echarlaix HF staff commited on
Commit
67806c0
1 Parent(s): 5868e68
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hf-internal-testing/tiny-random-PhiForCausalLM",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 32,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
+ "is_decoder": true,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "phi",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 2,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "partial_rotary_factor": 0.5,
25
+ "qk_layernorm": false,
26
+ "resid_pdrop": 0.0,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.38.2",
32
+ "type_vocab_size": 16,
33
+ "use_cache": true,
34
+ "vocab_size": 1024
35
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbbc177683bcd0c8d694d552461d9dba3cd6e7f5a883cb8c6c6cce36ce6882e
3
+ size 323520
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
@@ -0,0 +1,1849 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|padding|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": {
26
+ "type": "NFC"
27
+ },
28
+ "pre_tokenizer": {
29
+ "type": "ByteLevel",
30
+ "add_prefix_space": false,
31
+ "trim_offsets": true,
32
+ "use_regex": true
33
+ },
34
+ "post_processor": {
35
+ "type": "ByteLevel",
36
+ "add_prefix_space": false,
37
+ "trim_offsets": true,
38
+ "use_regex": true
39
+ },
40
+ "decoder": {
41
+ "type": "ByteLevel",
42
+ "add_prefix_space": false,
43
+ "trim_offsets": true,
44
+ "use_regex": true
45
+ },
46
+ "model": {
47
+ "type": "BPE",
48
+ "dropout": null,
49
+ "unk_token": null,
50
+ "continuing_subword_prefix": null,
51
+ "end_of_word_suffix": null,
52
+ "fuse_unk": false,
53
+ "byte_fallback": false,
54
+ "vocab": {
55
+ "<|endoftext|>": 0,
56
+ "<|padding|>": 1,
57
+ "!": 2,
58
+ "\"": 3,
59
+ "#": 4,
60
+ "$": 5,
61
+ "%": 6,
62
+ "&": 7,
63
+ "'": 8,
64
+ "(": 9,
65
+ ")": 10,
66
+ "*": 11,
67
+ "+": 12,
68
+ ",": 13,
69
+ "-": 14,
70
+ ".": 15,
71
+ "/": 16,
72
+ "0": 17,
73
+ "1": 18,
74
+ "2": 19,
75
+ "3": 20,
76
+ "4": 21,
77
+ "5": 22,
78
+ "6": 23,
79
+ "7": 24,
80
+ "8": 25,
81
+ "9": 26,
82
+ ":": 27,
83
+ ";": 28,
84
+ "<": 29,
85
+ "=": 30,
86
+ ">": 31,
87
+ "?": 32,
88
+ "@": 33,
89
+ "A": 34,
90
+ "B": 35,
91
+ "C": 36,
92
+ "D": 37,
93
+ "E": 38,
94
+ "F": 39,
95
+ "G": 40,
96
+ "H": 41,
97
+ "I": 42,
98
+ "J": 43,
99
+ "K": 44,
100
+ "L": 45,
101
+ "M": 46,
102
+ "N": 47,
103
+ "O": 48,
104
+ "P": 49,
105
+ "Q": 50,
106
+ "R": 51,
107
+ "S": 52,
108
+ "T": 53,
109
+ "U": 54,
110
+ "V": 55,
111
+ "W": 56,
112
+ "X": 57,
113
+ "Y": 58,
114
+ "Z": 59,
115
+ "[": 60,
116
+ "\\": 61,
117
+ "]": 62,
118
+ "^": 63,
119
+ "_": 64,
120
+ "`": 65,
121
+ "a": 66,
122
+ "b": 67,
123
+ "c": 68,
124
+ "d": 69,
125
+ "e": 70,
126
+ "f": 71,
127
+ "g": 72,
128
+ "h": 73,
129
+ "i": 74,
130
+ "j": 75,
131
+ "k": 76,
132
+ "l": 77,
133
+ "m": 78,
134
+ "n": 79,
135
+ "o": 80,
136
+ "p": 81,
137
+ "q": 82,
138
+ "r": 83,
139
+ "s": 84,
140
+ "t": 85,
141
+ "u": 86,
142
+ "v": 87,
143
+ "w": 88,
144
+ "x": 89,
145
+ "y": 90,
146
+ "z": 91,
147
+ "{": 92,
148
+ "|": 93,
149
+ "}": 94,
150
+ "~": 95,
151
+ "¡": 96,
152
+ "¢": 97,
153
+ "£": 98,
154
+ "¤": 99,
155
+ "¥": 100,
156
+ "¦": 101,
157
+ "§": 102,
158
+ "¨": 103,
159
+ "©": 104,
160
+ "ª": 105,
161
+ "«": 106,
162
+ "¬": 107,
163
+ "®": 108,
164
+ "¯": 109,
165
+ "°": 110,
166
+ "±": 111,
167
+ "²": 112,
168
+ "³": 113,
169
+ "´": 114,
170
+ "µ": 115,
171
+ "¶": 116,
172
+ "·": 117,
173
+ "¸": 118,
174
+ "¹": 119,
175
+ "º": 120,
176
+ "»": 121,
177
+ "¼": 122,
178
+ "½": 123,
179
+ "¾": 124,
180
+ "¿": 125,
181
+ "À": 126,
182
+ "Á": 127,
183
+ "Â": 128,
184
+ "Ã": 129,
185
+ "Ä": 130,
186
+ "Å": 131,
187
+ "Æ": 132,
188
+ "Ç": 133,
189
+ "È": 134,
190
+ "É": 135,
191
+ "Ê": 136,
192
+ "Ë": 137,
193
+ "Ì": 138,
194
+ "Í": 139,
195
+ "Î": 140,
196
+ "Ï": 141,
197
+ "Ð": 142,
198
+ "Ñ": 143,
199
+ "Ò": 144,
200
+ "Ó": 145,
201
+ "Ô": 146,
202
+ "Õ": 147,
203
+ "Ö": 148,
204
+ "×": 149,
205
+ "Ø": 150,
206
+ "Ù": 151,
207
+ "Ú": 152,
208
+ "Û": 153,
209
+ "Ü": 154,
210
+ "Ý": 155,
211
+ "Þ": 156,
212
+ "ß": 157,
213
+ "à": 158,
214
+ "á": 159,
215
+ "â": 160,
216
+ "ã": 161,
217
+ "ä": 162,
218
+ "å": 163,
219
+ "æ": 164,
220
+ "ç": 165,
221
+ "è": 166,
222
+ "é": 167,
223
+ "ê": 168,
224
+ "ë": 169,
225
+ "ì": 170,
226
+ "í": 171,
227
+ "î": 172,
228
+ "ï": 173,
229
+ "ð": 174,
230
+ "ñ": 175,
231
+ "ò": 176,
232
+ "ó": 177,
233
+ "ô": 178,
234
+ "õ": 179,
235
+ "ö": 180,
236
+ "÷": 181,
237
+ "ø": 182,
238
+ "ù": 183,
239
+ "ú": 184,
240
+ "û": 185,
241
+ "ü": 186,
242
+ "ý": 187,
243
+ "þ": 188,
244
+ "ÿ": 189,
245
+ "Ā": 190,
246
+ "ā": 191,
247
+ "Ă": 192,
248
+ "ă": 193,
249
+ "Ą": 194,
250
+ "ą": 195,
251
+ "Ć": 196,
252
+ "ć": 197,
253
+ "Ĉ": 198,
254
+ "ĉ": 199,
255
+ "Ċ": 200,
256
+ "ċ": 201,
257
+ "Č": 202,
258
+ "č": 203,
259
+ "Ď": 204,
260
+ "ď": 205,
261
+ "Đ": 206,
262
+ "đ": 207,
263
+ "Ē": 208,
264
+ "ē": 209,
265
+ "Ĕ": 210,
266
+ "ĕ": 211,
267
+ "Ė": 212,
268
+ "ė": 213,
269
+ "Ę": 214,
270
+ "ę": 215,
271
+ "Ě": 216,
272
+ "ě": 217,
273
+ "Ĝ": 218,
274
+ "ĝ": 219,
275
+ "Ğ": 220,
276
+ "ğ": 221,
277
+ "Ġ": 222,
278
+ "ġ": 223,
279
+ "Ģ": 224,
280
+ "ģ": 225,
281
+ "Ĥ": 226,
282
+ "ĥ": 227,
283
+ "Ħ": 228,
284
+ "ħ": 229,
285
+ "Ĩ": 230,
286
+ "ĩ": 231,
287
+ "Ī": 232,
288
+ "ī": 233,
289
+ "Ĭ": 234,
290
+ "ĭ": 235,
291
+ "Į": 236,
292
+ "į": 237,
293
+ "İ": 238,
294
+ "ı": 239,
295
+ "IJ": 240,
296
+ "ij": 241,
297
+ "Ĵ": 242,
298
+ "ĵ": 243,
299
+ "Ķ": 244,
300
+ "ķ": 245,
301
+ "ĸ": 246,
302
+ "Ĺ": 247,
303
+ "ĺ": 248,
304
+ "Ļ": 249,
305
+ "ļ": 250,
306
+ "Ľ": 251,
307
+ "ľ": 252,
308
+ "Ŀ": 253,
309
+ "ŀ": 254,
310
+ "Ł": 255,
311
+ "ł": 256,
312
+ "Ń": 257,
313
+ "Ġt": 258,
314
+ "he": 259,
315
+ "Ġa": 260,
316
+ "in": 261,
317
+ "Ġthe": 262,
318
+ "er": 263,
319
+ "on": 264,
320
+ "Ġ,": 265,
321
+ "re": 266,
322
+ "Ġs": 267,
323
+ "ed": 268,
324
+ "Ġo": 269,
325
+ "Ġw": 270,
326
+ "nd": 271,
327
+ "at": 272,
328
+ "Ġ.": 273,
329
+ "or": 274,
330
+ "it": 275,
331
+ "Ġc": 276,
332
+ "en": 277,
333
+ "Ġf": 278,
334
+ "is": 279,
335
+ "es": 280,
336
+ "ar": 281,
337
+ "Ġof": 282,
338
+ "Ġb": 283,
339
+ "an": 284,
340
+ "Ġin": 285,
341
+ "al": 286,
342
+ "ing": 287,
343
+ "Ġp": 288,
344
+ "Ġand": 289,
345
+ "as": 290,
346
+ "Ġto": 291,
347
+ "ro": 292,
348
+ "ic": 293,
349
+ "Ġm": 294,
350
+ "Ġd": 295,
351
+ "Ġh": 296,
352
+ "ion": 297,
353
+ "le": 298,
354
+ "ou": 299,
355
+ "ĠT": 300,
356
+ "Ġre": 301,
357
+ "Ġ=": 302,
358
+ "Ġ\"": 303,
359
+ "ĠA": 304,
360
+ "ĠS": 305,
361
+ "ent": 306,
362
+ "il": 307,
363
+ "Ġth": 308,
364
+ "Ġ1": 309,
365
+ "st": 310,
366
+ "ĠC": 311,
367
+ "el": 312,
368
+ "om": 313,
369
+ "Ġl": 314,
370
+ "am": 315,
371
+ "ĠĊ": 316,
372
+ "Ġe": 317,
373
+ "Ġn": 318,
374
+ "Ġ@": 319,
375
+ "ad": 320,
376
+ "ac": 321,
377
+ "Ġwas": 322,
378
+ "ĠM": 323,
379
+ "ur": 324,
380
+ "ĠThe": 325,
381
+ "ec": 326,
382
+ "Ġon": 327,
383
+ "ly": 328,
384
+ "ĠB": 329,
385
+ "ĠI": 330,
386
+ "Ġg": 331,
387
+ "Ġ'": 332,
388
+ "et": 333,
389
+ "ol": 334,
390
+ "id": 335,
391
+ "iv": 336,
392
+ "im": 337,
393
+ "Ġfor": 338,
394
+ "ir": 339,
395
+ "-@": 340,
396
+ "Ġ@-@": 341,
397
+ "ig": 342,
398
+ "ot": 343,
399
+ "ter": 344,
400
+ "Ġas": 345,
401
+ "ĠH": 346,
402
+ "us": 347,
403
+ "ow": 348,
404
+ "Ġst": 349,
405
+ "ut": 350,
406
+ "ith": 351,
407
+ "ay": 352,
408
+ "Ġ2": 353,
409
+ "ĠP": 354,
410
+ "ation": 355,
411
+ "ver": 356,
412
+ "Ġbe": 357,
413
+ "her": 358,
414
+ "Ġthat": 359,
415
+ "Ġwith": 360,
416
+ "ĠR": 361,
417
+ "ce": 362,
418
+ "th": 363,
419
+ "ĠD": 364,
420
+ "Ġis": 365,
421
+ "un": 366,
422
+ "em": 367,
423
+ "ĠF": 368,
424
+ "Ġwh": 369,
425
+ "ul": 370,
426
+ "Ġby": 371,
427
+ "Ġal": 372,
428
+ "ch": 373,
429
+ "Ġ)": 374,
430
+ "Ġ(": 375,
431
+ "ĠW": 376,
432
+ "Ġcon": 377,
433
+ "ra": 378,
434
+ "ĠG": 379,
435
+ "os": 380,
436
+ "ĠL": 381,
437
+ "ĠN": 382,
438
+ "Ġat": 383,
439
+ "ers": 384,
440
+ "ct": 385,
441
+ "Ġit": 386,
442
+ "Ġ19": 387,
443
+ "rom": 388,
444
+ "and": 389,
445
+ "Ġan": 390,
446
+ "um": 391,
447
+ "est": 392,
448
+ "ĠJ": 393,
449
+ "ag": 394,
450
+ "Ġhe": 395,
451
+ "00": 396,
452
+ "ist": 397,
453
+ "ain": 398,
454
+ "od": 399,
455
+ "av": 400,
456
+ "ri": 401,
457
+ "ĠE": 402,
458
+ "ĠO": 403,
459
+ "Ġfrom": 404,
460
+ "Ġcom": 405,
461
+ "Ġhis": 406,
462
+ "op": 407,
463
+ "Ġpro": 408,
464
+ "res": 409,
465
+ "ies": 410,
466
+ "if": 411,
467
+ "Ġv": 412,
468
+ "ort": 413,
469
+ "ere": 414,
470
+ "ill": 415,
471
+ "ld": 416,
472
+ "Ġde": 417,
473
+ "pp": 418,
474
+ "Ġsu": 419,
475
+ "ore": 420,
476
+ "ĠIn": 421,
477
+ "Ġr": 422,
478
+ "Ġse": 423,
479
+ "Ġwere": 424,
480
+ "ew": 425,
481
+ "ong": 426,
482
+ "igh": 427,
483
+ "ard": 428,
484
+ "ate": 429,
485
+ "all": 430,
486
+ "art": 431,
487
+ "ak": 432,
488
+ "ich": 433,
489
+ "Ġch": 434,
490
+ "Ġor": 435,
491
+ "ab": 436,
492
+ "ant": 437,
493
+ "ud": 438,
494
+ "oc": 439,
495
+ "ber": 440,
496
+ "Ġex": 441,
497
+ "gh": 442,
498
+ "ity": 443,
499
+ "ated": 444,
500
+ "pt": 445,
501
+ "ess": 446,
502
+ "ear": 447,
503
+ "ĠK": 448,
504
+ "Ġpl": 449,
505
+ "ame": 450,
506
+ "qu": 451,
507
+ "ive": 452,
508
+ "rou": 453,
509
+ "Ġare": 454,
510
+ "Ġâ": 455,
511
+ "Ġsh": 456,
512
+ "Ġk": 457,
513
+ "ack": 458,
514
+ "ect": 459,
515
+ "ĠâĢ": 460,
516
+ "ĠU": 461,
517
+ "Ġhad": 462,
518
+ "se": 463,
519
+ "Ġwhich": 464,
520
+ "red": 465,
521
+ "ov": 466,
522
+ "ĠSt": 467,
523
+ "ast": 468,
524
+ "Ġsp": 469,
525
+ "ian": 470,
526
+ "Ġy": 471,
527
+ "ment": 472,
528
+ "Ġle": 473,
529
+ "Ġnot": 474,
530
+ "ge": 475,
531
+ "ord": 476,
532
+ "rit": 477,
533
+ "ip": 478,
534
+ "ine": 479,
535
+ "ell": 480,
536
+ "ally": 481,
537
+ "our": 482,
538
+ "ost": 483,
539
+ "ight": 484,
540
+ "ther": 485,
541
+ "ap": 486,
542
+ "Ġu": 487,
543
+ "ish": 488,
544
+ "ĠCh": 489,
545
+ "oun": 490,
546
+ "ia": 491,
547
+ "Ġ3": 492,
548
+ "ave": 493,
549
+ "ary": 494,
550
+ "ust": 495,
551
+ "og": 496,
552
+ "Ġ200": 497,
553
+ "Ġun": 498,
554
+ "ous": 499,
555
+ "irst": 500,
556
+ "ĠV": 501,
557
+ "cc": 502,
558
+ "Ġinc": 503,
559
+ "Ġ;": 504,
560
+ "Ġcomp": 505,
561
+ "ru": 506,
562
+ "ions": 507,
563
+ "Ġtheir": 508,
564
+ "Ġbut": 509,
565
+ "ide": 510,
566
+ "ure": 511,
567
+ "so": 512,
568
+ "Ġcont": 513,
569
+ "Ġint": 514,
570
+ "fter": 515,
571
+ "ical": 516,
572
+ "ial": 517,
573
+ "Ġar": 518,
574
+ "Ġfirst": 519,
575
+ "ould": 520,
576
+ "Ġits": 521,
577
+ "hed": 522,
578
+ "ĠâĢĵ": 523,
579
+ "Ġwhe": 524,
580
+ "wo": 525,
581
+ "out": 526,
582
+ "ub": 527,
583
+ "Ġ20": 528,
584
+ "ff": 529,
585
+ "Ġ:": 530,
586
+ "ue": 531,
587
+ "Ġher": 532,
588
+ "own": 533,
589
+ "ok": 534,
590
+ "Ġalso": 535,
591
+ "Ġcl": 536,
592
+ "per": 537,
593
+ "ign": 538,
594
+ "ater": 539,
595
+ "ran": 540,
596
+ "orm": 541,
597
+ "ie": 542,
598
+ "ome": 543,
599
+ "ork": 544,
600
+ "ass": 545,
601
+ "ire": 546,
602
+ "end": 547,
603
+ "Ġres": 548,
604
+ "Ġab": 549,
605
+ "Ġad": 550,
606
+ "Ġus": 551,
607
+ "ry": 552,
608
+ "Ġrec": 553,
609
+ "Ġhave": 554,
610
+ "age": 555,
611
+ "ĠHe": 556,
612
+ "Ġ4": 557,
613
+ "Ġro": 558,
614
+ "mer": 559,
615
+ "Ġone": 560,
616
+ "ond": 561,
617
+ "low": 562,
618
+ "Ġhas": 563,
619
+ "ĠTh": 564,
620
+ "du": 565,
621
+ "Ġ5": 566,
622
+ "Ġper": 567,
623
+ "Ġbeen": 568,
624
+ "ime": 569,
625
+ "Ġtwo": 570,
626
+ "ence": 571,
627
+ "land": 572,
628
+ "Ġ18": 573,
629
+ ".@": 574,
630
+ "Ġ@.@": 575,
631
+ "ult": 576,
632
+ "ree": 577,
633
+ "ough": 578,
634
+ "ile": 579,
635
+ "Ġwho": 580,
636
+ "ĠAl": 581,
637
+ "Ġsc": 582,
638
+ "uring": 583,
639
+ "pl": 584,
640
+ "ory": 585,
641
+ "ition": 586,
642
+ "ric": 587,
643
+ "ations": 588,
644
+ "Ġdis": 589,
645
+ "Ġthis": 590,
646
+ "Ġbec": 591,
647
+ "Ġapp": 592,
648
+ "iz": 593,
649
+ "ĠIt": 594,
650
+ "are": 595,
651
+ "ach": 596,
652
+ "lud": 597,
653
+ "ade": 598,
654
+ "Ġplay": 599,
655
+ "Ġj": 600,
656
+ "Ġman": 601,
657
+ "act": 602,
658
+ "ely": 603,
659
+ "Ġpart": 604,
660
+ "Ġdes": 605,
661
+ "Ġag": 606,
662
+ "Ġthey": 607,
663
+ "Ġyear": 608,
664
+ "ount": 609,
665
+ "Ġ201": 610,
666
+ "Ġover": 611,
667
+ "Ġother": 612,
668
+ "ound": 613,
669
+ "Ġafter": 614,
670
+ "ib": 615,
671
+ "over": 616,
672
+ "Ġser": 617,
673
+ "Ġen": 618,
674
+ "Ġoff": 619,
675
+ "Ġim": 620,
676
+ "ction": 621,
677
+ "ĠY": 622,
678
+ "ke": 623,
679
+ "ite": 624,
680
+ ",@": 625,
681
+ "Ġ@,@": 626,
682
+ "te": 627,
683
+ "urn": 628,
684
+ "Ġinclud": 629,
685
+ "ress": 630,
686
+ "ance": 631,
687
+ "ang": 632,
688
+ "Ġatt": 633,
689
+ "ice": 634,
690
+ "ace": 635,
691
+ "ark": 636,
692
+ "Ġout": 637,
693
+ "wn": 638,
694
+ "ph": 639,
695
+ "ember": 640,
696
+ "Ġpre": 641,
697
+ "Ġup": 642,
698
+ "ens": 643,
699
+ "man": 644,
700
+ "Ġev": 645,
701
+ "Ġtime": 646,
702
+ "nder": 647,
703
+ "rough": 648,
704
+ "ced": 649,
705
+ "Ġfin": 650,
706
+ "Ġinto": 651,
707
+ "one": 652,
708
+ "port": 653,
709
+ "round": 654,
710
+ "we": 655,
711
+ "ren": 656,
712
+ "les": 657,
713
+ "int": 658,
714
+ "ĠOn": 659,
715
+ "vel": 660,
716
+ "Ġcomm": 661,
717
+ "Ġshe": 662,
718
+ "ason": 663,
719
+ "amp": 664,
720
+ "Ġte": 665,
721
+ "Ġwould": 666,
722
+ "ward": 667,
723
+ "Ġmore": 668,
724
+ "Ġ6": 669,
725
+ "ied": 670,
726
+ "ose": 671,
727
+ "rib": 672,
728
+ "ĠUn": 673,
729
+ "Ġall": 674,
730
+ "ings": 675,
731
+ "tern": 676,
732
+ "ces": 677,
733
+ "able": 678,
734
+ "Ġwe": 679,
735
+ "ited": 680,
736
+ "ever": 681,
737
+ "ents": 682,
738
+ "Ġhim": 683,
739
+ "ased": 684,
740
+ "ors": 685,
741
+ "oy": 686,
742
+ "ood": 687,
743
+ "Ġcent": 688,
744
+ "ix": 689,
745
+ "ase": 690,
746
+ "ild": 691,
747
+ "ĠAn": 692,
748
+ "Ġ7": 693,
749
+ "Ġwork": 694,
750
+ "ates": 695,
751
+ "ious": 696,
752
+ "ath": 697,
753
+ "Ġpo": 698,
754
+ "rop": 699,
755
+ "old": 700,
756
+ "als": 701,
757
+ "iss": 702,
758
+ "ey": 703,
759
+ "ict": 704,
760
+ "Ġfe": 705,
761
+ "Ġthem": 706,
762
+ "gan": 707,
763
+ "Ġsec": 708,
764
+ "Ġbet": 709,
765
+ "Ġwhen": 710,
766
+ "Ġsong": 711,
767
+ "Ġrem": 712,
768
+ "ep": 713,
769
+ "form": 714,
770
+ "ail": 715,
771
+ "fer": 716,
772
+ "Ġear": 717,
773
+ "ubl": 718,
774
+ "aw": 719,
775
+ "Ġkn": 720,
776
+ "ake": 721,
777
+ "aus": 722,
778
+ "Ġmost": 723,
779
+ "Ġcons": 724,
780
+ "Ġduring": 725,
781
+ "ĠAs": 726,
782
+ "orth": 727,
783
+ "Ġnew": 728,
784
+ "ered": 729,
785
+ "ilm": 730,
786
+ "ved": 731,
787
+ "att": 732,
788
+ "Ġonly": 733,
789
+ "Ġ9": 734,
790
+ "Ġdec": 735,
791
+ "Ġ8": 736,
792
+ "ick": 737,
793
+ "Ġgame": 738,
794
+ "ons": 739,
795
+ "ug": 740,
796
+ "Ġtr": 741,
797
+ "ft": 742,
798
+ "oth": 743,
799
+ "ook": 744,
800
+ "ĠMar": 745,
801
+ "reat": 746,
802
+ "way": 747,
803
+ "Ġcan": 748,
804
+ "ollow": 749,
805
+ "outh": 750,
806
+ "ween": 751,
807
+ "ĠEn": 752,
808
+ "Ġ199": 753,
809
+ "ters": 754,
810
+ "Ġrel": 755,
811
+ "ind": 756,
812
+ "Ġabout": 757,
813
+ "Ġseason": 758,
814
+ "Ġagain": 759,
815
+ "ral": 760,
816
+ "Ġthree": 761,
817
+ "ational": 762,
818
+ "Ġunder": 763,
819
+ "ular": 764,
820
+ "Ġme": 765,
821
+ "Ġthan": 766,
822
+ "ĠCom": 767,
823
+ "ĠAr": 768,
824
+ "hip": 769,
825
+ "ob": 770,
826
+ "Ġne": 771,
827
+ "Ġbetween": 772,
828
+ "Ġfl": 773,
829
+ "hn": 774,
830
+ "ve": 775,
831
+ "Ġchar": 776,
832
+ "Ġcol": 777,
833
+ "Ġrecord": 778,
834
+ "iew": 779,
835
+ "ron": 780,
836
+ "fore": 781,
837
+ "Ġthrough": 782,
838
+ "ision": 783,
839
+ "orn": 784,
840
+ "Ġ00": 785,
841
+ "ock": 786,
842
+ "Ġver": 787,
843
+ "Ġlater": 788,
844
+ "Ġnum": 789,
845
+ "Ġend": 790,
846
+ "olog": 791,
847
+ "ames": 792,
848
+ "Ġpos": 793,
849
+ "Ġwrit": 794,
850
+ "Ġprodu": 795,
851
+ "Ġwhile": 796,
852
+ "Ġact": 797,
853
+ "Ġrele": 798,
854
+ "Ġfilm": 799,
855
+ "ished": 800,
856
+ "Ġpr": 801,
857
+ "ans": 802,
858
+ "Ġreg": 803,
859
+ "Ġform": 804,
860
+ "Ġass": 805,
861
+ "ĠSe": 806,
862
+ "ury": 807,
863
+ "ted": 808,
864
+ "ts": 809,
865
+ "Ġmade": 810,
866
+ "Ġsub": 811,
867
+ "Ġpe": 812,
868
+ "Ġso": 813,
869
+ "orld": 814,
870
+ "Ġret": 815,
871
+ "ĠNew": 816,
872
+ "Ġspec": 817,
873
+ "Ġacc": 818,
874
+ "Ġqu": 819,
875
+ "Ġwhere": 820,
876
+ "ener": 821,
877
+ "Ġmov": 822,
878
+ "hes": 823,
879
+ "meric": 824,
880
+ "ating": 825,
881
+ "Ġinter": 826,
882
+ "ĠLe": 827,
883
+ "ĠAmeric": 828,
884
+ "Ġra": 829,
885
+ "Ġsome": 830,
886
+ "Ġco": 831,
887
+ "Ġlar": 832,
888
+ "Ġbu": 833,
889
+ "Ġdef": 834,
890
+ "bum": 835,
891
+ "Ġac": 836,
892
+ "Ġmus": 837,
893
+ "Ġfollow": 838,
894
+ "ĠAt": 839,
895
+ "ins": 840,
896
+ "ived": 841,
897
+ "ific": 842,
898
+ "ual": 843,
899
+ "Ġam": 844,
900
+ "Ġsuch": 845,
901
+ "Ġsecond": 846,
902
+ "ike": 847,
903
+ "Ġfour": 848,
904
+ "Ġind": 849,
905
+ "ann": 850,
906
+ "hen": 851,
907
+ "Ġused": 852,
908
+ "ĠRe": 853,
909
+ "ics": 854,
910
+ "lect": 855,
911
+ "Ġday": 856,
912
+ "iel": 857,
913
+ "ily": 858,
914
+ "ĠThis": 859,
915
+ "Ġ0": 860,
916
+ "Ġpubl": 861,
917
+ "Ġcall": 862,
918
+ "ĠJo": 863,
919
+ "ll": 864,
920
+ "Ġalbum": 865,
921
+ "Ġ000": 866,
922
+ "rans": 867,
923
+ "Ġdo": 868,
924
+ "any": 869,
925
+ "Ġbefore": 870,
926
+ "ros": 871,
927
+ "ĠSh": 872,
928
+ "Ġsy": 873,
929
+ "aid": 874,
930
+ "ĠEng": 875,
931
+ "Ġbeing": 876,
932
+ "Ġ10": 877,
933
+ "uc": 878,
934
+ "Ġep": 879,
935
+ "Ġsupp": 880,
936
+ "Ġthere": 881,
937
+ "Ġyears": 882,
938
+ "ars": 883,
939
+ "owever": 884,
940
+ "Ġent": 885,
941
+ "ife": 886,
942
+ "Ġhigh": 887,
943
+ "Ġfound": 888,
944
+ "ird": 889,
945
+ "Ġno": 890,
946
+ "Ġset": 891,
947
+ "ines": 892,
948
+ "iver": 893,
949
+ "io": 894,
950
+ "other": 895,
951
+ "ject": 896,
952
+ "Ġsur": 897,
953
+ "aj": 898,
954
+ "ten": 899,
955
+ "Ġtra": 900,
956
+ "Ġ12": 901,
957
+ "ised": 902,
958
+ "ities": 903,
959
+ "velop": 904,
960
+ "Ġbl": 905,
961
+ "ale": 906,
962
+ "Ġseries": 907,
963
+ "Ġloc": 908,
964
+ "Ġnumber": 909,
965
+ "Ġpres": 910,
966
+ "ane": 911,
967
+ "ause": 912,
968
+ "ode": 913,
969
+ "ek": 914,
970
+ "ton": 915,
971
+ "ĠSc": 916,
972
+ "ier": 917,
973
+ "ise": 918,
974
+ "Ġsever": 919,
975
+ "ince": 920,
976
+ "Ġboth": 921,
977
+ "ank": 922,
978
+ "row": 923,
979
+ "irect": 924,
980
+ "son": 925,
981
+ "Ġthen": 926,
982
+ "ĠBrit": 927,
983
+ "iet": 928,
984
+ "Ġ16": 929,
985
+ "Ġepis": 930,
986
+ "Ġincluding": 931,
987
+ "its": 932,
988
+ "igin": 933,
989
+ "pr": 934,
990
+ "Ġ/": 935,
991
+ "Ġagainst": 936,
992
+ "Ġwell": 937,
993
+ "Ġbecame": 938,
994
+ "Ġexp": 939,
995
+ "Ġknown": 940,
996
+ "Ġtrans": 941,
997
+ "Ġcharac": 942,
998
+ "ĠâĢĶ": 943,
999
+ "ram": 944,
1000
+ "Ġback": 945,
1001
+ "Ġadd": 946,
1002
+ "Ġpop": 947,
1003
+ "Ġgo": 948,
1004
+ "urch": 949,
1005
+ "Ġdesc": 950,
1006
+ "Ġsing": 951,
1007
+ "ield": 952,
1008
+ "Ġperform": 953,
1009
+ "ained": 954,
1010
+ "Ġrece": 955,
1011
+ "ident": 956,
1012
+ "Ġem": 957,
1013
+ "ert": 958,
1014
+ "ures": 959,
1015
+ "Ġinv": 960,
1016
+ "Ġdep": 961,
1017
+ "Ġ198": 962,
1018
+ "air": 963,
1019
+ "ern": 964,
1020
+ "ather": 965,
1021
+ "ful": 966,
1022
+ "ĠZ": 967,
1023
+ "Ġmon": 968,
1024
+ "Ġmany": 969,
1025
+ "Ġmain": 970,
1026
+ "Ġstud": 971,
1027
+ "Ġlong": 972,
1028
+ "inn": 973,
1029
+ "though": 974,
1030
+ "up": 975,
1031
+ "ool": 976,
1032
+ "ĠUnited": 977,
1033
+ "led": 978,
1034
+ "ement": 979,
1035
+ "Ġ15": 980,
1036
+ "ower": 981,
1037
+ "ĠJohn": 982,
1038
+ "Ġop": 983,
1039
+ "Ġ11": 984,
1040
+ "ined": 985,
1041
+ "Ġmet": 986,
1042
+ "ober": 987,
1043
+ "ley": 988,
1044
+ "Ġ17": 989,
1045
+ "Ġcentury": 990,
1046
+ "Ġteam": 991,
1047
+ "Ġest": 992,
1048
+ "ĠAfter": 993,
1049
+ "yl": 994,
1050
+ "Ġmin": 995,
1051
+ "uch": 996,
1052
+ "ute": 997,
1053
+ "Ġdevelop": 998,
1054
+ "ĠShe": 999,
1055
+ "iam": 1000,
1056
+ "Ġshow": 1001,
1057
+ "elf": 1002,
1058
+ "Ġrep": 1003,
1059
+ "Ġconc": 1004,
1060
+ "ative": 1005,
1061
+ "Ġcre": 1006,
1062
+ "overn": 1007,
1063
+ "ared": 1008,
1064
+ "Ġ194": 1009,
1065
+ "Ġorigin": 1010,
1066
+ "Ġsm": 1011,
1067
+ "ivers": 1012,
1068
+ "az": 1013,
1069
+ "Ġlead": 1014,
1070
+ "Ġseveral": 1015,
1071
+ "ah": 1016,
1072
+ "Ġob": 1017,
1073
+ "Ġrev": 1018,
1074
+ "Ġmill": 1019,
1075
+ "erm": 1020,
1076
+ "ually": 1021,
1077
+ "oot": 1022,
1078
+ "Ġbegan": 1023
1079
+ },
1080
+ "merges": [
1081
+ "Ġ t",
1082
+ "h e",
1083
+ "Ġ a",
1084
+ "i n",
1085
+ "Ġt he",
1086
+ "e r",
1087
+ "o n",
1088
+ "Ġ ,",
1089
+ "r e",
1090
+ "Ġ s",
1091
+ "e d",
1092
+ "Ġ o",
1093
+ "Ġ w",
1094
+ "n d",
1095
+ "a t",
1096
+ "Ġ .",
1097
+ "o r",
1098
+ "i t",
1099
+ "Ġ c",
1100
+ "e n",
1101
+ "Ġ f",
1102
+ "i s",
1103
+ "e s",
1104
+ "a r",
1105
+ "Ġo f",
1106
+ "Ġ b",
1107
+ "a n",
1108
+ "Ġ in",
1109
+ "a l",
1110
+ "in g",
1111
+ "Ġ p",
1112
+ "Ġa nd",
1113
+ "a s",
1114
+ "Ġt o",
1115
+ "r o",
1116
+ "i c",
1117
+ "Ġ m",
1118
+ "Ġ d",
1119
+ "Ġ h",
1120
+ "i on",
1121
+ "l e",
1122
+ "o u",
1123
+ "Ġ T",
1124
+ "Ġ re",
1125
+ "Ġ =",
1126
+ "Ġ \"",
1127
+ "Ġ A",
1128
+ "Ġ S",
1129
+ "en t",
1130
+ "i l",
1131
+ "Ġt h",
1132
+ "Ġ 1",
1133
+ "s t",
1134
+ "Ġ C",
1135
+ "e l",
1136
+ "o m",
1137
+ "Ġ l",
1138
+ "a m",
1139
+ "Ġ Ċ",
1140
+ "Ġ e",
1141
+ "Ġ n",
1142
+ "Ġ @",
1143
+ "a d",
1144
+ "a c",
1145
+ "Ġw as",
1146
+ "Ġ M",
1147
+ "u r",
1148
+ "ĠT he",
1149
+ "e c",
1150
+ "Ġ on",
1151
+ "l y",
1152
+ "Ġ B",
1153
+ "Ġ I",
1154
+ "Ġ g",
1155
+ "Ġ '",
1156
+ "e t",
1157
+ "o l",
1158
+ "i d",
1159
+ "i v",
1160
+ "i m",
1161
+ "Ġf or",
1162
+ "i r",
1163
+ "- @",
1164
+ "Ġ@ -@",
1165
+ "i g",
1166
+ "o t",
1167
+ "t er",
1168
+ "Ġa s",
1169
+ "Ġ H",
1170
+ "u s",
1171
+ "o w",
1172
+ "Ġs t",
1173
+ "u t",
1174
+ "it h",
1175
+ "a y",
1176
+ "Ġ 2",
1177
+ "Ġ P",
1178
+ "at ion",
1179
+ "v er",
1180
+ "Ġb e",
1181
+ "he r",
1182
+ "Ġth at",
1183
+ "Ġw ith",
1184
+ "Ġ R",
1185
+ "c e",
1186
+ "t h",
1187
+ "Ġ D",
1188
+ "Ġ is",
1189
+ "u n",
1190
+ "e m",
1191
+ "Ġ F",
1192
+ "Ġw h",
1193
+ "u l",
1194
+ "Ġb y",
1195
+ "Ġa l",
1196
+ "c h",
1197
+ "Ġ )",
1198
+ "Ġ (",
1199
+ "Ġ W",
1200
+ "Ġc on",
1201
+ "r a",
1202
+ "Ġ G",
1203
+ "o s",
1204
+ "Ġ L",
1205
+ "Ġ N",
1206
+ "Ġa t",
1207
+ "er s",
1208
+ "c t",
1209
+ "Ġ it",
1210
+ "Ġ1 9",
1211
+ "ro m",
1212
+ "a nd",
1213
+ "Ġa n",
1214
+ "u m",
1215
+ "es t",
1216
+ "Ġ J",
1217
+ "a g",
1218
+ "Ġ he",
1219
+ "0 0",
1220
+ "is t",
1221
+ "a in",
1222
+ "o d",
1223
+ "a v",
1224
+ "r i",
1225
+ "Ġ E",
1226
+ "Ġ O",
1227
+ "Ġf rom",
1228
+ "Ġc om",
1229
+ "Ġh is",
1230
+ "o p",
1231
+ "Ġp ro",
1232
+ "re s",
1233
+ "i es",
1234
+ "i f",
1235
+ "Ġ v",
1236
+ "or t",
1237
+ "er e",
1238
+ "il l",
1239
+ "l d",
1240
+ "Ġd e",
1241
+ "p p",
1242
+ "Ġs u",
1243
+ "o re",
1244
+ "ĠI n",
1245
+ "Ġ r",
1246
+ "Ġs e",
1247
+ "Ġw ere",
1248
+ "e w",
1249
+ "on g",
1250
+ "ig h",
1251
+ "ar d",
1252
+ "at e",
1253
+ "al l",
1254
+ "ar t",
1255
+ "a k",
1256
+ "ic h",
1257
+ "Ġc h",
1258
+ "Ġo r",
1259
+ "a b",
1260
+ "an t",
1261
+ "u d",
1262
+ "o c",
1263
+ "b er",
1264
+ "Ġe x",
1265
+ "g h",
1266
+ "it y",
1267
+ "at ed",
1268
+ "p t",
1269
+ "es s",
1270
+ "e ar",
1271
+ "Ġ K",
1272
+ "Ġp l",
1273
+ "am e",
1274
+ "q u",
1275
+ "iv e",
1276
+ "ro u",
1277
+ "Ġa re",
1278
+ "Ġ â",
1279
+ "Ġs h",
1280
+ "Ġ k",
1281
+ "ac k",
1282
+ "ec t",
1283
+ "Ġâ Ģ",
1284
+ "Ġ U",
1285
+ "Ġh ad",
1286
+ "s e",
1287
+ "Ġwh ich",
1288
+ "re d",
1289
+ "o v",
1290
+ "ĠS t",
1291
+ "as t",
1292
+ "Ġs p",
1293
+ "i an",
1294
+ "Ġ y",
1295
+ "m ent",
1296
+ "Ġ le",
1297
+ "Ġn ot",
1298
+ "g e",
1299
+ "or d",
1300
+ "r it",
1301
+ "i p",
1302
+ "in e",
1303
+ "el l",
1304
+ "al ly",
1305
+ "ou r",
1306
+ "o st",
1307
+ "igh t",
1308
+ "t her",
1309
+ "a p",
1310
+ "Ġ u",
1311
+ "is h",
1312
+ "ĠC h",
1313
+ "ou n",
1314
+ "i a",
1315
+ "Ġ 3",
1316
+ "av e",
1317
+ "ar y",
1318
+ "u st",
1319
+ "o g",
1320
+ "Ġ2 00",
1321
+ "Ġ un",
1322
+ "ou s",
1323
+ "ir st",
1324
+ "Ġ V",
1325
+ "c c",
1326
+ "Ġin c",
1327
+ "Ġ ;",
1328
+ "Ġcom p",
1329
+ "r u",
1330
+ "ion s",
1331
+ "Ġthe ir",
1332
+ "Ġb ut",
1333
+ "id e",
1334
+ "u re",
1335
+ "s o",
1336
+ "Ġcon t",
1337
+ "Ġin t",
1338
+ "f ter",
1339
+ "ic al",
1340
+ "i al",
1341
+ "Ġa r",
1342
+ "Ġf irst",
1343
+ "ou ld",
1344
+ "Ġit s",
1345
+ "he d",
1346
+ "ĠâĢ ĵ",
1347
+ "Ġw he",
1348
+ "w o",
1349
+ "ou t",
1350
+ "u b",
1351
+ "Ġ2 0",
1352
+ "f f",
1353
+ "Ġ :",
1354
+ "u e",
1355
+ "Ġ her",
1356
+ "ow n",
1357
+ "o k",
1358
+ "Ġal so",
1359
+ "Ġc l",
1360
+ "p er",
1361
+ "ig n",
1362
+ "at er",
1363
+ "r an",
1364
+ "or m",
1365
+ "i e",
1366
+ "om e",
1367
+ "or k",
1368
+ "as s",
1369
+ "i re",
1370
+ "e nd",
1371
+ "Ġre s",
1372
+ "Ġa b",
1373
+ "Ġa d",
1374
+ "Ġ us",
1375
+ "r y",
1376
+ "Ġre c",
1377
+ "Ġh ave",
1378
+ "ag e",
1379
+ "ĠH e",
1380
+ "Ġ 4",
1381
+ "Ġ ro",
1382
+ "m er",
1383
+ "Ġon e",
1384
+ "on d",
1385
+ "l ow",
1386
+ "Ġh as",
1387
+ "ĠT h",
1388
+ "d u",
1389
+ "Ġ 5",
1390
+ "Ġp er",
1391
+ "Ġbe en",
1392
+ "im e",
1393
+ "Ġt wo",
1394
+ "en ce",
1395
+ "l and",
1396
+ "Ġ1 8",
1397
+ ". @",
1398
+ "Ġ@ .@",
1399
+ "ul t",
1400
+ "re e",
1401
+ "ou gh",
1402
+ "i le",
1403
+ "Ġwh o",
1404
+ "ĠA l",
1405
+ "Ġs c",
1406
+ "ur ing",
1407
+ "p l",
1408
+ "or y",
1409
+ "it ion",
1410
+ "r ic",
1411
+ "ation s",
1412
+ "Ġd is",
1413
+ "Ġth is",
1414
+ "Ġb ec",
1415
+ "Ġa pp",
1416
+ "i z",
1417
+ "ĠI t",
1418
+ "a re",
1419
+ "ac h",
1420
+ "l ud",
1421
+ "ad e",
1422
+ "Ġpl ay",
1423
+ "Ġ j",
1424
+ "Ġm an",
1425
+ "ac t",
1426
+ "el y",
1427
+ "Ġp art",
1428
+ "Ġd es",
1429
+ "Ġa g",
1430
+ "Ġthe y",
1431
+ "Ġy ear",
1432
+ "oun t",
1433
+ "Ġ20 1",
1434
+ "Ġo ver",
1435
+ "Ġo ther",
1436
+ "ou nd",
1437
+ "Ġa fter",
1438
+ "i b",
1439
+ "o ver",
1440
+ "Ġs er",
1441
+ "Ġ en",
1442
+ "Ġof f",
1443
+ "Ġ im",
1444
+ "ct ion",
1445
+ "Ġ Y",
1446
+ "k e",
1447
+ "it e",
1448
+ ", @",
1449
+ "Ġ@ ,@",
1450
+ "t e",
1451
+ "ur n",
1452
+ "Ġinc lud",
1453
+ "res s",
1454
+ "an ce",
1455
+ "an g",
1456
+ "Ġat t",
1457
+ "ic e",
1458
+ "ac e",
1459
+ "ar k",
1460
+ "Ġo ut",
1461
+ "w n",
1462
+ "p h",
1463
+ "em ber",
1464
+ "Ġp re",
1465
+ "Ġu p",
1466
+ "en s",
1467
+ "m an",
1468
+ "Ġe v",
1469
+ "Ġt ime",
1470
+ "nd er",
1471
+ "rou gh",
1472
+ "c ed",
1473
+ "Ġf in",
1474
+ "Ġint o",
1475
+ "on e",
1476
+ "p ort",
1477
+ "rou nd",
1478
+ "w e",
1479
+ "re n",
1480
+ "l es",
1481
+ "in t",
1482
+ "ĠO n",
1483
+ "v el",
1484
+ "Ġcom m",
1485
+ "Ġs he",
1486
+ "as on",
1487
+ "am p",
1488
+ "Ġt e",
1489
+ "Ġw ould",
1490
+ "w ard",
1491
+ "Ġm ore",
1492
+ "Ġ 6",
1493
+ "i ed",
1494
+ "os e",
1495
+ "ri b",
1496
+ "ĠU n",
1497
+ "Ġal l",
1498
+ "ing s",
1499
+ "ter n",
1500
+ "c es",
1501
+ "ab le",
1502
+ "Ġw e",
1503
+ "it ed",
1504
+ "e ver",
1505
+ "ent s",
1506
+ "Ġh im",
1507
+ "as ed",
1508
+ "or s",
1509
+ "o y",
1510
+ "o od",
1511
+ "Ġc ent",
1512
+ "i x",
1513
+ "as e",
1514
+ "il d",
1515
+ "ĠA n",
1516
+ "Ġ 7",
1517
+ "Ġw ork",
1518
+ "at es",
1519
+ "i ous",
1520
+ "at h",
1521
+ "Ġp o",
1522
+ "ro p",
1523
+ "ol d",
1524
+ "al s",
1525
+ "is s",
1526
+ "e y",
1527
+ "ic t",
1528
+ "Ġf e",
1529
+ "Ġthe m",
1530
+ "g an",
1531
+ "Ġs ec",
1532
+ "Ġb et",
1533
+ "Ġwhe n",
1534
+ "Ġs ong",
1535
+ "Ġre m",
1536
+ "e p",
1537
+ "f orm",
1538
+ "a il",
1539
+ "f er",
1540
+ "Ġe ar",
1541
+ "ub l",
1542
+ "a w",
1543
+ "Ġk n",
1544
+ "ak e",
1545
+ "a us",
1546
+ "Ġm ost",
1547
+ "Ġcon s",
1548
+ "Ġd uring",
1549
+ "ĠA s",
1550
+ "or th",
1551
+ "Ġn ew",
1552
+ "er ed",
1553
+ "il m",
1554
+ "v ed",
1555
+ "at t",
1556
+ "Ġon ly",
1557
+ "Ġ 9",
1558
+ "Ġd ec",
1559
+ "Ġ 8",
1560
+ "ic k",
1561
+ "Ġg ame",
1562
+ "on s",
1563
+ "u g",
1564
+ "Ġt r",
1565
+ "f t",
1566
+ "ot h",
1567
+ "o ok",
1568
+ "ĠM ar",
1569
+ "re at",
1570
+ "w ay",
1571
+ "Ġc an",
1572
+ "ol low",
1573
+ "ou th",
1574
+ "we en",
1575
+ "ĠE n",
1576
+ "Ġ19 9",
1577
+ "ter s",
1578
+ "Ġre l",
1579
+ "in d",
1580
+ "Ġab out",
1581
+ "Ġse ason",
1582
+ "Ġag ain",
1583
+ "r al",
1584
+ "Ġth ree",
1585
+ "ation al",
1586
+ "Ġu nder",
1587
+ "ul ar",
1588
+ "Ġm e",
1589
+ "Ġth an",
1590
+ "ĠC om",
1591
+ "ĠA r",
1592
+ "h ip",
1593
+ "o b",
1594
+ "Ġn e",
1595
+ "Ġbet ween",
1596
+ "Ġf l",
1597
+ "h n",
1598
+ "v e",
1599
+ "Ġch ar",
1600
+ "Ġc ol",
1601
+ "Ġrec ord",
1602
+ "i ew",
1603
+ "r on",
1604
+ "f ore",
1605
+ "Ġth rough",
1606
+ "is ion",
1607
+ "or n",
1608
+ "Ġ 00",
1609
+ "oc k",
1610
+ "Ġ ver",
1611
+ "Ġl ater",
1612
+ "Ġn um",
1613
+ "Ġe nd",
1614
+ "ol og",
1615
+ "am es",
1616
+ "Ġp os",
1617
+ "Ġw rit",
1618
+ "Ġpro du",
1619
+ "Ġwh ile",
1620
+ "Ġa ct",
1621
+ "Ġre le",
1622
+ "Ġf ilm",
1623
+ "is hed",
1624
+ "Ġp r",
1625
+ "an s",
1626
+ "Ġre g",
1627
+ "Ġfor m",
1628
+ "Ġas s",
1629
+ "ĠS e",
1630
+ "ur y",
1631
+ "t ed",
1632
+ "t s",
1633
+ "Ġm ade",
1634
+ "Ġsu b",
1635
+ "Ġp e",
1636
+ "Ġs o",
1637
+ "or ld",
1638
+ "Ġre t",
1639
+ "ĠN ew",
1640
+ "Ġsp ec",
1641
+ "Ġa cc",
1642
+ "Ġ qu",
1643
+ "Ġwhe re",
1644
+ "en er",
1645
+ "Ġm ov",
1646
+ "he s",
1647
+ "mer ic",
1648
+ "at ing",
1649
+ "Ġin ter",
1650
+ "ĠL e",
1651
+ "ĠA meric",
1652
+ "Ġ ra",
1653
+ "Ġs ome",
1654
+ "Ġc o",
1655
+ "Ġl ar",
1656
+ "Ġb u",
1657
+ "Ġde f",
1658
+ "b um",
1659
+ "Ġa c",
1660
+ "Ġm us",
1661
+ "Ġf ollow",
1662
+ "ĠA t",
1663
+ "in s",
1664
+ "iv ed",
1665
+ "if ic",
1666
+ "u al",
1667
+ "Ġa m",
1668
+ "Ġsu ch",
1669
+ "Ġsec ond",
1670
+ "i ke",
1671
+ "Ġf our",
1672
+ "Ġin d",
1673
+ "an n",
1674
+ "he n",
1675
+ "Ġus ed",
1676
+ "ĠR e",
1677
+ "ic s",
1678
+ "le ct",
1679
+ "Ġd ay",
1680
+ "i el",
1681
+ "il y",
1682
+ "ĠTh is",
1683
+ "Ġ 0",
1684
+ "Ġp ubl",
1685
+ "Ġc all",
1686
+ "ĠJ o",
1687
+ "l l",
1688
+ "Ġal bum",
1689
+ "Ġ00 0",
1690
+ "ran s",
1691
+ "Ġd o",
1692
+ "an y",
1693
+ "Ġbe fore",
1694
+ "ro s",
1695
+ "ĠS h",
1696
+ "Ġs y",
1697
+ "a id",
1698
+ "ĠEn g",
1699
+ "Ġbe ing",
1700
+ "Ġ1 0",
1701
+ "u c",
1702
+ "Ġe p",
1703
+ "Ġsu pp",
1704
+ "Ġthe re",
1705
+ "Ġyear s",
1706
+ "ar s",
1707
+ "ow ever",
1708
+ "Ġ ent",
1709
+ "if e",
1710
+ "Ġh igh",
1711
+ "Ġf ound",
1712
+ "ir d",
1713
+ "Ġn o",
1714
+ "Ġs et",
1715
+ "in es",
1716
+ "iv er",
1717
+ "i o",
1718
+ "ot her",
1719
+ "j ect",
1720
+ "Ġs ur",
1721
+ "a j",
1722
+ "t en",
1723
+ "Ġt ra",
1724
+ "Ġ1 2",
1725
+ "is ed",
1726
+ "it ies",
1727
+ "vel op",
1728
+ "Ġb l",
1729
+ "al e",
1730
+ "Ġser ies",
1731
+ "Ġl oc",
1732
+ "Ġnum ber",
1733
+ "Ġp res",
1734
+ "an e",
1735
+ "aus e",
1736
+ "od e",
1737
+ "e k",
1738
+ "t on",
1739
+ "ĠS c",
1740
+ "i er",
1741
+ "is e",
1742
+ "Ġse ver",
1743
+ "in ce",
1744
+ "Ġb oth",
1745
+ "an k",
1746
+ "ro w",
1747
+ "ire ct",
1748
+ "s on",
1749
+ "Ġthe n",
1750
+ "ĠB rit",
1751
+ "i et",
1752
+ "Ġ1 6",
1753
+ "Ġep is",
1754
+ "Ġinclud ing",
1755
+ "it s",
1756
+ "ig in",
1757
+ "p r",
1758
+ "Ġ /",
1759
+ "Ġagain st",
1760
+ "Ġw ell",
1761
+ "Ġbec ame",
1762
+ "Ġex p",
1763
+ "Ġkn own",
1764
+ "Ġt rans",
1765
+ "Ġchar ac",
1766
+ "ĠâĢ Ķ",
1767
+ "r am",
1768
+ "Ġb ack",
1769
+ "Ġad d",
1770
+ "Ġp op",
1771
+ "Ġg o",
1772
+ "ur ch",
1773
+ "Ġdes c",
1774
+ "Ġs ing",
1775
+ "iel d",
1776
+ "Ġper form",
1777
+ "ain ed",
1778
+ "Ġre ce",
1779
+ "id ent",
1780
+ "Ġe m",
1781
+ "er t",
1782
+ "u res",
1783
+ "Ġin v",
1784
+ "Ġde p",
1785
+ "Ġ19 8",
1786
+ "a ir",
1787
+ "er n",
1788
+ "at her",
1789
+ "f ul",
1790
+ "Ġ Z",
1791
+ "Ġm on",
1792
+ "Ġman y",
1793
+ "Ġm ain",
1794
+ "Ġst ud",
1795
+ "Ġl ong",
1796
+ "in n",
1797
+ "th ough",
1798
+ "u p",
1799
+ "o ol",
1800
+ "ĠUn ited",
1801
+ "l ed",
1802
+ "em ent",
1803
+ "Ġ1 5",
1804
+ "ow er",
1805
+ "ĠJo hn",
1806
+ "Ġo p",
1807
+ "Ġ1 1",
1808
+ "in ed",
1809
+ "Ġm et",
1810
+ "o ber",
1811
+ "le y",
1812
+ "Ġ1 7",
1813
+ "Ġcent ury",
1814
+ "Ġte am",
1815
+ "Ġ est",
1816
+ "ĠA fter",
1817
+ "y l",
1818
+ "Ġm in",
1819
+ "u ch",
1820
+ "ut e",
1821
+ "Ġde velop",
1822
+ "ĠS he",
1823
+ "i am",
1824
+ "Ġsh ow",
1825
+ "el f",
1826
+ "Ġre p",
1827
+ "Ġcon c",
1828
+ "at ive",
1829
+ "Ġc re",
1830
+ "over n",
1831
+ "a red",
1832
+ "Ġ19 4",
1833
+ "Ġor igin",
1834
+ "Ġs m",
1835
+ "iv ers",
1836
+ "a z",
1837
+ "Ġle ad",
1838
+ "Ġsever al",
1839
+ "a h",
1840
+ "Ġo b",
1841
+ "Ġre v",
1842
+ "Ġm ill",
1843
+ "er m",
1844
+ "u ally",
1845
+ "o ot",
1846
+ "Ġbe gan"
1847
+ ]
1848
+ }
1849
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }