ġs er",
1469
+ "Ġ en",
1470
+ "Ġof f",
1471
+ "Ġ im",
1472
+ "ct ion",
1473
+ "Ġ Y",
1474
+ "k e",
1475
+ "it e",
1476
+ "t e",
1477
+ "ur n",
1478
+ "Ġinc lud",
1479
+ "res s",
1480
+ "an ce",
1481
+ "an g",
1482
+ "Ġat t",
1483
+ "ic e",
1484
+ "ac e",
1485
+ "ar k",
1486
+ "Ġo ut",
1487
+ "w n",
1488
+ "p h",
1489
+ "em ber",
1490
+ "Ġ) Ġ,",
1491
+ "Ġp re",
1492
+ "Ġu p",
1493
+ "en s",
1494
+ "m an",
1495
+ "Ġe v",
1496
+ "Ġt ime",
1497
+ "nd er",
1498
+ "rou gh",
1499
+ "c ed",
1500
+ "Ġf in",
1501
+ "Ġint o",
1502
+ "on e",
1503
+ "p ort",
1504
+ "rou nd",
1505
+ "w e",
1506
+ "re n",
1507
+ "l es",
1508
+ "in t",
1509
+ "ĠO n",
1510
+ "v el",
1511
+ "Ġcom m",
1512
+ "Ġs he",
1513
+ "as on",
1514
+ "am p",
1515
+ "Ġt e",
1516
+ "Ġw ould",
1517
+ "w ard",
1518
+ "Ġm ore",
1519
+ "Ġ 6",
1520
+ "i ed",
1521
+ "os e",
1522
+ "ri b",
1523
+ "ĠU n",
1524
+ "Ġal l",
1525
+ "ing s",
1526
+ "ter n",
1527
+ "c es",
1528
+ "ab le",
1529
+ "Ġw e",
1530
+ "it ed",
1531
+ "e ver",
1532
+ "ent s",
1533
+ "Ġh im",
1534
+ "as ed",
1535
+ "or s",
1536
+ "o y",
1537
+ "o od",
1538
+ "Ġc ent",
1539
+ "i x",
1540
+ "as e",
1541
+ "il d",
1542
+ "ĠA n",
1543
+ "Ġ 7",
1544
+ "Ġw ork",
1545
+ "at es",
1546
+ "i ous",
1547
+ "at h",
1548
+ "Ġp o",
1549
+ "ro p",
1550
+ "ol d",
1551
+ "al s",
1552
+ "is s",
1553
+ "e y",
1554
+ "ic t",
1555
+ "Ġf e",
1556
+ "Ġthe m",
1557
+ "g an",
1558
+ "Ġs ec",
1559
+ "Ġb et",
1560
+ "Ġwhe n",
1561
+ "Ġs ong",
1562
+ "Ġre m",
1563
+ "e p",
1564
+ "f orm",
1565
+ "a il",
1566
+ "f er",
1567
+ "Ġe ar",
1568
+ "ub l",
1569
+ "a w",
1570
+ "Ġk n",
1571
+ "ak e",
1572
+ "a us",
1573
+ "Ġm ost",
1574
+ "Ġcon s",
1575
+ "Ġd uring",
1576
+ "ĠA s",
1577
+ "or th",
1578
+ "Ġn ew",
1579
+ "er ed",
1580
+ "il m",
1581
+ "v ed",
1582
+ "at t",
1583
+ "Ġon ly",
1584
+ "Ġ 9",
1585
+ "Ġd ec",
1586
+ "Ġ 8",
1587
+ "ic k",
1588
+ "Ġg ame",
1589
+ "on s",
1590
+ "u g",
1591
+ "Ġt r",
1592
+ "f t",
1593
+ "ot h",
1594
+ "o ok",
1595
+ "ĠM ar",
1596
+ "re at",
1597
+ "w ay",
1598
+ "Ġc an",
1599
+ "ol low",
1600
+ "ou th",
1601
+ "we en",
1602
+ "ĠE n",
1603
+ "Ġ19 9",
1604
+ "ter s",
1605
+ "Ġre l",
1606
+ "in d",
1607
+ "Ġab out",
1608
+ "Ġse ason",
1609
+ "Ġag ain",
1610
+ "r al",
1611
+ "Ġth ree",
1612
+ "ation al",
1613
+ "Ġu nder",
1614
+ "ul ar",
1615
+ "Ġm e",
1616
+ "Ġth an",
1617
+ "ĠC om",
1618
+ "ĠA r",
1619
+ "h ip",
1620
+ "o b",
1621
+ "Ġn e",
1622
+ "Ġbet ween",
1623
+ "Ġf l",
1624
+ "h n",
1625
+ "v e",
1626
+ "Ġch ar",
1627
+ "Ġc ol",
1628
+ "Ġrec ord",
1629
+ "i ew",
1630
+ "r on",
1631
+ "f ore",
1632
+ "Ġth rough",
1633
+ "is ion",
1634
+ "or n",
1635
+ "Ġ 00",
1636
+ "oc k",
1637
+ "Ġ ver",
1638
+ "Ġl ater",
1639
+ "Ġn um",
1640
+ "Ġe nd",
1641
+ "ol og",
1642
+ "am es",
1643
+ "Ġp os",
1644
+ "Ġw rit",
1645
+ "Ġpro du",
1646
+ "Ġwh ile",
1647
+ "Ġa ct",
1648
+ "Ġre le",
1649
+ "Ġf ilm",
1650
+ "Ġ) Ġ.",
1651
+ "is hed",
1652
+ "Ġp r",
1653
+ "an s",
1654
+ "Ġre g",
1655
+ "Ġfor m",
1656
+ "Ġas s",
1657
+ "ĠS e",
1658
+ "ur y",
1659
+ "t ed",
1660
+ "t s",
1661
+ "Ġm ade",
1662
+ "Ġsu b",
1663
+ "Ġp e",
1664
+ "Ġs o",
1665
+ "or ld",
1666
+ "Ġre t",
1667
+ "ĠN ew",
1668
+ "Ġsp ec",
1669
+ "Ġa cc",
1670
+ "Ġ qu",
1671
+ "Ġwhe re",
1672
+ "en er",
1673
+ "Ġm ov",
1674
+ "he s",
1675
+ "mer ic",
1676
+ "at ing",
1677
+ "Ġin ter",
1678
+ "ĠL e",
1679
+ "ĠA meric",
1680
+ "Ġ ra",
1681
+ "Ġs ome",
1682
+ "Ġc o",
1683
+ "Ġl ar",
1684
+ "Ġb u",
1685
+ "Ġde f",
1686
+ "b um",
1687
+ "Ġa c",
1688
+ "Ġm us",
1689
+ "Ġf ollow",
1690
+ "ĠA t",
1691
+ "in s",
1692
+ "iv ed",
1693
+ "if ic",
1694
+ "u al",
1695
+ "Ġa m",
1696
+ "Ġsu ch",
1697
+ "Ġsec ond",
1698
+ "i ke",
1699
+ "Ġf our",
1700
+ "Ġin d",
1701
+ "an n",
1702
+ "he n",
1703
+ "Ġus ed",
1704
+ "ĠR e",
1705
+ "ic s",
1706
+ "le ct",
1707
+ "Ġd ay",
1708
+ "i el",
1709
+ "il y",
1710
+ "ĠTh is",
1711
+ "Ġ 0",
1712
+ "Ġp ubl",
1713
+ "Ġc all",
1714
+ "ĠJ o",
1715
+ "l l",
1716
+ "Ġal bum",
1717
+ "Ġ00 0",
1718
+ "ran s",
1719
+ "Ġd o",
1720
+ "an y",
1721
+ "Ġbe fore",
1722
+ "ro s",
1723
+ "ĠS h",
1724
+ "Ġs y",
1725
+ "a id",
1726
+ "ĠEn g",
1727
+ "Ġbe ing",
1728
+ "Ġ1 0",
1729
+ "u c",
1730
+ "Ġe p",
1731
+ "Ġsu pp",
1732
+ "Ġthe re",
1733
+ "Ġyear s",
1734
+ "ar s",
1735
+ "ow ever",
1736
+ "Ġ ent",
1737
+ "if e",
1738
+ "Ġh igh",
1739
+ "Ġf ound",
1740
+ "ir d",
1741
+ "Ġn o",
1742
+ "Ġs et",
1743
+ "in es",
1744
+ "iv er",
1745
+ "i o",
1746
+ "ot her",
1747
+ "j ect",
1748
+ "Ġs ur",
1749
+ "a j",
1750
+ "t en",
1751
+ "Ġt ra",
1752
+ "Ġ1 2",
1753
+ "is ed",
1754
+ "it ies",
1755
+ "vel op",
1756
+ "Ġb l",
1757
+ "al e",
1758
+ "Ġser ies",
1759
+ "Ġl oc",
1760
+ "Ġnum ber",
1761
+ "Ġp res",
1762
+ "an e",
1763
+ "aus e",
1764
+ "od e",
1765
+ "e k",
1766
+ "t on",
1767
+ "ĠS c",
1768
+ "i er",
1769
+ "is e",
1770
+ "Ġse ver",
1771
+ "in ce",
1772
+ "Ġb oth",
1773
+ "an k",
1774
+ "ro w",
1775
+ "ire ct",
1776
+ "s on",
1777
+ "Ġthe n",
1778
+ "ĠB rit",
1779
+ "i et",
1780
+ "Ġ1 6",
1781
+ "Ġep is",
1782
+ "Ġinclud ing",
1783
+ "it s",
1784
+ "ig in",
1785
+ "p r",
1786
+ "Ġ /",
1787
+ "Ġagain st",
1788
+ "Ġw ell",
1789
+ "Ġbec ame",
1790
+ "Ġex p",
1791
+ "Ġkn own",
1792
+ "Ġt rans",
1793
+ "Ġchar ac",
1794
+ "ĠâĢ Ķ",
1795
+ "r am",
1796
+ "Ġb ack",
1797
+ "Ġad d",
1798
+ "Ġp op",
1799
+ "Ġg o",
1800
+ "ur ch",
1801
+ "Ġdes c",
1802
+ "Ġs ing",
1803
+ "iel d",
1804
+ "Ġper form",
1805
+ "ain ed",
1806
+ "Ġre ce",
1807
+ "id ent",
1808
+ "Ġe m",
1809
+ "er t",
1810
+ "u res",
1811
+ "Ġin v",
1812
+ "Ġde p",
1813
+ "Ġ19 8",
1814
+ "a ir",
1815
+ "er n",
1816
+ "at her",
1817
+ "f ul",
1818
+ "Ġ Z",
1819
+ "Ġm on",
1820
+ "Ġman y",
1821
+ "Ġm ain",
1822
+ "Ġst ud",
1823
+ "Ġl ong",
1824
+ "in n",
1825
+ "th ough",
1826
+ "u p",
1827
+ "o ol",
1828
+ "ĠUn ited",
1829
+ "l ed",
1830
+ "em ent",
1831
+ "Ġ1 5",
1832
+ "ow er",
1833
+ "ĠJo hn",
1834
+ "Ġo p",
1835
+ "Ġ1 1",
1836
+ "in ed",
1837
+ "Ġm et",
1838
+ "o ber",
1839
+ "le y",
1840
+ "Ġ1 7",
1841
+ "Ġcent ury",
1842
+ "Ġte am",
1843
+ "Ġ est",
1844
+ "ĠA fter",
1845
+ "y l",
1846
+ "Ġm in",
1847
+ "u ch",
1848
+ "ut e",
1849
+ "Ġde velop",
1850
+ "ĠS he",
1851
+ "0 s",
1852
+ "i am",
1853
+ "Ġsh ow",
1854
+ "el f",
1855
+ "Ġre p",
1856
+ "Ġcon c",
1857
+ "at ive",
1858
+ "Ġc re",
1859
+ "over n",
1860
+ "a red",
1861
+ "Ġ19 4",
1862
+ "Ġor igin",
1863
+ "Ġs m",
1864
+ "iv ers",
1865
+ "a z",
1866
+ "Ġle ad",
1867
+ "Ġsever al",
1868
+ "a h",
1869
+ "Ġo b",
1870
+ "Ġre v",
1871
+ "Ġm ill",
1872
+ "er m",
1873
+ "u ally",
1874
+ "o ot",
1875
+ "Ġbe gan",
1876
+ "Ġ19 6",
1877
+ "i red",
1878
+ "Ġd if",
1879
+ "Ġcont in",
1880
+ "Ġs ign",
1881
+ "i k",
1882
+ "ĠI nd",
1883
+ "ment s",
1884
+ "iz ed",
1885
+ "Ġ19 7",
1886
+ "Ġd irect",
1887
+ "a u",
1888
+ "Ġex t",
1889
+ "ros s",
1890
+ "em b",
1891
+ "d er",
1892
+ "Ġp ol",
1893
+ "Ġm ay",
1894
+ "a pt",
1895
+ "el s",
1896
+ "ĠW h",
1897
+ "Ġcomp le",
1898
+ "Ġar t",
1899
+ "ĠB r",
1900
+ "ĠI s",
1901
+ "un e",
1902
+ "t il",
1903
+ "Ġc rit",
1904
+ "Ġh ist",
1905
+ "Ġear ly",
1906
+ "Ġc ould",
1907
+ "ĠC on",
1908
+ "Ġd id",
1909
+ "Ġb el",
1910
+ "Ġcall ed",
1911
+ "u ed",
1912
+ "Ġn ear",
1913
+ "Ġepis ode",
1914
+ "y p",
1915
+ "Ġdesc rib",
1916
+ "im es",
1917
+ "Ġb ro",
1918
+ "rou p",
1919
+ "op le",
1920
+ "Ġd own",
1921
+ "Ġr un",
1922
+ "ak ing",
1923
+ "Ġdis c",
1924
+ "Ġal ong",
1925
+ "cc ess",
1926
+ "ĠM ay",
1927
+ "Ġfe at",
1928
+ "Ġin st",
1929
+ "ĠAmeric an",
1930
+ "Ġs aid",
1931
+ "Ġd ist",
1932
+ "Ġin f",
1933
+ "Ġim p",
1934
+ "in k",
1935
+ "Ġin s"
1936
+ ]
1937
+ }
1938
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "BloomTokenizer",
11
+ "unk_token": "<unk>"
12
+ }