Now-or-Never commited on
Commit
692b01d
1 Parent(s): efee301

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[UNUSED_TOKEN_141]": 92544,
3
+ "[UNUSED_TOKEN_142]": 92545,
4
+ "[UNUSED_TOKEN_143]": 92546,
5
+ "[UNUSED_TOKEN_144]": 92547,
6
+ "[UNUSED_TOKEN_145]": 92548,
7
+ "[UNUSED_TOKEN_146]": 92549
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
3
+ #
4
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
5
+ #
6
+ # Licensed under the Apache License, Version 2.0 (the "License");
7
+ # you may not use this file except in compliance with the License.
8
+ # You may obtain a copy of the License at
9
+ #
10
+ # http://www.apache.org/licenses/LICENSE-2.0
11
+ #
12
+ # Unless required by applicable law or agreed to in writing, software
13
+ # distributed under the License is distributed on an "AS IS" BASIS,
14
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ # See the License for the specific language governing permissions and
16
+ # limitations under the License.
17
+
18
+ """Tokenization classes for InternLM."""
19
+ import os
20
+ from shutil import copyfile
21
+ from typing import Any, Dict, List, Optional, Tuple
22
+
23
+ import sentencepiece as spm
24
+ from transformers.tokenization_utils import PreTrainedTokenizer
25
+ from transformers.utils import logging
26
+
27
+ logger = logging.get_logger(__name__)
28
+
29
+ VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
30
+
31
+ PRETRAINED_VOCAB_FILES_MAP = {}
32
+
33
+
34
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
35
+ class InternLM2Tokenizer(PreTrainedTokenizer):
36
+ """
37
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
38
+
39
+ Args:
40
+ vocab_file (`str`):
41
+ Path to the vocabulary file.
42
+ """
43
+
44
+ vocab_files_names = VOCAB_FILES_NAMES
45
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
46
+ model_input_names = ["input_ids", "attention_mask"]
47
+ _auto_class = "AutoTokenizer"
48
+
49
+ def __init__(
50
+ self,
51
+ vocab_file,
52
+ unk_token="<unk>",
53
+ bos_token="<s>",
54
+ eos_token="</s>",
55
+ pad_token="</s>",
56
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
57
+ add_bos_token=True,
58
+ add_eos_token=False,
59
+ decode_with_prefix_space=False,
60
+ clean_up_tokenization_spaces=False,
61
+ **kwargs,
62
+ ):
63
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
64
+ self.vocab_file = vocab_file
65
+ self.add_bos_token = add_bos_token
66
+ self.add_eos_token = add_eos_token
67
+ self.decode_with_prefix_space = decode_with_prefix_space
68
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
69
+ self.sp_model.Load(vocab_file)
70
+ self._no_prefix_space_tokens = None
71
+ super().__init__(
72
+ bos_token=bos_token,
73
+ eos_token=eos_token,
74
+ unk_token=unk_token,
75
+ pad_token=pad_token,
76
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
77
+ **kwargs,
78
+ )
79
+
80
+ @property
81
+ def no_prefix_space_tokens(self):
82
+ if self._no_prefix_space_tokens is None:
83
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
84
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
85
+ return self._no_prefix_space_tokens
86
+
87
+ @property
88
+ def vocab_size(self):
89
+ """Returns vocab size"""
90
+ return self.sp_model.get_piece_size()
91
+
92
+ @property
93
+ def bos_token_id(self) -> Optional[int]:
94
+ return self.sp_model.bos_id()
95
+
96
+ @property
97
+ def eos_token_id(self) -> Optional[int]:
98
+ return self.sp_model.eos_id()
99
+
100
+ def get_vocab(self):
101
+ """Returns vocab as a dict"""
102
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
103
+ vocab.update(self.added_tokens_encoder)
104
+ return vocab
105
+
106
+ def _tokenize(self, text):
107
+ """Returns a tokenized string."""
108
+ return self.sp_model.encode(text, out_type=str)
109
+
110
+ def _convert_token_to_id(self, token):
111
+ """Converts a token (str) in an id using the vocab."""
112
+ return self.sp_model.piece_to_id(token)
113
+
114
+ def _convert_id_to_token(self, index):
115
+ """Converts an index (integer) in a token (str) using the vocab."""
116
+ token = self.sp_model.IdToPiece(index)
117
+ return token
118
+
119
+ def _maybe_add_prefix_space(self, tokens, decoded):
120
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
121
+ return " " + decoded
122
+ else:
123
+ return decoded
124
+
125
+ def convert_tokens_to_string(self, tokens):
126
+ """Converts a sequence of tokens (string) in a single string."""
127
+ current_sub_tokens = []
128
+ out_string = ""
129
+ prev_is_special = False
130
+ for token in tokens:
131
+ # make sure that special tokens are not decoded using sentencepiece model
132
+ if token in self.all_special_tokens:
133
+ if not prev_is_special:
134
+ out_string += " "
135
+ out_string += self.sp_model.decode(current_sub_tokens) + token
136
+ prev_is_special = True
137
+ current_sub_tokens = []
138
+ else:
139
+ current_sub_tokens.append(token)
140
+ prev_is_special = False
141
+ out_string += self.sp_model.decode(current_sub_tokens)
142
+ out_string = self.clean_up_tokenization(out_string)
143
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
144
+ return out_string[1:]
145
+
146
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
147
+ """
148
+ Save the vocabulary and special tokens file to a directory.
149
+
150
+ Args:
151
+ save_directory (`str`):
152
+ The directory in which to save the vocabulary.
153
+
154
+ Returns:
155
+ `Tuple(str)`: Paths to the files saved.
156
+ """
157
+ if not os.path.isdir(save_directory):
158
+ logger.error(f"Vocabulary path ({save_directory}) should be a directory")
159
+ return
160
+ out_vocab_file = os.path.join(
161
+ save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
162
+ )
163
+
164
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
165
+ copyfile(self.vocab_file, out_vocab_file)
166
+ elif not os.path.isfile(self.vocab_file):
167
+ with open(out_vocab_file, "wb") as fi:
168
+ content_spiece_model = self.sp_model.serialized_model_proto()
169
+ fi.write(content_spiece_model)
170
+
171
+ return (out_vocab_file,)
172
+
173
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
174
+ if self.add_bos_token:
175
+ bos_token_ids = [self.bos_token_id]
176
+ else:
177
+ bos_token_ids = []
178
+
179
+ output = bos_token_ids + token_ids_0
180
+
181
+ if token_ids_1 is not None:
182
+ output = output + token_ids_1
183
+
184
+ if self.add_eos_token:
185
+ output = output + [self.eos_token_id]
186
+
187
+ return output
188
+
189
+ def get_special_tokens_mask(
190
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
191
+ ) -> List[int]:
192
+ """
193
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
194
+ special tokens using the tokenizer `prepare_for_model` method.
195
+
196
+ Args:
197
+ token_ids_0 (`List[int]`):
198
+ List of IDs.
199
+ token_ids_1 (`List[int]`, *optional*):
200
+ Optional second list of IDs for sequence pairs.
201
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
202
+ Whether or not the token list is already formatted with special tokens for the model.
203
+
204
+ Returns:
205
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
206
+ """
207
+ if already_has_special_tokens:
208
+ return super().get_special_tokens_mask(
209
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
210
+ )
211
+
212
+ if token_ids_1 is None:
213
+ return [1] + ([0] * len(token_ids_0)) + [1]
214
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
215
+
216
+ def create_token_type_ids_from_sequences(
217
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
218
+ ) -> List[int]:
219
+ """
220
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
221
+ use of token type ids, therefore a list of zeros is returned.
222
+
223
+ Args:
224
+ token_ids_0 (`List[int]`):
225
+ List of IDs.
226
+ token_ids_1 (`List[int]`, *optional*):
227
+ Optional second list of IDs for sequence pairs.
228
+
229
+ Returns:
230
+ `List[int]`: List of zeros.
231
+ """
232
+ eos = [self.eos_token_id]
233
+
234
+ if token_ids_1 is None:
235
+ return len(token_ids_0 + eos) * [0]
236
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenization_internlm2_fast.py ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
3
+ #
4
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama_fast.py
5
+ #
6
+ # Licensed under the Apache License, Version 2.0 (the "License");
7
+ # you may not use this file except in compliance with the License.
8
+ # You may obtain a copy of the License at
9
+ #
10
+ # http://www.apache.org/licenses/LICENSE-2.0
11
+ #
12
+ # Unless required by applicable law or agreed to in writing, software
13
+ # distributed under the License is distributed on an "AS IS" BASIS,
14
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ # See the License for the specific language governing permissions and
16
+ # limitations under the License.
17
+
18
+ """Tokenization Fast class for InternLM."""
19
+ import os
20
+ from shutil import copyfile
21
+ from typing import Any, Dict, Optional, Tuple
22
+
23
+ from tokenizers import processors, decoders, Tokenizer, normalizers
24
+ from tokenizers.models import BPE
25
+
26
+ from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
27
+ from transformers.utils import logging
28
+
29
+ from transformers.convert_slow_tokenizer import (
30
+ SLOW_TO_FAST_CONVERTERS,
31
+ SpmConverter,
32
+ SentencePieceExtractor,
33
+ )
34
+
35
+ from .tokenization_internlm2 import InternLM2Tokenizer
36
+
37
+ logger = logging.get_logger(__name__)
38
+
39
+ VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
40
+
41
+ # Modified from transformers.convert_slow_tokenizer.LlamaConverter
42
+ class InternLM2Converter(SpmConverter):
43
+ handle_byte_fallback = True
44
+
45
+ def vocab(self, proto):
46
+ vocab = [
47
+ ("<unk>", 0.0),
48
+ ("<s>", 0.0),
49
+ ("</s>", 0.0),
50
+ ]
51
+ vocab += [(piece.piece, piece.score) for piece in proto.pieces[3:]]
52
+ return vocab
53
+
54
+ def unk_id(self, proto):
55
+ unk_id = 0
56
+ return unk_id
57
+
58
+ def decoder(self, replacement, add_prefix_space):
59
+ decoders_sequence = [
60
+ decoders.Replace("▁", " "),
61
+ decoders.ByteFallback(),
62
+ decoders.Fuse(),
63
+ ]
64
+ if self.proto.normalizer_spec.add_dummy_prefix:
65
+ decoders_sequence.append(decoders.Strip(content=" ", left=1))
66
+ return decoders.Sequence(decoders_sequence)
67
+
68
+ def tokenizer(self, proto):
69
+ model_type = proto.trainer_spec.model_type
70
+ vocab_scores = self.vocab(proto)
71
+ # special tokens
72
+ added_tokens = self.original_tokenizer.added_tokens_decoder
73
+ for i in range(len(vocab_scores)):
74
+ piece, score = vocab_scores[i]
75
+ if i in added_tokens:
76
+ vocab_scores[i] = (added_tokens[i].content, score)
77
+ if model_type == 1:
78
+ raise RuntimeError("InternLM2 is supposed to be a BPE model!")
79
+
80
+ elif model_type == 2:
81
+ _, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract(vocab_scores)
82
+ bpe_vocab = {word: i for i, (word, _score) in enumerate(vocab_scores)}
83
+ tokenizer = Tokenizer(
84
+ BPE(bpe_vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True, byte_fallback=True)
85
+ )
86
+ tokenizer.add_special_tokens(
87
+ [ added_token for index, added_token in added_tokens.items()]
88
+ )
89
+ else:
90
+ raise Exception(
91
+ "You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
92
+ )
93
+
94
+ return tokenizer
95
+
96
+ def normalizer(self, proto):
97
+ normalizers_list = []
98
+ if proto.normalizer_spec.add_dummy_prefix:
99
+ normalizers_list.append(normalizers.Prepend(prepend="▁"))
100
+ normalizers_list.append(normalizers.Replace(pattern=" ", content="▁"))
101
+ return normalizers.Sequence(normalizers_list)
102
+
103
+ def pre_tokenizer(self, replacement, add_prefix_space):
104
+ return None
105
+
106
+ SLOW_TO_FAST_CONVERTERS["InternLM2Tokenizer"] = InternLM2Converter
107
+
108
+
109
+ # Modified from transformers.model.llama.tokenization_llama_fast.LlamaTokenizerFast -> InternLM2TokenizerFast
110
+ class InternLM2TokenizerFast(PreTrainedTokenizerFast):
111
+ vocab_files_names = VOCAB_FILES_NAMES
112
+ slow_tokenizer_class = InternLM2Tokenizer
113
+ padding_side = "left"
114
+ model_input_names = ["input_ids", "attention_mask"]
115
+ _auto_class = "AutoTokenizer"
116
+
117
+ def __init__(
118
+ self,
119
+ vocab_file,
120
+ unk_token="<unk>",
121
+ bos_token="<s>",
122
+ eos_token="</s>",
123
+ pad_token="</s>",
124
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
125
+ add_bos_token=True,
126
+ add_eos_token=False,
127
+ decode_with_prefix_space=False,
128
+ clean_up_tokenization_spaces=False,
129
+ **kwargs,
130
+ ):
131
+ super().__init__(
132
+ vocab_file=vocab_file,
133
+ unk_token=unk_token,
134
+ bos_token=bos_token,
135
+ eos_token=eos_token,
136
+ pad_token=pad_token,
137
+ sp_model_kwargs=sp_model_kwargs,
138
+ add_bos_token=add_bos_token,
139
+ add_eos_token=add_eos_token,
140
+ decode_with_prefix_space=decode_with_prefix_space,
141
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
142
+ **kwargs,
143
+ )
144
+ self._add_bos_token = add_bos_token
145
+ self._add_eos_token = add_eos_token
146
+ self.update_post_processor()
147
+ self.vocab_file = vocab_file
148
+
149
+ @property
150
+ def can_save_slow_tokenizer(self) -> bool:
151
+ return os.path.isfile(self.vocab_file) if self.vocab_file else False
152
+
153
+ def update_post_processor(self):
154
+ """
155
+ Updates the underlying post processor with the current `bos_token` and `eos_token`.
156
+ """
157
+ bos = self.bos_token
158
+ bos_token_id = self.bos_token_id
159
+ if bos is None and self.add_bos_token:
160
+ raise ValueError("add_bos_token = True but bos_token = None")
161
+
162
+ eos = self.eos_token
163
+ eos_token_id = self.eos_token_id
164
+ if eos is None and self.add_eos_token:
165
+ raise ValueError("add_eos_token = True but eos_token = None")
166
+
167
+ single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
168
+ pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
169
+
170
+ special_tokens = []
171
+ if self.add_bos_token:
172
+ special_tokens.append((bos, bos_token_id))
173
+ if self.add_eos_token:
174
+ special_tokens.append((eos, eos_token_id))
175
+ self._tokenizer.post_processor = processors.TemplateProcessing(
176
+ single=single, pair=pair, special_tokens=special_tokens
177
+ )
178
+
179
+ @property
180
+ def add_eos_token(self):
181
+ return self._add_eos_token
182
+
183
+ @property
184
+ def add_bos_token(self):
185
+ return self._add_bos_token
186
+
187
+ @add_eos_token.setter
188
+ def add_eos_token(self, value):
189
+ self._add_eos_token = value
190
+ self.update_post_processor()
191
+
192
+ @add_bos_token.setter
193
+ def add_bos_token(self, value):
194
+ self._add_bos_token = value
195
+ self.update_post_processor()
196
+
197
+ def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
198
+ if not self.can_save_slow_tokenizer:
199
+ raise ValueError(
200
+ "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
201
+ "tokenizer."
202
+ )
203
+
204
+ if not os.path.isdir(save_directory):
205
+ logger.error(f"Vocabulary path ({save_directory}) should be a directory")
206
+ return
207
+ out_vocab_file = os.path.join(
208
+ save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
209
+ )
210
+
211
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
212
+ copyfile(self.vocab_file, out_vocab_file)
213
+
214
+ return (out_vocab_file,)
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,1638 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "92352": {
30
+ "content": "E",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "92353": {
38
+ "content": "F",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "92354": {
46
+ "content": "G",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "92355": {
54
+ "content": "H",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "92356": {
62
+ "content": "I",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "92357": {
70
+ "content": "J",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "92358": {
78
+ "content": "K",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "92359": {
86
+ "content": "L",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "92360": {
94
+ "content": "M",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "92361": {
102
+ "content": "N",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "92362": {
110
+ "content": "R",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "92363": {
118
+ "content": "U",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "92364": {
126
+ "content": "V",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "92365": {
134
+ "content": "W",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "92366": {
142
+ "content": "X",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "92367": {
150
+ "content": "Y",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "92368": {
158
+ "content": "Z",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "92369": {
166
+ "content": "a",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "92370": {
174
+ "content": "b",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "92371": {
182
+ "content": "c",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "92372": {
190
+ "content": "d",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "92373": {
198
+ "content": "e",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "92374": {
206
+ "content": "f",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "92375": {
214
+ "content": "g",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "92376": {
222
+ "content": "h",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "92377": {
230
+ "content": "i",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "92378": {
238
+ "content": "j",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "92379": {
246
+ "content": "k",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "92380": {
254
+ "content": "l",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "92381": {
262
+ "content": "m",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "92382": {
270
+ "content": "n",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "92383": {
278
+ "content": "o",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "92384": {
286
+ "content": "p",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "92385": {
294
+ "content": "q",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "92386": {
302
+ "content": "r",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "92387": {
310
+ "content": "s",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "92388": {
318
+ "content": "t",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "92389": {
326
+ "content": "u",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "92390": {
334
+ "content": "v",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "92391": {
342
+ "content": "w",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "92392": {
350
+ "content": "x",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "92393": {
358
+ "content": "y",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "92394": {
366
+ "content": "z",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "92395": {
374
+ "content": "——",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "92396": {
382
+ "content": "……",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "92397": {
390
+ "content": "[UNUSED_TOKEN_0]",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "92398": {
398
+ "content": "[UNUSED_TOKEN_1]",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "92399": {
406
+ "content": "[UNUSED_TOKEN_2]",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "92400": {
414
+ "content": "[UNUSED_TOKEN_3]",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "92401": {
422
+ "content": "[UNUSED_TOKEN_4]",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "92402": {
430
+ "content": "[UNUSED_TOKEN_5]",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "92403": {
438
+ "content": "[UNUSED_TOKEN_6]",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "92404": {
446
+ "content": "[UNUSED_TOKEN_7]",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "92405": {
454
+ "content": "[UNUSED_TOKEN_8]",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "92406": {
462
+ "content": "[UNUSED_TOKEN_9]",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "92407": {
470
+ "content": "[UNUSED_TOKEN_10]",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "92408": {
478
+ "content": "[UNUSED_TOKEN_11]",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "92409": {
486
+ "content": "[UNUSED_TOKEN_12]",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "92410": {
494
+ "content": "[UNUSED_TOKEN_13]",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "92411": {
502
+ "content": "[UNUSED_TOKEN_14]",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "92412": {
510
+ "content": "[UNUSED_TOKEN_15]",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "92413": {
518
+ "content": "[UNUSED_TOKEN_16]",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "92414": {
526
+ "content": "[UNUSED_TOKEN_17]",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "92415": {
534
+ "content": "[UNUSED_TOKEN_18]",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "92416": {
542
+ "content": "[UNUSED_TOKEN_19]",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "92417": {
550
+ "content": "[UNUSED_TOKEN_20]",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "92418": {
558
+ "content": "[UNUSED_TOKEN_21]",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "92419": {
566
+ "content": "[UNUSED_TOKEN_22]",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "92420": {
574
+ "content": "[UNUSED_TOKEN_23]",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "92421": {
582
+ "content": "[UNUSED_TOKEN_24]",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "92422": {
590
+ "content": "[UNUSED_TOKEN_25]",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "92423": {
598
+ "content": "[UNUSED_TOKEN_26]",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "92424": {
606
+ "content": "[UNUSED_TOKEN_27]",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "92425": {
614
+ "content": "[UNUSED_TOKEN_28]",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "92426": {
622
+ "content": "[UNUSED_TOKEN_29]",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "92427": {
630
+ "content": "[UNUSED_TOKEN_30]",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "92428": {
638
+ "content": "[UNUSED_TOKEN_31]",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "92429": {
646
+ "content": "[UNUSED_TOKEN_32]",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "92430": {
654
+ "content": "[UNUSED_TOKEN_33]",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "92431": {
662
+ "content": "[UNUSED_TOKEN_34]",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "92432": {
670
+ "content": "[UNUSED_TOKEN_35]",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "92433": {
678
+ "content": "[UNUSED_TOKEN_36]",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "92434": {
686
+ "content": "[UNUSED_TOKEN_37]",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "92435": {
694
+ "content": "[UNUSED_TOKEN_38]",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "92436": {
702
+ "content": "[UNUSED_TOKEN_39]",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "92437": {
710
+ "content": "[UNUSED_TOKEN_40]",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "92438": {
718
+ "content": "[UNUSED_TOKEN_41]",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "92439": {
726
+ "content": "[UNUSED_TOKEN_42]",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "92440": {
734
+ "content": "[UNUSED_TOKEN_43]",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92441": {
742
+ "content": "[UNUSED_TOKEN_44]",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "92442": {
750
+ "content": "[UNUSED_TOKEN_45]",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "92443": {
758
+ "content": "[UNUSED_TOKEN_46]",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "92444": {
766
+ "content": "[UNUSED_TOKEN_47]",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "92445": {
774
+ "content": "[UNUSED_TOKEN_48]",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "92446": {
782
+ "content": "[UNUSED_TOKEN_49]",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "92447": {
790
+ "content": "[UNUSED_TOKEN_50]",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "92448": {
798
+ "content": "[UNUSED_TOKEN_51]",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "92449": {
806
+ "content": "[UNUSED_TOKEN_52]",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "92450": {
814
+ "content": "[UNUSED_TOKEN_53]",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "92451": {
822
+ "content": "[UNUSED_TOKEN_54]",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "92452": {
830
+ "content": "[UNUSED_TOKEN_55]",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "92453": {
838
+ "content": "[UNUSED_TOKEN_56]",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "92454": {
846
+ "content": "[UNUSED_TOKEN_57]",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "92455": {
854
+ "content": "[UNUSED_TOKEN_58]",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "92456": {
862
+ "content": "[UNUSED_TOKEN_59]",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "92457": {
870
+ "content": "[UNUSED_TOKEN_60]",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "92458": {
878
+ "content": "[UNUSED_TOKEN_61]",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "92459": {
886
+ "content": "[UNUSED_TOKEN_62]",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "92460": {
894
+ "content": "[UNUSED_TOKEN_63]",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "92461": {
902
+ "content": "[UNUSED_TOKEN_64]",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "92462": {
910
+ "content": "[UNUSED_TOKEN_65]",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "92463": {
918
+ "content": "[UNUSED_TOKEN_66]",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "92464": {
926
+ "content": "[UNUSED_TOKEN_67]",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "92465": {
934
+ "content": "[UNUSED_TOKEN_68]",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "92466": {
942
+ "content": "[UNUSED_TOKEN_69]",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "92467": {
950
+ "content": "[UNUSED_TOKEN_70]",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "92468": {
958
+ "content": "[UNUSED_TOKEN_71]",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "92469": {
966
+ "content": "[UNUSED_TOKEN_72]",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "92470": {
974
+ "content": "[UNUSED_TOKEN_73]",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "92471": {
982
+ "content": "[UNUSED_TOKEN_74]",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "92472": {
990
+ "content": "[UNUSED_TOKEN_75]",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "92473": {
998
+ "content": "[UNUSED_TOKEN_76]",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "92474": {
1006
+ "content": "[UNUSED_TOKEN_77]",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "92475": {
1014
+ "content": "[UNUSED_TOKEN_78]",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "92476": {
1022
+ "content": "[UNUSED_TOKEN_79]",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "92477": {
1030
+ "content": "[UNUSED_TOKEN_80]",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "92478": {
1038
+ "content": "[UNUSED_TOKEN_81]",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "92479": {
1046
+ "content": "[UNUSED_TOKEN_82]",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "92480": {
1054
+ "content": "[UNUSED_TOKEN_83]",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "92481": {
1062
+ "content": "[UNUSED_TOKEN_84]",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "92482": {
1070
+ "content": "[UNUSED_TOKEN_85]",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "92483": {
1078
+ "content": "[UNUSED_TOKEN_86]",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "92484": {
1086
+ "content": "[UNUSED_TOKEN_87]",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "92485": {
1094
+ "content": "[UNUSED_TOKEN_88]",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "92486": {
1102
+ "content": "[UNUSED_TOKEN_89]",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "92487": {
1110
+ "content": "[UNUSED_TOKEN_90]",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "92488": {
1118
+ "content": "[UNUSED_TOKEN_91]",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "92489": {
1126
+ "content": "[UNUSED_TOKEN_92]",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "92490": {
1134
+ "content": "[UNUSED_TOKEN_93]",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "92491": {
1142
+ "content": "[UNUSED_TOKEN_94]",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "92492": {
1150
+ "content": "[UNUSED_TOKEN_95]",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "92493": {
1158
+ "content": "[UNUSED_TOKEN_96]",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "92494": {
1166
+ "content": "[UNUSED_TOKEN_97]",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "92495": {
1174
+ "content": "[UNUSED_TOKEN_98]",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "92496": {
1182
+ "content": "[UNUSED_TOKEN_99]",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "92497": {
1190
+ "content": "[UNUSED_TOKEN_100]",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "92498": {
1198
+ "content": "[UNUSED_TOKEN_101]",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "92499": {
1206
+ "content": "[UNUSED_TOKEN_102]",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "92500": {
1214
+ "content": "[UNUSED_TOKEN_103]",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "92501": {
1222
+ "content": "[UNUSED_TOKEN_104]",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "92502": {
1230
+ "content": "[UNUSED_TOKEN_105]",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "92503": {
1238
+ "content": "[UNUSED_TOKEN_106]",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "92504": {
1246
+ "content": "[UNUSED_TOKEN_107]",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "92505": {
1254
+ "content": "[UNUSED_TOKEN_108]",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "92506": {
1262
+ "content": "[UNUSED_TOKEN_109]",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "92507": {
1270
+ "content": "[UNUSED_TOKEN_110]",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "92508": {
1278
+ "content": "[UNUSED_TOKEN_111]",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "92509": {
1286
+ "content": "[UNUSED_TOKEN_112]",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "92510": {
1294
+ "content": "[UNUSED_TOKEN_113]",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "92511": {
1302
+ "content": "[UNUSED_TOKEN_114]",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "92512": {
1310
+ "content": "[UNUSED_TOKEN_115]",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "92513": {
1318
+ "content": "[UNUSED_TOKEN_116]",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "92514": {
1326
+ "content": "[UNUSED_TOKEN_117]",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "92515": {
1334
+ "content": "[UNUSED_TOKEN_118]",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "92516": {
1342
+ "content": "[UNUSED_TOKEN_119]",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "92517": {
1350
+ "content": "[UNUSED_TOKEN_120]",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "92518": {
1358
+ "content": "[UNUSED_TOKEN_121]",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "92519": {
1366
+ "content": "[UNUSED_TOKEN_122]",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "92520": {
1374
+ "content": "[UNUSED_TOKEN_123]",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "92521": {
1382
+ "content": "[UNUSED_TOKEN_124]",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "92522": {
1390
+ "content": "[UNUSED_TOKEN_125]",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "92523": {
1398
+ "content": "[UNUSED_TOKEN_126]",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "92524": {
1406
+ "content": "[UNUSED_TOKEN_127]",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "92525": {
1414
+ "content": "[UNUSED_TOKEN_128]",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "92526": {
1422
+ "content": "[UNUSED_TOKEN_129]",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "92527": {
1430
+ "content": "[UNUSED_TOKEN_130]",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "92528": {
1438
+ "content": "[UNUSED_TOKEN_131]",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "92529": {
1446
+ "content": "[UNUSED_TOKEN_132]",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "92530": {
1454
+ "content": "[UNUSED_TOKEN_133]",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "92531": {
1462
+ "content": "[UNUSED_TOKEN_134]",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "92532": {
1470
+ "content": "[UNUSED_TOKEN_135]",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "92533": {
1478
+ "content": "[UNUSED_TOKEN_136]",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "92534": {
1486
+ "content": "[UNUSED_TOKEN_137]",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "92535": {
1494
+ "content": "[UNUSED_TOKEN_138]",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "92536": {
1502
+ "content": "[UNUSED_TOKEN_139]",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "92537": {
1510
+ "content": "[UNUSED_TOKEN_140]",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "92538": {
1518
+ "content": "<|plugin|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "92539": {
1526
+ "content": "<|interpreter|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "92540": {
1534
+ "content": "<|action_end|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "92541": {
1542
+ "content": "<|action_start|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "92542": {
1550
+ "content": "<|im_end|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "92543": {
1558
+ "content": "<|im_start|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "92544": {
1566
+ "content": "[UNUSED_TOKEN_141]",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "92545": {
1574
+ "content": "[UNUSED_TOKEN_142]",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "92546": {
1582
+ "content": "[UNUSED_TOKEN_143]",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "92547": {
1590
+ "content": "[UNUSED_TOKEN_144]",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "92548": {
1598
+ "content": "[UNUSED_TOKEN_145]",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "92549": {
1606
+ "content": "[UNUSED_TOKEN_146]",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ }
1613
+ },
1614
+ "additional_special_tokens": [
1615
+ "<|im_start|>",
1616
+ "<|im_end|>",
1617
+ "<|action_start|>",
1618
+ "<|action_end|>",
1619
+ "<|interpreter|>",
1620
+ "<|plugin|>"
1621
+ ],
1622
+ "auto_map": {
1623
+ "AutoTokenizer": [
1624
+ "tokenization_internlm2.InternLM2Tokenizer",
1625
+ "tokenization_internlm2_fast.InternLM2TokenizerFast"
1626
+ ]
1627
+ },
1628
+ "bos_token": "<s>",
1629
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
1630
+ "clean_up_tokenization_spaces": false,
1631
+ "decode_with_prefix_space": false,
1632
+ "eos_token": "</s>",
1633
+ "model_max_length": 1000000000000000019884624838656,
1634
+ "pad_token": "</s>",
1635
+ "sp_model_kwargs": null,
1636
+ "tokenizer_class": "InternLM2Tokenizer",
1637
+ "unk_token": "<unk>"
1638
+ }