Hugging Face's logo

hf-internal-testing
/
tiny-random-MptForQuestionAnswering

Question Answering
Transformers
PyTorch
mpt
text-generation-inference
Model card Files
xet
Community
6
hf-transformers-bot commited on
Commit
6ee4657
路
1 Parent(s): a0b8732

Upload tiny models for MptForQuestionAnswering

Browse files
Files changed (5) hide show
  1. config.json +121 -0
  2. pytorch_model.bin +3 -0
  3. special_tokens_map.json +5 -0
  4. tokenizer.json +1849 -0
  5. tokenizer_config.json +9 -0
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "MptForQuestionAnswering"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "attn_config": {
8
+ "_name_or_path": "",
9
+ "add_cross_attention": false,
10
+ "alibi": true,
11
+ "alibi_bias_max": 8,
12
+ "architectures": null,
13
+ "attn_impl": "torch",
14
+ "attn_pdrop": 0,
15
+ "attn_type": "multihead_attention",
16
+ "attn_uses_sequence_id": false,
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "clip_qkv": null,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": null,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "is_decoder": false,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "min_length": 0,
46
+ "model_type": "",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_return_sequences": 1,
51
+ "output_attentions": false,
52
+ "output_hidden_states": false,
53
+ "output_scores": false,
54
+ "pad_token_id": null,
55
+ "prefix": null,
56
+ "prefix_lm": false,
57
+ "problem_type": null,
58
+ "pruned_heads": {},
59
+ "qk_ln": false,
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "sep_token_id": null,
65
+ "softmax_scale": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.32.0.dev0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false
80
+ },
81
+ "bos_token_id": 0,
82
+ "d_model": 32,
83
+ "dtype": "float32",
84
+ "emb_pdrop": 0.0,
85
+ "embedding_fraction": 1.0,
86
+ "eos_token_id": 0,
87
+ "expansion_ratio": 4,
88
+ "gradient_checkpointing": false,
89
+ "hidden_dropout": 0.1,
90
+ "id2label": {
91
+ "0": "LABEL_0",
92
+ "1": "LABEL_1",
93
+ "2": "LABEL_2"
94
+ },
95
+ "init_device": "cpu",
96
+ "initializer_range": 0.02,
97
+ "label2id": {
98
+ "LABEL_0": 0,
99
+ "LABEL_1": 1,
100
+ "LABEL_2": 2
101
+ },
102
+ "layer_norm_epsilon": 1e-05,
103
+ "learned_pos_emb": true,
104
+ "logit_scale": null,
105
+ "max_seq_len": 2048,
106
+ "model_type": "mpt",
107
+ "n_heads": 4,
108
+ "n_layers": 5,
109
+ "n_positions": 512,
110
+ "no_bias": true,
111
+ "norm_type": "low_precision_layernorm",
112
+ "pad_token_id": 1023,
113
+ "resid_pdrop": 0.0,
114
+ "seq_length": 7,
115
+ "torch_dtype": "float32",
116
+ "transformers_version": null,
117
+ "type_vocab_size": 16,
118
+ "use_cache": true,
119
+ "verbose": 0,
120
+ "vocab_size": 1024
121
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdec6e599a681cc3fac68514c97e0320580c97f68ab05d485e3cc38a16ab1d75
3
+ size 388951
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
+ "隆": 96,
152
+ "垄": 97,
153
+ "拢": 98,
154
+ "陇": 99,
155
+ "楼": 100,
156
+ "娄": 101,
157
+ "搂": 102,
158
+ "篓": 103,
159
+ "漏": 104,
160
+ "陋": 105,
161
+ "芦": 106,
162
+ "卢": 107,
163
+ "庐": 108,
164
+ "炉": 109,
165
+ "掳": 110,
166
+ "卤": 111,
167
+ "虏": 112,
168
+ "鲁": 113,
169
+ "麓": 114,
170
+ "碌": 115,
171
+ "露": 116,
172
+ "路": 117,
173
+ "赂": 118,
174
+ "鹿": 119,
175
+ "潞": 120,
176
+ "禄": 121,
177
+ "录": 122,
178
+ "陆": 123,
179
+ "戮": 124,
180
+ "驴": 125,
181
+ "脌": 126,
182
+ "脕": 127,
183
+ "脗": 128,
184
+ "脙": 129,
185
+ "脛": 130,
186
+ "脜": 131,
187
+ "脝": 132,
188
+ "脟": 133,
189
+ "脠": 134,
190
+ "脡": 135,
191
+ "脢": 136,
192
+ "脣": 137,
193
+ "脤": 138,
194
+ "脥": 139,
195
+ "脦": 140,
196
+ "脧": 141,
197
+ "脨": 142,
198
+ "脩": 143,
199
+ "脪": 144,
200
+ "脫": 145,
201
+ "脭": 146,
202
+ "脮": 147,
203
+ "脰": 148,
204
+ "脳": 149,
205
+ "脴": 150,
206
+ "脵": 151,
207
+ "脷": 152,
208
+ "脹": 153,
209
+ "脺": 154,
210
+ "脻": 155,
211
+ "脼": 156,
212
+ "脽": 157,
213
+ "脿": 158,
214
+ "谩": 159,
215
+ "芒": 160,
216
+ "茫": 161,
217
+ "盲": 162,
218
+ "氓": 163,
219
+ "忙": 164,
220
+ "莽": 165,
221
+ "猫": 166,
222
+ "茅": 167,
223
+ "锚": 168,
224
+ "毛": 169,
225
+ "矛": 170,
226
+ "铆": 171,
227
+ "卯": 172,
228
+ "茂": 173,
229
+ "冒": 174,
230
+ "帽": 175,
231
+ "貌": 176,
232
+ "贸": 177,
233
+ "么": 178,
234
+ "玫": 179,
235
+ "枚": 180,
236
+ "梅": 181,
237
+ "酶": 182,
238
+ "霉": 183,
239
+ "煤": 184,
240
+ "没": 185,
241
+ "眉": 186,
242
+ "媒": 187,
243
+ "镁": 188,
244
+ "每": 189,
245
+ "膧": 190,
246
+ "膩": 191,
247
+ "膫": 192,
248
+ "膬": 193,
249
+ "膭": 194,
250
+ "膮": 195,
251
+ "膯": 196,
252
+ "膰": 197,
253
+ "膱": 198,
254
+ "膲": 199,
255
+ "膴": 200,
256
+ "膵": 201,
257
+ "膶": 202,
258
+ "膷": 203,
259
+ "膸": 204,
260
+ "膹": 205,
261
+ "膼": 206,
262
+ "膽": 207,
263
+ "膾": 208,
264
+ "膿": 209,
265
+ "臄": 210,
266
+ "臅": 211,
267
+ "臇": 212,
268
+ "臈": 213,
269
+ "臉": 214,
270
+ "臋": 215,
271
+ "臍": 216,
272
+ "臎": 217,
273
+ "臏": 218,
274
+ "臐": 219,
275
+ "臑": 220,
276
+ "臒": 221,
277
+ "臓": 222,
278
+ "摹": 223,
279
+ "蘑": 224,
280
+ "模": 225,
281
+ "膜": 226,
282
+ "磨": 227,
283
+ "摩": 228,
284
+ "魔": 229,
285
+ "抹": 230,
286
+ "末": 231,
287
+ "莫": 232,
288
+ "墨": 233,
289
+ "默": 234,
290
+ "沫": 235,
291
+ "漠": 236,
292
+ "寞": 237,
293
+ "陌": 238,
294
+ "谋": 239,
295
+ "牟": 240,
296
+ "某": 241,
297
+ "拇": 242,
298
+ "牡": 243,
299
+ "亩": 244,
300
+ "姆": 245,
301
+ "母": 246,
302
+ "墓": 247,
303
+ "暮": 248,
304
+ "幕": 249,
305
+ "募": 250,
306
+ "慕": 251,
307
+ "木": 252,
308
+ "目": 253,
309
+ "艀": 254,
310
+ "艁": 255,
311
+ "艂": 256,
312
+ "艃": 257,
313
+ "臓t": 258,
314
+ "he": 259,
315
+ "臓a": 260,
316
+ "in": 261,
317
+ "臓the": 262,
318
+ "er": 263,
319
+ "on": 264,
320
+ "臓,": 265,
321
+ "re": 266,
322
+ "臓s": 267,
323
+ "ed": 268,
324
+ "臓o": 269,
325
+ "臓w": 270,
326
+ "nd": 271,
327
+ "at": 272,
328
+ "臓.": 273,
329
+ "or": 274,
330
+ "it": 275,
331
+ "臓c": 276,
332
+ "en": 277,
333
+ "臓f": 278,
334
+ "is": 279,
335
+ "es": 280,
336
+ "ar": 281,
337
+ "臓of": 282,
338
+ "臓b": 283,
339
+ "an": 284,
340
+ "臓in": 285,
341
+ "al": 286,
342
+ "ing": 287,
343
+ "臓p": 288,
344
+ "臓and": 289,
345
+ "as": 290,
346
+ "臓to": 291,
347
+ "ro": 292,
348
+ "ic": 293,
349
+ "臓m": 294,
350
+ "臓d": 295,
351
+ "臓h": 296,
352
+ "ion": 297,
353
+ "le": 298,
354
+ "ou": 299,
355
+ "臓T": 300,
356
+ "臓re": 301,
357
+ "臓=": 302,
358
+ "臓\"": 303,
359
+ "臓A": 304,
360
+ "臓S": 305,
361
+ "ent": 306,
362
+ "il": 307,
363
+ "臓th": 308,
364
+ "臓1": 309,
365
+ "st": 310,
366
+ "臓C": 311,
367
+ "el": 312,
368
+ "om": 313,
369
+ "臓l": 314,
370
+ "am": 315,
371
+ "臓膴": 316,
372
+ "臓e": 317,
373
+ "臓n": 318,
374
+ "臓@": 319,
375
+ "ad": 320,
376
+ "ac": 321,
377
+ "臓was": 322,
378
+ "臓M": 323,
379
+ "ur": 324,
380
+ "臓The": 325,
381
+ "ec": 326,
382
+ "臓on": 327,
383
+ "ly": 328,
384
+ "臓B": 329,
385
+ "臓I": 330,
386
+ "臓g": 331,
387
+ "臓'": 332,
388
+ "et": 333,
389
+ "ol": 334,
390
+ "id": 335,
391
+ "iv": 336,
392
+ "im": 337,
393
+ "臓for": 338,
394
+ "ir": 339,
395
+ "-@": 340,
396
+ "臓@-@": 341,
397
+ "ig": 342,
398
+ "ot": 343,
399
+ "ter": 344,
400
+ "臓as": 345,
401
+ "臓H": 346,
402
+ "us": 347,
403
+ "ow": 348,
404
+ "臓st": 349,
405
+ "ut": 350,
406
+ "ith": 351,
407
+ "ay": 352,
408
+ "臓2": 353,
409
+ "臓P": 354,
410
+ "ation": 355,
411
+ "ver": 356,
412
+ "臓be": 357,
413
+ "her": 358,
414
+ "臓that": 359,
415
+ "臓with": 360,
416
+ "臓R": 361,
417
+ "ce": 362,
418
+ "th": 363,
419
+ "臓D": 364,
420
+ "臓is": 365,
421
+ "un": 366,
422
+ "em": 367,
423
+ "臓F": 368,
424
+ "臓wh": 369,
425
+ "ul": 370,
426
+ "臓by": 371,
427
+ "臓al": 372,
428
+ "ch": 373,
429
+ "臓)": 374,
430
+ "臓(": 375,
431
+ "臓W": 376,
432
+ "臓con": 377,
433
+ "ra": 378,
434
+ "臓G": 379,
435
+ "os": 380,
436
+ "臓L": 381,
437
+ "臓N": 382,
438
+ "臓at": 383,
439
+ "ers": 384,
440
+ "ct": 385,
441
+ "臓it": 386,
442
+ "臓19": 387,
443
+ "rom": 388,
444
+ "and": 389,
445
+ "臓an": 390,
446
+ "um": 391,
447
+ "est": 392,
448
+ "臓J": 393,
449
+ "ag": 394,
450
+ "臓he": 395,
451
+ "00": 396,
452
+ "ist": 397,
453
+ "ain": 398,
454
+ "od": 399,
455
+ "av": 400,
456
+ "ri": 401,
457
+ "臓E": 402,
458
+ "臓O": 403,
459
+ "臓from": 404,
460
+ "臓com": 405,
461
+ "臓his": 406,
462
+ "op": 407,
463
+ "臓pro": 408,
464
+ "res": 409,
465
+ "ies": 410,
466
+ "if": 411,
467
+ "臓v": 412,
468
+ "ort": 413,
469
+ "ere": 414,
470
+ "ill": 415,
471
+ "ld": 416,
472
+ "臓de": 417,
473
+ "pp": 418,
474
+ "臓su": 419,
475
+ "ore": 420,
476
+ "臓In": 421,
477
+ "臓r": 422,
478
+ "臓se": 423,
479
+ "臓were": 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
+ "臓ch": 434,
490
+ "臓or": 435,
491
+ "ab": 436,
492
+ "ant": 437,
493
+ "ud": 438,
494
+ "oc": 439,
495
+ "ber": 440,
496
+ "臓ex": 441,
497
+ "gh": 442,
498
+ "ity": 443,
499
+ "ated": 444,
500
+ "pt": 445,
501
+ "ess": 446,
502
+ "ear": 447,
503
+ "臓K": 448,
504
+ "臓pl": 449,
505
+ "ame": 450,
506
+ "qu": 451,
507
+ "ive": 452,
508
+ "rou": 453,
509
+ "臓are": 454,
510
+ "臓芒": 455,
511
+ "臓sh": 456,
512
+ "臓k": 457,
513
+ "ack": 458,
514
+ "ect": 459,
515
+ "臓芒蘑": 460,
516
+ "臓U": 461,
517
+ "臓had": 462,
518
+ "se": 463,
519
+ "臓which": 464,
520
+ "red": 465,
521
+ "ov": 466,
522
+ "臓St": 467,
523
+ "ast": 468,
524
+ "臓sp": 469,
525
+ "ian": 470,
526
+ "臓y": 471,
527
+ "ment": 472,
528
+ "臓le": 473,
529
+ "臓not": 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
+ "臓u": 487,
543
+ "ish": 488,
544
+ "臓Ch": 489,
545
+ "oun": 490,
546
+ "ia": 491,
547
+ "臓3": 492,
548
+ "ave": 493,
549
+ "ary": 494,
550
+ "ust": 495,
551
+ "og": 496,
552
+ "臓200": 497,
553
+ "臓un": 498,
554
+ "ous": 499,
555
+ "irst": 500,
556
+ "臓V": 501,
557
+ "cc": 502,
558
+ "臓inc": 503,
559
+ "臓;": 504,
560
+ "臓comp": 505,
561
+ "ru": 506,
562
+ "ions": 507,
563
+ "臓their": 508,
564
+ "臓but": 509,
565
+ "ide": 510,
566
+ "ure": 511,
567
+ "so": 512,
568
+ "臓cont": 513,
569
+ "臓int": 514,
570
+ "fter": 515,
571
+ "ical": 516,
572
+ "ial": 517,
573
+ "臓ar": 518,
574
+ "臓first": 519,
575
+ "ould": 520,
576
+ "臓its": 521,
577
+ "hed": 522,
578
+ "臓芒蘑牡": 523,
579
+ "臓whe": 524,
580
+ "wo": 525,
581
+ "out": 526,
582
+ "ub": 527,
583
+ "臓20": 528,
584
+ "ff": 529,
585
+ "臓:": 530,
586
+ "ue": 531,
587
+ "臓her": 532,
588
+ "own": 533,
589
+ "ok": 534,
590
+ "臓also": 535,
591
+ "臓cl": 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
+ "臓res": 548,
604
+ "臓ab": 549,
605
+ "臓ad": 550,
606
+ "臓us": 551,
607
+ "ry": 552,
608
+ "臓rec": 553,
609
+ "臓have": 554,
610
+ "age": 555,
611
+ "臓He": 556,
612
+ "臓4": 557,
613
+ "臓ro": 558,
614
+ "mer": 559,
615
+ "臓one": 560,
616
+ "ond": 561,
617
+ "low": 562,
618
+ "臓has": 563,
619
+ "臓Th": 564,
620
+ "du": 565,
621
+ "臓5": 566,
622
+ "臓per": 567,
623
+ "臓been": 568,
624
+ "ime": 569,
625
+ "臓two": 570,
626
+ "ence": 571,
627
+ "land": 572,
628
+ "臓18": 573,
629
+ ".@": 574,
630
+ "臓@.@": 575,
631
+ "ult": 576,
632
+ "ree": 577,
633
+ "ough": 578,
634
+ "ile": 579,
635
+ "臓who": 580,
636
+ "臓Al": 581,
637
+ "臓sc": 582,
638
+ "uring": 583,
639
+ "pl": 584,
640
+ "ory": 585,
641
+ "ition": 586,
642
+ "ric": 587,
643
+ "ations": 588,
644
+ "臓dis": 589,
645
+ "臓this": 590,
646
+ "臓bec": 591,
647
+ "臓app": 592,
648
+ "iz": 593,
649
+ "臓It": 594,
650
+ "are": 595,
651
+ "ach": 596,
652
+ "lud": 597,
653
+ "ade": 598,
654
+ "臓play": 599,
655
+ "臓j": 600,
656
+ "臓man": 601,
657
+ "act": 602,
658
+ "ely": 603,
659
+ "臓part": 604,
660
+ "臓des": 605,
661
+ "臓ag": 606,
662
+ "臓they": 607,
663
+ "臓year": 608,
664
+ "ount": 609,
665
+ "臓201": 610,
666
+ "臓over": 611,
667
+ "臓other": 612,
668
+ "ound": 613,
669
+ "臓after": 614,
670
+ "ib": 615,
671
+ "over": 616,
672
+ "臓ser": 617,
673
+ "臓en": 618,
674
+ "臓off": 619,
675
+ "臓im": 620,
676
+ "ction": 621,
677
+ "臓Y": 622,
678
+ "ke": 623,
679
+ "ite": 624,
680
+ ",@": 625,
681
+ "臓@,@": 626,
682
+ "te": 627,
683
+ "urn": 628,
684
+ "臓includ": 629,
685
+ "ress": 630,
686
+ "ance": 631,
687
+ "ang": 632,
688
+ "臓att": 633,
689
+ "ice": 634,
690
+ "ace": 635,
691
+ "ark": 636,
692
+ "臓out": 637,
693
+ "wn": 638,
694
+ "ph": 639,
695
+ "ember": 640,
696
+ "臓pre": 641,
697
+ "臓up": 642,
698
+ "ens": 643,
699
+ "man": 644,
700
+ "臓ev": 645,
701
+ "臓time": 646,
702
+ "nder": 647,
703
+ "rough": 648,
704
+ "ced": 649,
705
+ "臓fin": 650,
706
+ "臓into": 651,
707
+ "one": 652,
708
+ "port": 653,
709
+ "round": 654,
710
+ "we": 655,
711
+ "ren": 656,
712
+ "les": 657,
713
+ "int": 658,
714
+ "臓On": 659,
715
+ "vel": 660,
716
+ "臓comm": 661,
717
+ "臓she": 662,
718
+ "ason": 663,
719
+ "amp": 664,
720
+ "臓te": 665,
721
+ "臓would": 666,
722
+ "ward": 667,
723
+ "臓more": 668,
724
+ "臓6": 669,
725
+ "ied": 670,
726
+ "ose": 671,
727
+ "rib": 672,
728
+ "臓Un": 673,
729
+ "臓all": 674,
730
+ "ings": 675,
731
+ "tern": 676,
732
+ "ces": 677,
733
+ "able": 678,
734
+ "臓we": 679,
735
+ "ited": 680,
736
+ "ever": 681,
737
+ "ents": 682,
738
+ "臓him": 683,
739
+ "ased": 684,
740
+ "ors": 685,
741
+ "oy": 686,
742
+ "ood": 687,
743
+ "臓cent": 688,
744
+ "ix": 689,
745
+ "ase": 690,
746
+ "ild": 691,
747
+ "臓An": 692,
748
+ "臓7": 693,
749
+ "臓work": 694,
750
+ "ates": 695,
751
+ "ious": 696,
752
+ "ath": 697,
753
+ "臓po": 698,
754
+ "rop": 699,
755
+ "old": 700,
756
+ "als": 701,
757
+ "iss": 702,
758
+ "ey": 703,
759
+ "ict": 704,
760
+ "臓fe": 705,
761
+ "臓them": 706,
762
+ "gan": 707,
763
+ "臓sec": 708,
764
+ "臓bet": 709,
765
+ "臓when": 710,
766
+ "臓song": 711,
767
+ "臓rem": 712,
768
+ "ep": 713,
769
+ "form": 714,
770
+ "ail": 715,
771
+ "fer": 716,
772
+ "臓ear": 717,
773
+ "ubl": 718,
774
+ "aw": 719,
775
+ "臓kn": 720,
776
+ "ake": 721,
777
+ "aus": 722,
778
+ "臓most": 723,
779
+ "臓cons": 724,
780
+ "臓during": 725,
781
+ "臓As": 726,
782
+ "orth": 727,
783
+ "臓new": 728,
784
+ "ered": 729,
785
+ "ilm": 730,
786
+ "ved": 731,
787
+ "att": 732,
788
+ "臓only": 733,
789
+ "臓9": 734,
790
+ "臓dec": 735,
791
+ "臓8": 736,
792
+ "ick": 737,
793
+ "臓game": 738,
794
+ "ons": 739,
795
+ "ug": 740,
796
+ "臓tr": 741,
797
+ "ft": 742,
798
+ "oth": 743,
799
+ "ook": 744,
800
+ "臓Mar": 745,
801
+ "reat": 746,
802
+ "way": 747,
803
+ "臓can": 748,
804
+ "ollow": 749,
805
+ "outh": 750,
806
+ "ween": 751,
807
+ "臓En": 752,
808
+ "臓199": 753,
809
+ "ters": 754,
810
+ "臓rel": 755,
811
+ "ind": 756,
812
+ "臓about": 757,
813
+ "臓season": 758,
814
+ "臓again": 759,
815
+ "ral": 760,
816
+ "臓three": 761,
817
+ "ational": 762,
818
+ "臓under": 763,
819
+ "ular": 764,
820
+ "臓me": 765,
821
+ "臓than": 766,
822
+ "臓Com": 767,
823
+ "臓Ar": 768,
824
+ "hip": 769,
825
+ "ob": 770,
826
+ "臓ne": 771,
827
+ "臓between": 772,
828
+ "臓fl": 773,
829
+ "hn": 774,
830
+ "ve": 775,
831
+ "臓char": 776,
832
+ "臓col": 777,
833
+ "臓record": 778,
834
+ "iew": 779,
835
+ "ron": 780,
836
+ "fore": 781,
837
+ "臓through": 782,
838
+ "ision": 783,
839
+ "orn": 784,
840
+ "臓00": 785,
841
+ "ock": 786,
842
+ "臓ver": 787,
843
+ "臓later": 788,
844
+ "臓num": 789,
845
+ "臓end": 790,
846
+ "olog": 791,
847
+ "ames": 792,
848
+ "臓pos": 793,
849
+ "臓writ": 794,
850
+ "臓produ": 795,
851
+ "臓while": 796,
852
+ "臓act": 797,
853
+ "臓rele": 798,
854
+ "臓film": 799,
855
+ "ished": 800,
856
+ "臓pr": 801,
857
+ "ans": 802,
858
+ "臓reg": 803,
859
+ "臓form": 804,
860
+ "臓ass": 805,
861
+ "臓Se": 806,
862
+ "ury": 807,
863
+ "ted": 808,
864
+ "ts": 809,
865
+ "臓made": 810,
866
+ "臓sub": 811,
867
+ "臓pe": 812,
868
+ "臓so": 813,
869
+ "orld": 814,
870
+ "臓ret": 815,
871
+ "臓New": 816,
872
+ "臓spec": 817,
873
+ "臓acc": 818,
874
+ "臓qu": 819,
875
+ "臓where": 820,
876
+ "ener": 821,
877
+ "臓mov": 822,
878
+ "hes": 823,
879
+ "meric": 824,
880
+ "ating": 825,
881
+ "臓inter": 826,
882
+ "臓Le": 827,
883
+ "臓Americ": 828,
884
+ "臓ra": 829,
885
+ "臓some": 830,
886
+ "臓co": 831,
887
+ "臓lar": 832,
888
+ "臓bu": 833,
889
+ "臓def": 834,
890
+ "bum": 835,
891
+ "臓ac": 836,
892
+ "臓mus": 837,
893
+ "臓follow": 838,
894
+ "臓At": 839,
895
+ "ins": 840,
896
+ "ived": 841,
897
+ "ific": 842,
898
+ "ual": 843,
899
+ "臓am": 844,
900
+ "臓such": 845,
901
+ "臓second": 846,
902
+ "ike": 847,
903
+ "臓four": 848,
904
+ "臓ind": 849,
905
+ "ann": 850,
906
+ "hen": 851,
907
+ "臓used": 852,
908
+ "臓Re": 853,
909
+ "ics": 854,
910
+ "lect": 855,
911
+ "臓day": 856,
912
+ "iel": 857,
913
+ "ily": 858,
914
+ "臓This": 859,
915
+ "臓0": 860,
916
+ "臓publ": 861,
917
+ "臓call": 862,
918
+ "臓Jo": 863,
919
+ "ll": 864,
920
+ "臓album": 865,
921
+ "臓000": 866,
922
+ "rans": 867,
923
+ "臓do": 868,
924
+ "any": 869,
925
+ "臓before": 870,
926
+ "ros": 871,
927
+ "臓Sh": 872,
928
+ "臓sy": 873,
929
+ "aid": 874,
930
+ "臓Eng": 875,
931
+ "臓being": 876,
932
+ "臓10": 877,
933
+ "uc": 878,
934
+ "臓ep": 879,
935
+ "臓supp": 880,
936
+ "臓there": 881,
937
+ "臓years": 882,
938
+ "ars": 883,
939
+ "owever": 884,
940
+ "臓ent": 885,
941
+ "ife": 886,
942
+ "臓high": 887,
943
+ "臓found": 888,
944
+ "ird": 889,
945
+ "臓no": 890,
946
+ "臓set": 891,
947
+ "ines": 892,
948
+ "iver": 893,
949
+ "io": 894,
950
+ "other": 895,
951
+ "ject": 896,
952
+ "臓sur": 897,
953
+ "aj": 898,
954
+ "ten": 899,
955
+ "臓tra": 900,
956
+ "臓12": 901,
957
+ "ised": 902,
958
+ "ities": 903,
959
+ "velop": 904,
960
+ "臓bl": 905,
961
+ "ale": 906,
962
+ "臓series": 907,
963
+ "臓loc": 908,
964
+ "臓number": 909,
965
+ "臓pres": 910,
966
+ "ane": 911,
967
+ "ause": 912,
968
+ "ode": 913,
969
+ "ek": 914,
970
+ "ton": 915,
971
+ "臓Sc": 916,
972
+ "ier": 917,
973
+ "ise": 918,
974
+ "臓sever": 919,
975
+ "ince": 920,
976
+ "臓both": 921,
977
+ "ank": 922,
978
+ "row": 923,
979
+ "irect": 924,
980
+ "son": 925,
981
+ "臓then": 926,
982
+ "臓Brit": 927,
983
+ "iet": 928,
984
+ "臓16": 929,
985
+ "臓epis": 930,
986
+ "臓including": 931,
987
+ "its": 932,
988
+ "igin": 933,
989
+ "pr": 934,
990
+ "臓/": 935,
991
+ "臓against": 936,
992
+ "臓well": 937,
993
+ "臓became": 938,
994
+ "臓exp": 939,
995
+ "臓known": 940,
996
+ "臓trans": 941,
997
+ "臓charac": 942,
998
+ "臓芒蘑亩": 943,
999
+ "ram": 944,
1000
+ "臓back": 945,
1001
+ "臓add": 946,
1002
+ "臓pop": 947,
1003
+ "臓go": 948,
1004
+ "urch": 949,
1005
+ "臓desc": 950,
1006
+ "臓sing": 951,
1007
+ "ield": 952,
1008
+ "臓perform": 953,
1009
+ "ained": 954,
1010
+ "臓rece": 955,
1011
+ "ident": 956,
1012
+ "臓em": 957,
1013
+ "ert": 958,
1014
+ "ures": 959,
1015
+ "臓inv": 960,
1016
+ "臓dep": 961,
1017
+ "臓198": 962,
1018
+ "air": 963,
1019
+ "ern": 964,
1020
+ "ather": 965,
1021
+ "ful": 966,
1022
+ "臓Z": 967,
1023
+ "臓mon": 968,
1024
+ "臓many": 969,
1025
+ "臓main": 970,
1026
+ "臓stud": 971,
1027
+ "臓long": 972,
1028
+ "inn": 973,
1029
+ "though": 974,
1030
+ "up": 975,
1031
+ "ool": 976,
1032
+ "臓United": 977,
1033
+ "led": 978,
1034
+ "ement": 979,
1035
+ "臓15": 980,
1036
+ "ower": 981,
1037
+ "臓John": 982,
1038
+ "臓op": 983,
1039
+ "臓11": 984,
1040
+ "ined": 985,
1041
+ "臓met": 986,
1042
+ "ober": 987,
1043
+ "ley": 988,
1044
+ "臓17": 989,
1045
+ "臓century": 990,
1046
+ "臓team": 991,
1047
+ "臓est": 992,
1048
+ "臓After": 993,
1049
+ "yl": 994,
1050
+ "臓min": 995,
1051
+ "uch": 996,
1052
+ "ute": 997,
1053
+ "臓develop": 998,
1054
+ "臓She": 999,
1055
+ "iam": 1000,
1056
+ "臓show": 1001,
1057
+ "elf": 1002,
1058
+ "臓rep": 1003,
1059
+ "臓conc": 1004,
1060
+ "ative": 1005,
1061
+ "臓cre": 1006,
1062
+ "overn": 1007,
1063
+ "ared": 1008,
1064
+ "臓194": 1009,
1065
+ "臓origin": 1010,
1066
+ "臓sm": 1011,
1067
+ "ivers": 1012,
1068
+ "az": 1013,
1069
+ "臓lead": 1014,
1070
+ "臓several": 1015,
1071
+ "ah": 1016,
1072
+ "臓ob": 1017,
1073
+ "臓rev": 1018,
1074
+ "臓mill": 1019,
1075
+ "erm": 1020,
1076
+ "ually": 1021,
1077
+ "oot": 1022,
1078
+ "臓began": 1023
1079
+ },
1080
+ "merges": [
1081
+ "臓 t",
1082
+ "h e",
1083
+ "臓 a",
1084
+ "i n",
1085
+ "臓t he",
1086
+ "e r",
1087
+ "o n",
1088
+ "臓 ,",
1089
+ "r e",
1090
+ "臓 s",
1091
+ "e d",
1092
+ "臓 o",
1093
+ "臓 w",
1094
+ "n d",
1095
+ "a t",
1096
+ "臓 .",
1097
+ "o r",
1098
+ "i t",
1099
+ "臓 c",
1100
+ "e n",
1101
+ "臓 f",
1102
+ "i s",
1103
+ "e s",
1104
+ "a r",
1105
+ "臓o f",
1106
+ "臓 b",
1107
+ "a n",
1108
+ "臓 in",
1109
+ "a l",
1110
+ "in g",
1111
+ "臓 p",
1112
+ "臓a nd",
1113
+ "a s",
1114
+ "臓t o",
1115
+ "r o",
1116
+ "i c",
1117
+ "臓 m",
1118
+ "臓 d",
1119
+ "臓 h",
1120
+ "i on",
1121
+ "l e",
1122
+ "o u",
1123
+ "臓 T",
1124
+ "臓 re",
1125
+ "臓 =",
1126
+ "臓 \"",
1127
+ "臓 A",
1128
+ "臓 S",
1129
+ "en t",
1130
+ "i l",
1131
+ "臓t h",
1132
+ "臓 1",
1133
+ "s t",
1134
+ "臓 C",
1135
+ "e l",
1136
+ "o m",
1137
+ "臓 l",
1138
+ "a m",
1139
+ "臓 膴",
1140
+ "臓 e",
1141
+ "臓 n",
1142
+ "臓 @",
1143
+ "a d",
1144
+ "a c",
1145
+ "臓w as",
1146
+ "臓 M",
1147
+ "u r",
1148
+ "臓T he",
1149
+ "e c",
1150
+ "臓 on",
1151
+ "l y",
1152
+ "臓 B",
1153
+ "臓 I",
1154
+ "臓 g",
1155
+ "臓 '",
1156
+ "e t",
1157
+ "o l",
1158
+ "i d",
1159
+ "i v",
1160
+ "i m",
1161
+ "臓f or",
1162
+ "i r",
1163
+ "- @",
1164
+ "臓@ -@",
1165
+ "i g",
1166
+ "o t",
1167
+ "t er",
1168
+ "臓a s",
1169
+ "臓 H",
1170
+ "u s",
1171
+ "o w",
1172
+ "臓s t",
1173
+ "u t",
1174
+ "it h",
1175
+ "a y",
1176
+ "臓 2",
1177
+ "臓 P",
1178
+ "at ion",
1179
+ "v er",
1180
+ "臓b e",
1181
+ "he r",
1182
+ "臓th at",
1183
+ "臓w ith",
1184
+ "臓 R",
1185
+ "c e",
1186
+ "t h",
1187
+ "臓 D",
1188
+ "臓 is",
1189
+ "u n",
1190
+ "e m",
1191
+ "臓 F",
1192
+ "臓w h",
1193
+ "u l",
1194
+ "臓b y",
1195
+ "臓a l",
1196
+ "c h",
1197
+ "臓 )",
1198
+ "臓 (",
1199
+ "臓 W",
1200
+ "臓c on",
1201
+ "r a",
1202
+ "臓 G",
1203
+ "o s",
1204
+ "臓 L",
1205
+ "臓 N",
1206
+ "臓a t",
1207
+ "er s",
1208
+ "c t",
1209
+ "臓 it",
1210
+ "臓1 9",
1211
+ "ro m",
1212
+ "a nd",
1213
+ "臓a n",
1214
+ "u m",
1215
+ "es t",
1216
+ "臓 J",
1217
+ "a g",
1218
+ "臓 he",
1219
+ "0 0",
1220
+ "is t",
1221
+ "a in",
1222
+ "o d",
1223
+ "a v",
1224
+ "r i",
1225
+ "臓 E",
1226
+ "臓 O",
1227
+ "臓f rom",
1228
+ "臓c om",
1229
+ "臓h is",
1230
+ "o p",
1231
+ "臓p ro",
1232
+ "re s",
1233
+ "i es",
1234
+ "i f",
1235
+ "臓 v",
1236
+ "or t",
1237
+ "er e",
1238
+ "il l",
1239
+ "l d",
1240
+ "臓d e",
1241
+ "p p",
1242
+ "臓s u",
1243
+ "o re",
1244
+ "臓I n",
1245
+ "臓 r",
1246
+ "臓s e",
1247
+ "臓w 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
+ "臓c h",
1258
+ "臓o r",
1259
+ "a b",
1260
+ "an t",
1261
+ "u d",
1262
+ "o c",
1263
+ "b er",
1264
+ "臓e x",
1265
+ "g h",
1266
+ "it y",
1267
+ "at ed",
1268
+ "p t",
1269
+ "es s",
1270
+ "e ar",
1271
+ "臓 K",
1272
+ "臓p l",
1273
+ "am e",
1274
+ "q u",
1275
+ "iv e",
1276
+ "ro u",
1277
+ "臓a re",
1278
+ "臓 芒",
1279
+ "臓s h",
1280
+ "臓 k",
1281
+ "ac k",
1282
+ "ec t",
1283
+ "臓芒 蘑",
1284
+ "臓 U",
1285
+ "臓h ad",
1286
+ "s e",
1287
+ "臓wh ich",
1288
+ "re d",
1289
+ "o v",
1290
+ "臓S t",
1291
+ "as t",
1292
+ "臓s p",
1293
+ "i an",
1294
+ "臓 y",
1295
+ "m ent",
1296
+ "臓 le",
1297
+ "臓n 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
+ "臓 u",
1311
+ "is h",
1312
+ "臓C h",
1313
+ "ou n",
1314
+ "i a",
1315
+ "臓 3",
1316
+ "av e",
1317
+ "ar y",
1318
+ "u st",
1319
+ "o g",
1320
+ "臓2 00",
1321
+ "臓 un",
1322
+ "ou s",
1323
+ "ir st",
1324
+ "臓 V",
1325
+ "c c",
1326
+ "臓in c",
1327
+ "臓 ;",
1328
+ "臓com p",
1329
+ "r u",
1330
+ "ion s",
1331
+ "臓the ir",
1332
+ "臓b ut",
1333
+ "id e",
1334
+ "u re",
1335
+ "s o",
1336
+ "臓con t",
1337
+ "臓in t",
1338
+ "f ter",
1339
+ "ic al",
1340
+ "i al",
1341
+ "臓a r",
1342
+ "臓f irst",
1343
+ "ou ld",
1344
+ "臓it s",
1345
+ "he d",
1346
+ "臓芒蘑 牡",
1347
+ "臓w he",
1348
+ "w o",
1349
+ "ou t",
1350
+ "u b",
1351
+ "臓2 0",
1352
+ "f f",
1353
+ "臓 :",
1354
+ "u e",
1355
+ "臓 her",
1356
+ "ow n",
1357
+ "o k",
1358
+ "臓al so",
1359
+ "臓c 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
+ "臓re s",
1372
+ "臓a b",
1373
+ "臓a d",
1374
+ "臓 us",
1375
+ "r y",
1376
+ "臓re c",
1377
+ "臓h ave",
1378
+ "ag e",
1379
+ "臓H e",
1380
+ "臓 4",
1381
+ "臓 ro",
1382
+ "m er",
1383
+ "臓on e",
1384
+ "on d",
1385
+ "l ow",
1386
+ "臓h as",
1387
+ "臓T h",
1388
+ "d u",
1389
+ "臓 5",
1390
+ "臓p er",
1391
+ "臓be en",
1392
+ "im e",
1393
+ "臓t wo",
1394
+ "en ce",
1395
+ "l and",
1396
+ "臓1 8",
1397
+ ". @",
1398
+ "臓@ .@",
1399
+ "ul t",
1400
+ "re e",
1401
+ "ou gh",
1402
+ "i le",
1403
+ "臓wh o",
1404
+ "臓A l",
1405
+ "臓s c",
1406
+ "ur ing",
1407
+ "p l",
1408
+ "or y",
1409
+ "it ion",
1410
+ "r ic",
1411
+ "ation s",
1412
+ "臓d is",
1413
+ "臓th is",
1414
+ "臓b ec",
1415
+ "臓a pp",
1416
+ "i z",
1417
+ "臓I t",
1418
+ "a re",
1419
+ "ac h",
1420
+ "l ud",
1421
+ "ad e",
1422
+ "臓pl ay",
1423
+ "臓 j",
1424
+ "臓m an",
1425
+ "ac t",
1426
+ "el y",
1427
+ "臓p art",
1428
+ "臓d es",
1429
+ "臓a g",
1430
+ "臓the y",
1431
+ "臓y ear",
1432
+ "oun t",
1433
+ "臓20 1",
1434
+ "臓o ver",
1435
+ "臓o ther",
1436
+ "ou nd",
1437
+ "臓a fter",
1438
+ "i b",
1439
+ "o ver",
1440
+ "臓s er",
1441
+ "臓 en",
1442
+ "臓of f",
1443
+ "臓 im",
1444
+ "ct ion",
1445
+ "臓 Y",
1446
+ "k e",
1447
+ "it e",
1448
+ ", @",
1449
+ "臓@ ,@",
1450
+ "t e",
1451
+ "ur n",
1452
+ "臓inc lud",
1453
+ "res s",
1454
+ "an ce",
1455
+ "an g",
1456
+ "臓at t",
1457
+ "ic e",
1458
+ "ac e",
1459
+ "ar k",
1460
+ "臓o ut",
1461
+ "w n",
1462
+ "p h",
1463
+ "em ber",
1464
+ "臓p re",
1465
+ "臓u p",
1466
+ "en s",
1467
+ "m an",
1468
+ "臓e v",
1469
+ "臓t ime",
1470
+ "nd er",
1471
+ "rou gh",
1472
+ "c ed",
1473
+ "臓f in",
1474
+ "臓int o",
1475
+ "on e",
1476
+ "p ort",
1477
+ "rou nd",
1478
+ "w e",
1479
+ "re n",
1480
+ "l es",
1481
+ "in t",
1482
+ "臓O n",
1483
+ "v el",
1484
+ "臓com m",
1485
+ "臓s he",
1486
+ "as on",
1487
+ "am p",
1488
+ "臓t e",
1489
+ "臓w ould",
1490
+ "w ard",
1491
+ "臓m ore",
1492
+ "臓 6",
1493
+ "i ed",
1494
+ "os e",
1495
+ "ri b",
1496
+ "臓U n",
1497
+ "臓al l",
1498
+ "ing s",
1499
+ "ter n",
1500
+ "c es",
1501
+ "ab le",
1502
+ "臓w e",
1503
+ "it ed",
1504
+ "e ver",
1505
+ "ent s",
1506
+ "臓h im",
1507
+ "as ed",
1508
+ "or s",
1509
+ "o y",
1510
+ "o od",
1511
+ "臓c ent",
1512
+ "i x",
1513
+ "as e",
1514
+ "il d",
1515
+ "臓A n",
1516
+ "臓 7",
1517
+ "臓w ork",
1518
+ "at es",
1519
+ "i ous",
1520
+ "at h",
1521
+ "臓p o",
1522
+ "ro p",
1523
+ "ol d",
1524
+ "al s",
1525
+ "is s",
1526
+ "e y",
1527
+ "ic t",
1528
+ "臓f e",
1529
+ "臓the m",
1530
+ "g an",
1531
+ "臓s ec",
1532
+ "臓b et",
1533
+ "臓whe n",
1534
+ "臓s ong",
1535
+ "臓re m",
1536
+ "e p",
1537
+ "f orm",
1538
+ "a il",
1539
+ "f er",
1540
+ "臓e ar",
1541
+ "ub l",
1542
+ "a w",
1543
+ "臓k n",
1544
+ "ak e",
1545
+ "a us",
1546
+ "臓m ost",
1547
+ "臓con s",
1548
+ "臓d uring",
1549
+ "臓A s",
1550
+ "or th",
1551
+ "臓n ew",
1552
+ "er ed",
1553
+ "il m",
1554
+ "v ed",
1555
+ "at t",
1556
+ "臓on ly",
1557
+ "臓 9",
1558
+ "臓d ec",
1559
+ "臓 8",
1560
+ "ic k",
1561
+ "臓g ame",
1562
+ "on s",
1563
+ "u g",
1564
+ "臓t r",
1565
+ "f t",
1566
+ "ot h",
1567
+ "o ok",
1568
+ "臓M ar",
1569
+ "re at",
1570
+ "w ay",
1571
+ "臓c an",
1572
+ "ol low",
1573
+ "ou th",
1574
+ "we en",
1575
+ "臓E n",
1576
+ "臓19 9",
1577
+ "ter s",
1578
+ "臓re l",
1579
+ "in d",
1580
+ "臓ab out",
1581
+ "臓se ason",
1582
+ "臓ag ain",
1583
+ "r al",
1584
+ "臓th ree",
1585
+ "ation al",
1586
+ "臓u nder",
1587
+ "ul ar",
1588
+ "臓m e",
1589
+ "臓th an",
1590
+ "臓C om",
1591
+ "臓A r",
1592
+ "h ip",
1593
+ "o b",
1594
+ "臓n e",
1595
+ "臓bet ween",
1596
+ "臓f l",
1597
+ "h n",
1598
+ "v e",
1599
+ "臓ch ar",
1600
+ "臓c ol",
1601
+ "臓rec ord",
1602
+ "i ew",
1603
+ "r on",
1604
+ "f ore",
1605
+ "臓th rough",
1606
+ "is ion",
1607
+ "or n",
1608
+ "臓 00",
1609
+ "oc k",
1610
+ "臓 ver",
1611
+ "臓l ater",
1612
+ "臓n um",
1613
+ "臓e nd",
1614
+ "ol og",
1615
+ "am es",
1616
+ "臓p os",
1617
+ "臓w rit",
1618
+ "臓pro du",
1619
+ "臓wh ile",
1620
+ "臓a ct",
1621
+ "臓re le",
1622
+ "臓f ilm",
1623
+ "is hed",
1624
+ "臓p r",
1625
+ "an s",
1626
+ "臓re g",
1627
+ "臓for m",
1628
+ "臓as s",
1629
+ "臓S e",
1630
+ "ur y",
1631
+ "t ed",
1632
+ "t s",
1633
+ "臓m ade",
1634
+ "臓su b",
1635
+ "臓p e",
1636
+ "臓s o",
1637
+ "or ld",
1638
+ "臓re t",
1639
+ "臓N ew",
1640
+ "臓sp ec",
1641
+ "臓a cc",
1642
+ "臓 qu",
1643
+ "臓whe re",
1644
+ "en er",
1645
+ "臓m ov",
1646
+ "he s",
1647
+ "mer ic",
1648
+ "at ing",
1649
+ "臓in ter",
1650
+ "臓L e",
1651
+ "臓A meric",
1652
+ "臓 ra",
1653
+ "臓s ome",
1654
+ "臓c o",
1655
+ "臓l ar",
1656
+ "臓b u",
1657
+ "臓de f",
1658
+ "b um",
1659
+ "臓a c",
1660
+ "臓m us",
1661
+ "臓f ollow",
1662
+ "臓A t",
1663
+ "in s",
1664
+ "iv ed",
1665
+ "if ic",
1666
+ "u al",
1667
+ "臓a m",
1668
+ "臓su ch",
1669
+ "臓sec ond",
1670
+ "i ke",
1671
+ "臓f our",
1672
+ "臓in d",
1673
+ "an n",
1674
+ "he n",
1675
+ "臓us ed",
1676
+ "臓R e",
1677
+ "ic s",
1678
+ "le ct",
1679
+ "臓d ay",
1680
+ "i el",
1681
+ "il y",
1682
+ "臓Th is",
1683
+ "臓 0",
1684
+ "臓p ubl",
1685
+ "臓c all",
1686
+ "臓J o",
1687
+ "l l",
1688
+ "臓al bum",
1689
+ "臓00 0",
1690
+ "ran s",
1691
+ "臓d o",
1692
+ "an y",
1693
+ "臓be fore",
1694
+ "ro s",
1695
+ "臓S h",
1696
+ "臓s y",
1697
+ "a id",
1698
+ "臓En g",
1699
+ "臓be ing",
1700
+ "臓1 0",
1701
+ "u c",
1702
+ "臓e p",
1703
+ "臓su pp",
1704
+ "臓the re",
1705
+ "臓year s",
1706
+ "ar s",
1707
+ "ow ever",
1708
+ "臓 ent",
1709
+ "if e",
1710
+ "臓h igh",
1711
+ "臓f ound",
1712
+ "ir d",
1713
+ "臓n o",
1714
+ "臓s et",
1715
+ "in es",
1716
+ "iv er",
1717
+ "i o",
1718
+ "ot her",
1719
+ "j ect",
1720
+ "臓s ur",
1721
+ "a j",
1722
+ "t en",
1723
+ "臓t ra",
1724
+ "臓1 2",
1725
+ "is ed",
1726
+ "it ies",
1727
+ "vel op",
1728
+ "臓b l",
1729
+ "al e",
1730
+ "臓ser ies",
1731
+ "臓l oc",
1732
+ "臓num ber",
1733
+ "臓p res",
1734
+ "an e",
1735
+ "aus e",
1736
+ "od e",
1737
+ "e k",
1738
+ "t on",
1739
+ "臓S c",
1740
+ "i er",
1741
+ "is e",
1742
+ "臓se ver",
1743
+ "in ce",
1744
+ "臓b oth",
1745
+ "an k",
1746
+ "ro w",
1747
+ "ire ct",
1748
+ "s on",
1749
+ "臓the n",
1750
+ "臓B rit",
1751
+ "i et",
1752
+ "臓1 6",
1753
+ "臓ep is",
1754
+ "臓includ ing",
1755
+ "it s",
1756
+ "ig in",
1757
+ "p r",
1758
+ "臓 /",
1759
+ "臓again st",
1760
+ "臓w ell",
1761
+ "臓bec ame",
1762
+ "臓ex p",
1763
+ "臓kn own",
1764
+ "臓t rans",
1765
+ "臓char ac",
1766
+ "臓芒蘑 亩",
1767
+ "r am",
1768
+ "臓b ack",
1769
+ "臓ad d",
1770
+ "臓p op",
1771
+ "臓g o",
1772
+ "ur ch",
1773
+ "臓des c",
1774
+ "臓s ing",
1775
+ "iel d",
1776
+ "臓per form",
1777
+ "ain ed",
1778
+ "臓re ce",
1779
+ "id ent",
1780
+ "臓e m",
1781
+ "er t",
1782
+ "u res",
1783
+ "臓in v",
1784
+ "臓de p",
1785
+ "臓19 8",
1786
+ "a ir",
1787
+ "er n",
1788
+ "at her",
1789
+ "f ul",
1790
+ "臓 Z",
1791
+ "臓m on",
1792
+ "臓man y",
1793
+ "臓m ain",
1794
+ "臓st ud",
1795
+ "臓l ong",
1796
+ "in n",
1797
+ "th ough",
1798
+ "u p",
1799
+ "o ol",
1800
+ "臓Un ited",
1801
+ "l ed",
1802
+ "em ent",
1803
+ "臓1 5",
1804
+ "ow er",
1805
+ "臓Jo hn",
1806
+ "臓o p",
1807
+ "臓1 1",
1808
+ "in ed",
1809
+ "臓m et",
1810
+ "o ber",
1811
+ "le y",
1812
+ "臓1 7",
1813
+ "臓cent ury",
1814
+ "臓te am",
1815
+ "臓 est",
1816
+ "臓A fter",
1817
+ "y l",
1818
+ "臓m in",
1819
+ "u ch",
1820
+ "ut e",
1821
+ "臓de velop",
1822
+ "臓S he",
1823
+ "i am",
1824
+ "臓sh ow",
1825
+ "el f",
1826
+ "臓re p",
1827
+ "臓con c",
1828
+ "at ive",
1829
+ "臓c re",
1830
+ "over n",
1831
+ "a red",
1832
+ "臓19 4",
1833
+ "臓or igin",
1834
+ "臓s m",
1835
+ "iv ers",
1836
+ "a z",
1837
+ "臓le ad",
1838
+ "臓sever al",
1839
+ "a h",
1840
+ "臓o b",
1841
+ "臓re v",
1842
+ "臓m ill",
1843
+ "er m",
1844
+ "u ally",
1845
+ "o ot",
1846
+ "臓be 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
+ }