Hugging Face's logo

tangledgroup
/
tangled-llama-n-128k-v0.1

Model card Files Community
mtasic85 commited on
Commit
36f3948
·
1 Parent(s): 17bea1f

tokenizer, pretrain dataset

Browse files
Files changed (16) hide show
  1. README.md +1 -1
  2. merges.txt +0 -0
  3. misc/logo.jpg +0 -0
  4. misc/logo.png +0 -3
  5. scripts/contrain-model-0.yaml +0 -156
  6. scripts/prepare_contrain_datasets.py +0 -46
  7. scripts/prepare_pretrain_datasets.py +10 -7
  8. scripts/{pretrain-model-0.yaml → pretrain-model.yaml} +1 -1
  9. scripts/{pretrain_datasets.py → pretrain_base_datasets.py} +16 -16
  10. scripts/{contrain_datasets.py → pretrain_instruct_datasets.py} +23 -35
  11. scripts/train_tokenizer.py +2 -3
  12. scripts/utils.py +21 -3
  13. special_tokens_map.json +0 -5
  14. tokenizer.json +0 -3
  15. tokenizer_config.json +0 -4108
  16. vocab.json +0 -0
README.md CHANGED
@@ -7,4 +7,4 @@ license: apache-2.0
7
  ```bash
8
  time python -B train_tokenizer.py
9
  time python -B prepare_pretrain_datasets.py
10
- ```
 
7
  ```bash
8
  time python -B train_tokenizer.py
9
  time python -B prepare_pretrain_datasets.py
10
+ ```
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
misc/logo.jpg ADDED
misc/logo.png DELETED

Git LFS Details

  • SHA256: 591bee6fa56315a84eeec47c5e04ff6331f842c773ce50b7a59e508b4d2904cf
  • Pointer size: 131 Bytes
  • Size of remote file: 684 kB
scripts/contrain-model-0.yaml DELETED
@@ -1,156 +0,0 @@
1
- # https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/config.json
2
-
3
- # The name of the model to pretrain. Choose from names in ``litgpt.config``. Mutually exclusive with
4
- # ``model_config``. (type: Optional[str], default: null)
5
- model_name: "Llama-3.2-1B"
6
-
7
- # A ``litgpt.Config`` object to define the model architecture. Mutually exclusive with
8
- # ``model_config``. (type: Optional[Config], default: null)
9
- model_config:
10
- padded_vocab_size: 65536
11
- vocab_size: 65536
12
- block_size: 131072
13
- n_layer: 32
14
- n_head: 16
15
- head_size: 64
16
- n_embd: 768
17
- n_query_groups: 4
18
- rotary_percentage: 1.0
19
- parallel_residual: false
20
- shared_attention_norm: false
21
- bias: false
22
- # attn_bias: true # qwen 2.5
23
- norm_class_name: "RMSNorm"
24
- mlp_class_name: "LLaMAMLP"
25
- intermediate_size: 2048
26
- # rope_base: 500000 # llama 3.2
27
- rope_base: 1000000 # qwen 2.5
28
- rope_adjustments: # llama 3.2
29
- factor: 32.0
30
- low_freq_factor: 1.0
31
- high_freq_factor: 4.0
32
- original_max_seq_len: 8192
33
-
34
- # Directory in which to save checkpoints and logs. If running in a Lightning Studio Job, look for it in
35
- # /teamspace/jobs/<job-name>/share. (type: <class 'Path'>, default: out/pretrain)
36
- out_dir: "../out/contrain-0/"
37
-
38
- # The precision to use for pretraining. Possible choices: "bf16-true", "bf16-mixed", "32-true". (type: Optional[str], default: null)
39
- # precision: bf16-mixed
40
- precision: bf16-true
41
-
42
- # Optional path to a checkpoint directory to initialize the model from.
43
- # Useful for continued pretraining. Mutually exclusive with ``resume``. (type: Optional[Path], default: null)
44
- initial_checkpoint_dir: "../out/pretrain-4-final-checkpoint/"
45
-
46
- # Path to a checkpoint directory to resume from in case training was interrupted, or ``True`` to resume
47
- # from the latest checkpoint in ``out_dir``. An error will be raised if no checkpoint is found. Passing
48
- # ``'auto'`` will resume from the latest checkpoint but not error if no checkpoint exists.
49
- # (type: Union[bool, Literal["auto"], Path], default: False)
50
- # resume:
51
-
52
- # Data-related arguments. If not provided, the default is ``litgpt.data.TinyLlama``.
53
- data:
54
- class_path: LitData
55
-
56
- init_args:
57
- data_path: "../contrain-data-0-4097-16388000/"
58
- num_workers: 32
59
-
60
- # Training-related arguments. See ``litgpt.args.TrainArgs`` for details
61
- train:
62
- # Number of optimizer steps between saving checkpoints (type: Optional[int], default: 1000)
63
- save_interval: 100
64
-
65
- # Number of iterations between logging calls (type: int, default: 1)
66
- log_interval: 1
67
-
68
- # Number of samples between optimizer steps across data-parallel ranks (type: int, default: 512)
69
- global_batch_size: 512
70
-
71
- # Number of samples per data-parallel rank (type: int, default: 4)
72
- micro_batch_size: 3
73
-
74
- # Number of iterations with learning rate warmup active (type: int, default: 2000)
75
- lr_warmup_steps: 0
76
-
77
- # Number of epochs to train on (type: Optional[int], default: null)
78
- epochs:
79
-
80
- # Total number of tokens to train on (type: Optional[int], default: 3000000000000)
81
- max_tokens: 1527816367 # 4_097 * 372_911
82
-
83
- # Limits the number of optimizer steps to run. (type: Optional[int], default: null)
84
- max_steps:
85
-
86
- # Limits the length of samples. Off by default (type: Optional[int], default: null)
87
- max_seq_length: 4097
88
-
89
- # Whether to tie the embedding weights with the language modeling head weights. (type: Optional[bool], default: False)
90
- tie_embeddings: true
91
-
92
- # (type: Optional[float], default: 1.0)
93
- max_norm: 1.0
94
-
95
- # (type: float, default: 4e-05)
96
- min_lr: 1e-06
97
-
98
- # Evaluation-related arguments. See ``litgpt.args.EvalArgs`` for details
99
- eval:
100
- # Number of optimizer steps between evaluation calls (type: int, default: 1000)
101
- interval: 25
102
-
103
- # Number of tokens to generate (type: Optional[int], default: null)
104
- max_new_tokens:
105
-
106
- # Number of iterations (type: int, default: 100)
107
- max_iters: 100
108
-
109
- # Whether to evaluate on the validation set at the beginning of the training
110
- initial_validation: false
111
-
112
- # Whether to evaluate on the validation set at the end the training
113
- final_validation: true
114
-
115
- # Optimizer-related arguments
116
- optimizer:
117
- class_path: grokadamw.GrokAdamW
118
-
119
- init_args:
120
- # (type: float, default: 0.001)
121
- lr: 1e-05
122
-
123
- # (type: float, default: 0.01)
124
- weight_decay: 1e-2
125
-
126
- # (type: tuple, default: (0.9,0.999))
127
- betas:
128
- - 0.9
129
- - 0.999
130
-
131
- # optimizer:
132
- # class_path: sophia_opt.SophiaG
133
- #
134
- # init_args:
135
- # lr: 4e-4
136
- # betas:
137
- # - 0.965
138
- # - 0.99
139
- # rho: 0.01
140
- # weight_decay: 1e-1
141
-
142
- # How many devices/GPUs to use. Uses all GPUs by default. (type: Union[int, str], default: auto)
143
- devices: auto
144
-
145
- # How many nodes to use. (type: int, default: 1)
146
- num_nodes: 1
147
-
148
- # Optional path to the tokenizer dir that was used for preprocessing the dataset. Only some data
149
- # module require this. (type: Optional[Path], default: null)
150
- tokenizer_dir: "../"
151
-
152
- # The name of the logger to send metrics to. (type: Literal['wandb', 'tensorboard', 'csv'], default: tensorboard)
153
- logger_name: "wandb"
154
-
155
- # The random seed to use for reproducibility. (type: int, default: 42)
156
- seed: 23
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
scripts/prepare_contrain_datasets.py DELETED
@@ -1,46 +0,0 @@
1
- from functools import partial
2
-
3
- from litgpt.tokenizer import Tokenizer
4
- from litdata import optimize, TokensLoader, StreamingDataset
5
- from transformers import AutoTokenizer
6
-
7
- from utils import tokenize_chat_fn
8
- from contrain_datasets import contrain_datasets
9
-
10
-
11
- #
12
- # optimize datasets
13
- #
14
- for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
15
- chunk_size = block_size * subchunk_size
16
- output_dir = f'../contrain-data-{i}-{block_size}-{chunk_size}'
17
-
18
- outputs = optimize(
19
- fn=partial(
20
- tokenize_chat_fn,
21
- hf_tokenizer=AutoTokenizer.from_pretrained('..', trust_remote_code=True, use_fast=True),
22
- tokenizer=Tokenizer('..'),
23
- ),
24
- inputs=contrain_datasets,
25
- output_dir=output_dir,
26
- chunk_size=chunk_size, # Number of tokens to store by chunks. This is roughly 64MB of tokens per chunk.
27
- num_workers=32,
28
- reorder_files=False,
29
- )
30
-
31
- #
32
- # total number of chunks in datasets
33
- #
34
- for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
35
- chunk_size = block_size * subchunk_size
36
- input_dir = f'../contrain-data-{i}-{block_size}-{chunk_size}'
37
-
38
- dataset = StreamingDataset(
39
- input_dir=input_dir,
40
- item_loader=TokensLoader(block_size=block_size),
41
- )
42
-
43
- print(f'{i=}, {block_size=}, {chunk_size=}, {len(dataset)=}, {len(dataset) * block_size=}')
44
-
45
- total_tokens = sum(len(data) for data in dataset)
46
- print(f'Total number of tokens in the optimized dataset {input_dir!r} is {total_tokens}')
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
scripts/prepare_pretrain_datasets.py CHANGED
@@ -4,8 +4,9 @@ from litgpt.tokenizer import Tokenizer
4
  from litdata import optimize, TokensLoader, StreamingDataset
5
  from transformers import AutoTokenizer
6
 
7
- from utils import tokenize_text_fn
8
- from pretrain_datasets import pretrain_datasets
 
9
 
10
 
11
  #
@@ -13,15 +14,15 @@ from pretrain_datasets import pretrain_datasets
13
  #
14
  for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
15
  chunk_size = block_size * subchunk_size
16
- output_dir = f'../pretrain-data-{i}-{block_size}-{chunk_size}'
17
 
18
  outputs = optimize(
19
  fn=partial(
20
- tokenize_text_fn,
21
  hf_tokenizer=AutoTokenizer.from_pretrained('..', trust_remote_code=True, use_fast=True),
22
  tokenizer=Tokenizer('..'),
23
  ),
24
- inputs=pretrain_datasets,
25
  output_dir=output_dir,
26
  chunk_size=chunk_size, # Number of tokens to store by chunks. This is roughly 64MB of tokens per chunk.
27
  num_workers=32,
@@ -36,7 +37,7 @@ for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
36
  #
37
  for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
38
  chunk_size = block_size * subchunk_size
39
- input_dir = f'../pretrain-data-{i}-{block_size}-{chunk_size}'
40
 
41
  dataset = StreamingDataset(
42
  input_dir=input_dir,
@@ -45,5 +46,7 @@ for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
45
 
46
  print(f'{i=}, {block_size=}, {chunk_size=}, {len(dataset)=}, {len(dataset) * block_size=}')
47
 
48
- total_tokens = sum(len(data) for data in dataset)
 
 
49
  print(f'Total number of tokens in the optimized dataset {input_dir!r} is {total_tokens}')
 
4
  from litdata import optimize, TokensLoader, StreamingDataset
5
  from transformers import AutoTokenizer
6
 
7
+ from utils import tokenize_fn
8
+ from pretrain_base_datasets import pretrain_base_datasets
9
+ from pretrain_instruct_datasets import pretrain_instruct_datasets
10
 
11
 
12
  #
 
14
  #
15
  for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
16
  chunk_size = block_size * subchunk_size
17
+ output_dir = f'../pretrain-data-{i}-{block_size}-{subchunk_size}'
18
 
19
  outputs = optimize(
20
  fn=partial(
21
+ tokenize_fn,
22
  hf_tokenizer=AutoTokenizer.from_pretrained('..', trust_remote_code=True, use_fast=True),
23
  tokenizer=Tokenizer('..'),
24
  ),
25
+ inputs=pretrain_base_datasets + pretrain_instruct_datasets,
26
  output_dir=output_dir,
27
  chunk_size=chunk_size, # Number of tokens to store by chunks. This is roughly 64MB of tokens per chunk.
28
  num_workers=32,
 
37
  #
38
  for i, (block_size, subchunk_size) in enumerate([(4097, 4000)]):
39
  chunk_size = block_size * subchunk_size
40
+ input_dir = f'../pretrain-data-{i}-{block_size}-{subchunk_size}'
41
 
42
  dataset = StreamingDataset(
43
  input_dir=input_dir,
 
46
 
47
  print(f'{i=}, {block_size=}, {chunk_size=}, {len(dataset)=}, {len(dataset) * block_size=}')
48
 
49
+ # total_tokens = sum(len(data) for data in dataset)
50
+ # print(f'Total number of tokens in the optimized dataset {input_dir!r} is {total_tokens}')
51
+ total_tokens = len(dataset) * block_size
52
  print(f'Total number of tokens in the optimized dataset {input_dir!r} is {total_tokens}')
scripts/{pretrain-model-0.yaml → pretrain-model.yaml} RENAMED
@@ -27,7 +27,7 @@ model_config:
27
 
28
  # Directory in which to save checkpoints and logs. If running in a Lightning Studio Job, look for it in
29
  # /teamspace/jobs/<job-name>/share. (type: <class 'Path'>, default: out/pretrain)
30
- out_dir: "../out/pretrain-0/"
31
 
32
  # The precision to use for pretraining. Possible choices: "bf16-true", "bf16-mixed", "32-true". (type: Optional[str], default: null)
33
  # precision: bf16-mixed
 
27
 
28
  # Directory in which to save checkpoints and logs. If running in a Lightning Studio Job, look for it in
29
  # /teamspace/jobs/<job-name>/share. (type: <class 'Path'>, default: out/pretrain)
30
+ out_dir: "../out/pretrain/"
31
 
32
  # The precision to use for pretraining. Possible choices: "bf16-true", "bf16-mixed", "32-true". (type: Optional[str], default: null)
33
  # precision: bf16-mixed
scripts/{pretrain_datasets.py → pretrain_base_datasets.py} RENAMED
@@ -1,25 +1,25 @@
1
- pretrain_datasets = [
2
  #
3
  # multilingual
4
  #
5
  # 3.17 GB, 2,226,907
6
  *[
7
- {'path': 'ontocord/fineweb-permissive-multilingual-2m', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['text']}
8
  for i in range(0, 100, 10)
9
  ],
10
  # 1.64 GB, 1,001,000
11
  *[
12
- {'path': 'distily/c4_multilingual_1M', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['text']}
13
  for i in range(0, 100, 10)
14
  ],
15
  # 3.8 GB, 19,454,996
16
  *[
17
- {'path': 'sentence-transformers/parallel-sentences-wikimatrix', 'data_dir': 'all', 'split': f'train[{i}%:{i + 5}%]', 'format': lambda n: n['non_english']}
18
  for i in range(0, 100, 5)
19
  ],
20
  # 193 MB, 1,141,967
21
  *[
22
- {'path': 'xu-song/cc100-samples', 'name': name, 'split': 'train', 'format': lambda n: n['text']}
23
  for name in [
24
  'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'bn_rom', 'br',
25
  'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'en', 'eo', 'es',
@@ -41,24 +41,24 @@ pretrain_datasets = [
41
  # general knowledge
42
  #
43
  # 65.1 MB, 7,819
44
- {'path': 'Sketched33/Cities_Wikipedia_Information', 'format': lambda n: n['wikipedia_content']},
45
  # 135 MB, 1,795
46
- {'path': 'open-phi/textbooks', 'format': lambda n: n['markdown']},
47
  # 631 MB, 111,048
48
- {'path': 'open-phi/programming_books_llama', 'format': lambda n: n['markdown']},
49
 
50
  #
51
  # misc
52
  #
53
  # 472 KB, 5,034
54
- {'path': 'badrex/llm-emoji-dataset', 'format': '{short description}. {LLM description}. {character}'},
55
 
56
  #
57
  # math
58
  #
59
  # 12.6 GB, 14M rows
60
  *[
61
- {'path': 'nvidia/OpenMathInstruct-2', 'split': f'train[{i}%:{i + 5}%]', 'format': '{problem} {generated_solution} {expected_answer}'}
62
  for i in range(0, 100, 5)
63
  ],
64
 
@@ -67,11 +67,11 @@ pretrain_datasets = [
67
  #
68
  # 1.44 GB, 63,357
69
  *[
70
- {'path': 'neuralwork/arxiver', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['abstract']}
71
  for i in range(0, 100, 10)
72
  ],
73
  *[
74
- {'path': 'neuralwork/arxiver', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['markdown']}
75
  for i in range(0, 100, 10)
76
  ],
77
 
@@ -80,7 +80,7 @@ pretrain_datasets = [
80
  #
81
  # 7.81 GB, ~2,804,025
82
  *[
83
- {'path': 'rombodawg/code_bagel_hermes-2.5', 'split': f'train[{i}%:{i + 10}%]', 'format': '{input} {output}'}
84
  for i in range(0, 100, 10)
85
  ],
86
 
@@ -89,9 +89,9 @@ pretrain_datasets = [
89
  #
90
  # 3.18 GB, 1,010,500 - paper says that extracted is 6GB
91
  *[
92
- {'path': 'JeanKaddour/minipile', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['text']}
93
  for i in range(0, 100, 10)
94
  ],
95
- {'path': 'JeanKaddour/minipile', 'split': 'validation', 'format': lambda n: n['text']},
96
- {'path': 'JeanKaddour/minipile', 'split': 'test', 'format': lambda n: n['text']},
97
  ]
 
1
+ pretrain_base_datasets = [
2
  #
3
  # multilingual
4
  #
5
  # 3.17 GB, 2,226,907
6
  *[
7
+ {'kind': 'base', 'path': 'ontocord/fineweb-permissive-multilingual-2m', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['text']}
8
  for i in range(0, 100, 10)
9
  ],
10
  # 1.64 GB, 1,001,000
11
  *[
12
+ {'kind': 'base', 'path': 'distily/c4_multilingual_1M', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['text']}
13
  for i in range(0, 100, 10)
14
  ],
15
  # 3.8 GB, 19,454,996
16
  *[
17
+ {'kind': 'base', 'path': 'sentence-transformers/parallel-sentences-wikimatrix', 'data_dir': 'all', 'split': f'train[{i}%:{i + 5}%]', 'format': lambda n: n['non_english']}
18
  for i in range(0, 100, 5)
19
  ],
20
  # 193 MB, 1,141,967
21
  *[
22
+ {'kind': 'base', 'path': 'xu-song/cc100-samples', 'name': name, 'split': 'train', 'format': lambda n: n['text']}
23
  for name in [
24
  'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'bn_rom', 'br',
25
  'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'en', 'eo', 'es',
 
41
  # general knowledge
42
  #
43
  # 65.1 MB, 7,819
44
+ {'kind': 'base', 'path': 'Sketched33/Cities_Wikipedia_Information', 'format': lambda n: n['wikipedia_content']},
45
  # 135 MB, 1,795
46
+ {'kind': 'base', 'path': 'open-phi/textbooks', 'format': lambda n: n['markdown']},
47
  # 631 MB, 111,048
48
+ {'kind': 'base', 'path': 'open-phi/programming_books_llama', 'format': lambda n: n['markdown']},
49
 
50
  #
51
  # misc
52
  #
53
  # 472 KB, 5,034
54
+ {'kind': 'base', 'path': 'badrex/llm-emoji-dataset', 'format': '{short description}. {LLM description}. {character}'},
55
 
56
  #
57
  # math
58
  #
59
  # 12.6 GB, 14M rows
60
  *[
61
+ {'kind': 'base', 'path': 'nvidia/OpenMathInstruct-2', 'split': f'train[{i}%:{i + 5}%]', 'format': '{problem} {generated_solution} {expected_answer}'}
62
  for i in range(0, 100, 5)
63
  ],
64
 
 
67
  #
68
  # 1.44 GB, 63,357
69
  *[
70
+ {'kind': 'base', 'path': 'neuralwork/arxiver', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['abstract']}
71
  for i in range(0, 100, 10)
72
  ],
73
  *[
74
+ {'kind': 'base', 'path': 'neuralwork/arxiver', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['markdown']}
75
  for i in range(0, 100, 10)
76
  ],
77
 
 
80
  #
81
  # 7.81 GB, ~2,804,025
82
  *[
83
+ {'kind': 'base', 'path': 'rombodawg/code_bagel_hermes-2.5', 'split': f'train[{i}%:{i + 10}%]', 'format': '{input} {output}'}
84
  for i in range(0, 100, 10)
85
  ],
86
 
 
89
  #
90
  # 3.18 GB, 1,010,500 - paper says that extracted is 6GB
91
  *[
92
+ {'kind': 'base', 'path': 'JeanKaddour/minipile', 'split': f'train[{i}%:{i + 10}%]', 'format': lambda n: n['text']}
93
  for i in range(0, 100, 10)
94
  ],
95
+ {'kind': 'base', 'path': 'JeanKaddour/minipile', 'split': 'validation', 'format': lambda n: n['text']},
96
+ {'kind': 'base', 'path': 'JeanKaddour/minipile', 'split': 'test', 'format': lambda n: n['text']},
97
  ]
scripts/{contrain_datasets.py → pretrain_instruct_datasets.py} RENAMED
@@ -11,29 +11,19 @@ roles_map = {
11
  }
12
 
13
 
14
- contrain_datasets = [
15
  #
16
  # general instructs
17
  #
18
  ## 138 MB, 205,568
19
- # {'path': 'CohereForAI/aya_dataset', 'format': lambda n: n['inputs']},
20
- # {'path': 'CohereForAI/aya_dataset', 'format': lambda n: n['targets']},
21
- {'path': 'CohereForAI/aya_dataset', 'transform': lambda r: [
22
  {'role': 'user', 'content': r['inputs']},
23
  {'role': 'assistant', 'content': r['targets']},
24
  ]},
25
 
26
- # *[
27
- # # ~3 GB, 4,976,850
28
- # {'path': 'saillab/taco-datasets', 'data_dir': name, 'split': 'train', 'format': '{instruction} {input} {output}'}
29
- # for name in [
30
- # 'multilingual-instruction-tuning-dataset /multilingual-alpaca-52k-gpt-4',
31
- # 'multilingual-instruction-tuning-dataset /multilinugal-dolly-15k',
32
- # ]
33
- # ],
34
  *[
35
- # ~3 GB, 4,976,850
36
- {'path': 'saillab/taco-datasets', 'data_dir': name, 'split': 'train', 'transform': lambda r: [
37
  {'role': 'system', 'content': r['instruction']},
38
  {'role': 'user', 'content': r['input']},
39
  {'role': 'assistant', 'content': r['output']},
@@ -54,7 +44,7 @@ contrain_datasets = [
54
  # Post-training-Data-Flywheel/AutoIF-instruct-61k 61,492
55
  # mlabonne/lmsys-arena-human-preference-55k-sharegpt 57,362
56
  *[
57
- {'path': 'mlabonne/open-perfectblend', 'split': f'train[{i}%:{i + 20}%]', 'field': 'conversations', 'transform': lambda msgs: [
58
  {'role': roles_map[m['from']], 'content': m['value']}
59
  for m in msgs
60
  ]}
@@ -71,7 +61,7 @@ contrain_datasets = [
71
  # - cognitivecomputations/SystemChat-2.0
72
  # - arcee-ai/qwen2-72b-magpie-en
73
  *[
74
- {'path': 'arcee-ai/The-Tome', 'split': f'train[{i}%:{i + 20}%]', 'field': 'conversations', 'transform': lambda msgs: [
75
  {'role': roles_map[m['from']], 'content': m['value']}
76
  for m in msgs
77
  ]}
@@ -133,7 +123,7 @@ contrain_datasets = [
133
  # General Instruct: (rombodawg/OpenHermes-2.5-Uncensored)
134
  # teknium/OpenHermes-2.5
135
  *[
136
- {'path': 'rombodawg/Everything_Instruct_Multilingual', 'split': f'train[{i}%:{i + 20}%]', 'transform': lambda r: [
137
  {'role': 'system', 'content': r['instruction']},
138
  {'role': 'user', 'content': r['input']},
139
  {'role': 'assistant', 'content': r['output']},
@@ -160,7 +150,7 @@ contrain_datasets = [
160
  # SciRIFF (ODC-BY-1.0), 10,000 prompts (Wadden et al., 2024)
161
  # Evol CodeAlpaca (Apache 2.0), 107,276 prompts (Luo et al., 2023)
162
  *[
163
- {'path': 'allenai/tulu-3-sft-mixture', 'split': f'train[{i}%:{i + 20}%]', 'field': 'messages'}
164
  for i in range(0, 100, 20)
165
  ],
166
 
@@ -168,7 +158,7 @@ contrain_datasets = [
168
  # tool/function calling
169
  #
170
  # 65.7 MB, 11,578
171
- {'path': 'NousResearch/hermes-function-calling-v1', 'field': 'conversations', 'transform': lambda msgs: [
172
  {'role': roles_map[m['from']], 'content': m['value']}
173
  for m in msgs
174
  ]},
@@ -178,7 +168,7 @@ contrain_datasets = [
178
  #
179
  # 1.51 GB, 485,874
180
  *[
181
- {'path': 'arcee-ai/agent-data', 'split': f'train[{i}%:{i + 20}%]', 'field': 'conversations', 'transform': lambda msgs: [
182
  {'role': roles_map[m['from']], 'content': m['value']}
183
  for m in msgs
184
  ]}
@@ -186,7 +176,7 @@ contrain_datasets = [
186
  ],
187
  # 2.21 GB, 1,046,410
188
  *[
189
- {'path': 'microsoft/orca-agentinstruct-1M-v1', 'split': split, 'field': 'messages', 'transform': lambda msgs: json.loads(msgs)}
190
  for split in [
191
  'creative_content', 'text_modification', 'struct2text_flow', 'rc', 'rag',
192
  'text_extraction', 'mcq', 'follow_up', 'analytical_reasoning', 'fermi', 'fs_cot_flow',
@@ -199,19 +189,19 @@ contrain_datasets = [
199
  #
200
  *[
201
  # 10.8 MB, 15,770
202
- {'path': 'AtlasUnified/Atlas-Reasoning', 'data_files': 'reasoning.csv', 'transform': lambda r: [
203
  {'role': 'user', 'content': r['Prompt']},
204
  {'role': 'assistant', 'content': r['Step-by-step reasoning'] + '\n' + r['Solution']},
205
  ]},
206
  ],
207
  # 1.23 GB, 859,594
208
  *[
209
- {'path': 'AI-MO/NuminaMath-CoT', 'split': f'train[{i}%:{i + 20}%]', 'field': 'messages'}
210
  for i in range(0, 100, 20)
211
  ],
212
  # 148 MB, 72,540
213
  *[
214
- {'path': 'AI-MO/NuminaMath-TIR', 'split': f'train[{i}%:{i + 20}%]', 'field': 'messages'}
215
  for i in range(0, 100, 20)
216
  ],
217
 
@@ -219,25 +209,25 @@ contrain_datasets = [
219
  # math reasoning
220
  #
221
  # 8.99 MB, 6,914
222
- {'path': 'thesven/gsm8k-reasoning', 'transform': lambda r: [
223
  {'role': 'user', 'content': r['question']},
224
  {'role': 'assistant', 'content': (r['generation'] or '') + '\n' + r['answer'] + '\n' + r['short_answer']},
225
  ]},
226
 
227
  # 1.79 MB, 3,963
228
- {'path': 'AlgorithmicResearchGroup/math_reasoning_autoformalization_track', 'transform': lambda r: [
229
  {'role': 'user', 'content': r['informal_statement']},
230
  {'role': 'assistant', 'content': r['informal_proof'] + '\n' + r['formal_proof']},
231
  ]},
232
 
233
  # 307 MB, 19,944
234
- {'path': 'KingNish/reasoning-base-20k', 'transform': lambda r: [
235
  {'role': 'user', 'content': r['user']},
236
  {'role': 'assistant', 'content': r['reasoning'] + '\n' + r['assistant']},
237
  ]},
238
 
239
  # 9.45 MB, 10,000
240
- {'path': 'Aarushhh/math-reasoning-10k', 'transform': lambda r: [
241
  {'role': 'user', 'content': r['problem']},
242
  {'role': 'assistant', 'content': r['plan'] + '\n' + r['solution']},
243
  ]},
@@ -246,25 +236,25 @@ contrain_datasets = [
246
  # reflection
247
  #
248
  # 4.17 MB, 1,000
249
- {'path': 'dvilasuero/reflection-v1-gpt-4o-judge', 'transform': lambda r: [
250
  {'role': 'system', 'content': r['system']},
251
  {'role': 'user', 'content': r['prompt']},
252
  {'role': 'assistant', 'content': r['response']},
253
  ]},
254
  # 12.4 MB, 3,000
255
- {'path': 'dvilasuero/reflection-v1-openai-o-mini-judge', 'transform': lambda r: [
256
  {'role': 'system', 'content': r['system']},
257
  {'role': 'user', 'content': r['prompt']},
258
  {'role': 'assistant', 'content': r['response']},
259
  ]},
260
  # 70.8 MB, 36,549
261
- {'path': 'dvilasuero/reflection-v1-final-dedup', 'transform': lambda r: [
262
  {'role': 'system', 'content': r['system']},
263
  {'role': 'user', 'content': r['prompt']},
264
  {'role': 'assistant', 'content': r['response']},
265
  ]},
266
  # 30.6 MB, 25,391
267
- {'path': 'flozi00/reflection-qwen2.5-72b-260924', 'transform': lambda r: [
268
  r['system'][0],
269
  {'role': 'user', 'content': r['input']},
270
  {'role': 'assistant', 'content': r['reflection'] + '\n' + r['output']},
@@ -273,8 +263,6 @@ contrain_datasets = [
273
  #
274
  # general instructs
275
  #
276
- # # 971 MB, 484,570
277
- # {'path': 'HuggingFaceTB/smol-smoltalk', 'field': 'messages'},
278
  # 4.15 GB, 2,197,730
279
- {'path': 'HuggingFaceTB/smoltalk', 'name': 'all', 'field': 'messages'},
280
  ]
 
11
  }
12
 
13
 
14
+ pretrain_instruct_datasets = [
15
  #
16
  # general instructs
17
  #
18
  ## 138 MB, 205,568
19
+ {'kind': 'instruct', 'path': 'CohereForAI/aya_dataset', 'transform': lambda r: [
 
 
20
  {'role': 'user', 'content': r['inputs']},
21
  {'role': 'assistant', 'content': r['targets']},
22
  ]},
23
 
24
+ # ~3 GB, 4,976,850
 
 
 
 
 
 
 
25
  *[
26
+ {'kind': 'instruct', 'path': 'saillab/taco-datasets', 'data_dir': name, 'split': 'train', 'transform': lambda r: [
 
27
  {'role': 'system', 'content': r['instruction']},
28
  {'role': 'user', 'content': r['input']},
29
  {'role': 'assistant', 'content': r['output']},
 
44
  # Post-training-Data-Flywheel/AutoIF-instruct-61k 61,492
45
  # mlabonne/lmsys-arena-human-preference-55k-sharegpt 57,362
46
  *[
47
+ {'kind': 'instruct', 'path': 'mlabonne/open-perfectblend', 'split': f'train[{i}%:{i + 20}%]', 'field': 'conversations', 'transform': lambda msgs: [
48
  {'role': roles_map[m['from']], 'content': m['value']}
49
  for m in msgs
50
  ]}
 
61
  # - cognitivecomputations/SystemChat-2.0
62
  # - arcee-ai/qwen2-72b-magpie-en
63
  *[
64
+ {'kind': 'instruct', 'path': 'arcee-ai/The-Tome', 'split': f'train[{i}%:{i + 20}%]', 'field': 'conversations', 'transform': lambda msgs: [
65
  {'role': roles_map[m['from']], 'content': m['value']}
66
  for m in msgs
67
  ]}
 
123
  # General Instruct: (rombodawg/OpenHermes-2.5-Uncensored)
124
  # teknium/OpenHermes-2.5
125
  *[
126
+ {'kind': 'instruct', 'path': 'rombodawg/Everything_Instruct_Multilingual', 'split': f'train[{i}%:{i + 20}%]', 'transform': lambda r: [
127
  {'role': 'system', 'content': r['instruction']},
128
  {'role': 'user', 'content': r['input']},
129
  {'role': 'assistant', 'content': r['output']},
 
150
  # SciRIFF (ODC-BY-1.0), 10,000 prompts (Wadden et al., 2024)
151
  # Evol CodeAlpaca (Apache 2.0), 107,276 prompts (Luo et al., 2023)
152
  *[
153
+ {'kind': 'instruct', 'path': 'allenai/tulu-3-sft-mixture', 'split': f'train[{i}%:{i + 20}%]', 'field': 'messages'}
154
  for i in range(0, 100, 20)
155
  ],
156
 
 
158
  # tool/function calling
159
  #
160
  # 65.7 MB, 11,578
161
+ {'kind': 'instruct', 'path': 'NousResearch/hermes-function-calling-v1', 'field': 'conversations', 'transform': lambda msgs: [
162
  {'role': roles_map[m['from']], 'content': m['value']}
163
  for m in msgs
164
  ]},
 
168
  #
169
  # 1.51 GB, 485,874
170
  *[
171
+ {'kind': 'instruct', 'path': 'arcee-ai/agent-data', 'split': f'train[{i}%:{i + 20}%]', 'field': 'conversations', 'transform': lambda msgs: [
172
  {'role': roles_map[m['from']], 'content': m['value']}
173
  for m in msgs
174
  ]}
 
176
  ],
177
  # 2.21 GB, 1,046,410
178
  *[
179
+ {'kind': 'instruct', 'path': 'microsoft/orca-agentinstruct-1M-v1', 'split': split, 'field': 'messages', 'transform': lambda msgs: json.loads(msgs)}
180
  for split in [
181
  'creative_content', 'text_modification', 'struct2text_flow', 'rc', 'rag',
182
  'text_extraction', 'mcq', 'follow_up', 'analytical_reasoning', 'fermi', 'fs_cot_flow',
 
189
  #
190
  *[
191
  # 10.8 MB, 15,770
192
+ {'kind': 'instruct', 'path': 'AtlasUnified/Atlas-Reasoning', 'data_files': 'reasoning.csv', 'transform': lambda r: [
193
  {'role': 'user', 'content': r['Prompt']},
194
  {'role': 'assistant', 'content': r['Step-by-step reasoning'] + '\n' + r['Solution']},
195
  ]},
196
  ],
197
  # 1.23 GB, 859,594
198
  *[
199
+ {'kind': 'instruct', 'path': 'AI-MO/NuminaMath-CoT', 'split': f'train[{i}%:{i + 20}%]', 'field': 'messages'}
200
  for i in range(0, 100, 20)
201
  ],
202
  # 148 MB, 72,540
203
  *[
204
+ {'kind': 'instruct', 'path': 'AI-MO/NuminaMath-TIR', 'split': f'train[{i}%:{i + 20}%]', 'field': 'messages'}
205
  for i in range(0, 100, 20)
206
  ],
207
 
 
209
  # math reasoning
210
  #
211
  # 8.99 MB, 6,914
212
+ {'kind': 'instruct', 'path': 'thesven/gsm8k-reasoning', 'transform': lambda r: [
213
  {'role': 'user', 'content': r['question']},
214
  {'role': 'assistant', 'content': (r['generation'] or '') + '\n' + r['answer'] + '\n' + r['short_answer']},
215
  ]},
216
 
217
  # 1.79 MB, 3,963
218
+ {'kind': 'instruct', 'path': 'AlgorithmicResearchGroup/math_reasoning_autoformalization_track', 'transform': lambda r: [
219
  {'role': 'user', 'content': r['informal_statement']},
220
  {'role': 'assistant', 'content': r['informal_proof'] + '\n' + r['formal_proof']},
221
  ]},
222
 
223
  # 307 MB, 19,944
224
+ {'kind': 'instruct', 'path': 'KingNish/reasoning-base-20k', 'transform': lambda r: [
225
  {'role': 'user', 'content': r['user']},
226
  {'role': 'assistant', 'content': r['reasoning'] + '\n' + r['assistant']},
227
  ]},
228
 
229
  # 9.45 MB, 10,000
230
+ {'kind': 'instruct', 'path': 'Aarushhh/math-reasoning-10k', 'transform': lambda r: [
231
  {'role': 'user', 'content': r['problem']},
232
  {'role': 'assistant', 'content': r['plan'] + '\n' + r['solution']},
233
  ]},
 
236
  # reflection
237
  #
238
  # 4.17 MB, 1,000
239
+ {'kind': 'instruct', 'path': 'dvilasuero/reflection-v1-gpt-4o-judge', 'transform': lambda r: [
240
  {'role': 'system', 'content': r['system']},
241
  {'role': 'user', 'content': r['prompt']},
242
  {'role': 'assistant', 'content': r['response']},
243
  ]},
244
  # 12.4 MB, 3,000
245
+ {'kind': 'instruct', 'path': 'dvilasuero/reflection-v1-openai-o-mini-judge', 'transform': lambda r: [
246
  {'role': 'system', 'content': r['system']},
247
  {'role': 'user', 'content': r['prompt']},
248
  {'role': 'assistant', 'content': r['response']},
249
  ]},
250
  # 70.8 MB, 36,549
251
+ {'kind': 'instruct', 'path': 'dvilasuero/reflection-v1-final-dedup', 'transform': lambda r: [
252
  {'role': 'system', 'content': r['system']},
253
  {'role': 'user', 'content': r['prompt']},
254
  {'role': 'assistant', 'content': r['response']},
255
  ]},
256
  # 30.6 MB, 25,391
257
+ {'kind': 'instruct', 'path': 'flozi00/reflection-qwen2.5-72b-260924', 'transform': lambda r: [
258
  r['system'][0],
259
  {'role': 'user', 'content': r['input']},
260
  {'role': 'assistant', 'content': r['reflection'] + '\n' + r['output']},
 
263
  #
264
  # general instructs
265
  #
 
 
266
  # 4.15 GB, 2,197,730
267
+ {'kind': 'instruct', 'path': 'HuggingFaceTB/smoltalk', 'name': 'all', 'field': 'messages'},
268
  ]
scripts/train_tokenizer.py CHANGED
@@ -10,10 +10,11 @@ from tokenizer_datasets import tokenizer_datasets
10
  # special_tokens
11
  #
12
  bos_token = '<|endoftext|>'
13
- eos_token = '<|endoftext|>'
14
  pad_token = '<|endoftext|>'
15
 
16
  special_tokens = [
 
17
  eos_token,
18
  '<|im_start|>',
19
  '<|im_end|>',
@@ -74,8 +75,6 @@ CHAT_TEMPLATE = (
74
 
75
  "{% if add_generation_prompt %}"
76
  "{{ '<|im_start|>assistant\n' }}"
77
- "{% else %}"
78
- "{{ eos_token }}"
79
  "{% endif %}"
80
  )
81
 
 
10
  # special_tokens
11
  #
12
  bos_token = '<|endoftext|>'
13
+ eos_token = '<|im_end|>'
14
  pad_token = '<|endoftext|>'
15
 
16
  special_tokens = [
17
+ bos_token,
18
  eos_token,
19
  '<|im_start|>',
20
  '<|im_end|>',
 
75
 
76
  "{% if add_generation_prompt %}"
77
  "{{ '<|im_start|>assistant\n' }}"
 
 
78
  "{% endif %}"
79
  )
80
 
scripts/utils.py CHANGED
@@ -1,5 +1,5 @@
1
  import gc
2
- from typing import Union, Optional, Iterator, Callable
3
 
4
  import torch
5
  from datasets import load_dataset
@@ -7,7 +7,8 @@ from litgpt.tokenizer import Tokenizer
7
  from transformers import AutoTokenizer
8
 
9
 
10
- def batch_text_iterator(path: str,
 
11
  name: Optional[str]=None,
12
  data_dir: Optional[str]=None,
13
  data_files: Optional[str]=None,
@@ -17,6 +18,7 @@ def batch_text_iterator(path: str,
17
  num_proc: Optional[int]=None,
18
  format: Optional[Callable|str]=None) -> Iterator[str]:
19
  assert isinstance(format, str) or callable(format), f'{path=} {format=}'
 
20
 
21
  dataset = load_dataset(path=path,
22
  name=name,
@@ -41,7 +43,8 @@ def batch_text_iterator(path: str,
41
  gc.collect()
42
 
43
 
44
- def batch_chat_iterator(path: str,
 
45
  name: Optional[str]=None,
46
  data_dir: Optional[str]=None,
47
  data_files: Optional[str]=None,
@@ -51,6 +54,7 @@ def batch_chat_iterator(path: str,
51
  num_proc: Optional[int]=None,
52
  field: Optional[str]=None,
53
  transform: Optional[Callable]=None) -> Iterator[list[dict[str, str]]]:
 
54
 
55
  dataset = load_dataset(path=path,
56
  name=name,
@@ -94,3 +98,17 @@ def tokenize_chat_fn(dataset_config: dict, hf_tokenizer: AutoTokenizer, tokenize
94
  text: str = hf_tokenizer.apply_chat_template(messages, tokenize=False)
95
  text_ids: torch.Tensor = tokenizer.encode(text, bos=False, eos=False)
96
  yield text_ids
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  import gc
2
+ from typing import Optional, Iterator, Callable
3
 
4
  import torch
5
  from datasets import load_dataset
 
7
  from transformers import AutoTokenizer
8
 
9
 
10
+ def batch_text_iterator(kind: str,
11
+ path: str,
12
  name: Optional[str]=None,
13
  data_dir: Optional[str]=None,
14
  data_files: Optional[str]=None,
 
18
  num_proc: Optional[int]=None,
19
  format: Optional[Callable|str]=None) -> Iterator[str]:
20
  assert isinstance(format, str) or callable(format), f'{path=} {format=}'
21
+ assert kind == 'base'
22
 
23
  dataset = load_dataset(path=path,
24
  name=name,
 
43
  gc.collect()
44
 
45
 
46
+ def batch_chat_iterator(kind: str,
47
+ path: str,
48
  name: Optional[str]=None,
49
  data_dir: Optional[str]=None,
50
  data_files: Optional[str]=None,
 
54
  num_proc: Optional[int]=None,
55
  field: Optional[str]=None,
56
  transform: Optional[Callable]=None) -> Iterator[list[dict[str, str]]]:
57
+ assert kind == 'instruct'
58
 
59
  dataset = load_dataset(path=path,
60
  name=name,
 
98
  text: str = hf_tokenizer.apply_chat_template(messages, tokenize=False)
99
  text_ids: torch.Tensor = tokenizer.encode(text, bos=False, eos=False)
100
  yield text_ids
101
+
102
+
103
+ def tokenize_fn(dataset_config: dict, hf_tokenizer: AutoTokenizer, tokenizer: Tokenizer) -> Iterator[torch.Tensor]:
104
+ if dataset_config['kind'] == 'base':
105
+ for text in batch_text_iterator(**dataset_config):
106
+ text_ids: torch.Tensor = tokenizer.encode(text, bos=False, eos=True)
107
+ yield text_ids
108
+ elif dataset_config['kind'] == 'instruct':
109
+ for messages in batch_chat_iterator(**dataset_config):
110
+ text: str = hf_tokenizer.apply_chat_template(messages, tokenize=False)
111
+ text_ids: torch.Tensor = tokenizer.encode(text, bos=False, eos=False)
112
+ yield text_ids
113
+ else:
114
+ raise ValueError(dataset_config['kind'])
special_tokens_map.json DELETED
@@ -1,5 +0,0 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>"
5
- }
 
 
 
 
 
 
tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bf3b7e915e35508fc236a489c2d9f10870d5c3d6564bbe982d3e225ecf1484f
3
- size 9650692
 
 
 
 
tokenizer_config.json DELETED
@@ -1,4108 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<|endoftext|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<|im_start|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "<|im_end|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "system",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "user",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "5": {
44
- "content": "assistant",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "<|reserved_0|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "7": {
60
- "content": "<|reserved_1|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "8": {
68
- "content": "<|reserved_2|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "9": {
76
- "content": "<|reserved_3|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "10": {
84
- "content": "<|reserved_4|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "11": {
92
- "content": "<|reserved_5|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "12": {
100
- "content": "<|reserved_6|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "13": {
108
- "content": "<|reserved_7|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "14": {
116
- "content": "<|reserved_8|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "15": {
124
- "content": "<|reserved_9|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "16": {
132
- "content": "<|reserved_10|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "17": {
140
- "content": "<|reserved_11|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "18": {
148
- "content": "<|reserved_12|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "19": {
156
- "content": "<|reserved_13|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "20": {
164
- "content": "<|reserved_14|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "21": {
172
- "content": "<|reserved_15|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "22": {
180
- "content": "<|reserved_16|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "23": {
188
- "content": "<|reserved_17|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "24": {
196
- "content": "<|reserved_18|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "25": {
204
- "content": "<|reserved_19|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "26": {
212
- "content": "<|reserved_20|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "27": {
220
- "content": "<|reserved_21|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "28": {
228
- "content": "<|reserved_22|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "29": {
236
- "content": "<|reserved_23|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "30": {
244
- "content": "<|reserved_24|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "31": {
252
- "content": "<|reserved_25|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "32": {
260
- "content": "<|reserved_26|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "33": {
268
- "content": "<|reserved_27|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "34": {
276
- "content": "<|reserved_28|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "35": {
284
- "content": "<|reserved_29|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "36": {
292
- "content": "<|reserved_30|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "37": {
300
- "content": "<|reserved_31|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "38": {
308
- "content": "<|reserved_32|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "39": {
316
- "content": "<|reserved_33|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "40": {
324
- "content": "<|reserved_34|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "41": {
332
- "content": "<|reserved_35|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "42": {
340
- "content": "<|reserved_36|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "43": {
348
- "content": "<|reserved_37|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "44": {
356
- "content": "<|reserved_38|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "45": {
364
- "content": "<|reserved_39|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "46": {
372
- "content": "<|reserved_40|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "47": {
380
- "content": "<|reserved_41|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "48": {
388
- "content": "<|reserved_42|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "49": {
396
- "content": "<|reserved_43|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "50": {
404
- "content": "<|reserved_44|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "51": {
412
- "content": "<|reserved_45|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "52": {
420
- "content": "<|reserved_46|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "53": {
428
- "content": "<|reserved_47|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "54": {
436
- "content": "<|reserved_48|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "55": {
444
- "content": "<|reserved_49|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "56": {
452
- "content": "<|reserved_50|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "57": {
460
- "content": "<|reserved_51|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "58": {
468
- "content": "<|reserved_52|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "59": {
476
- "content": "<|reserved_53|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "60": {
484
- "content": "<|reserved_54|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "61": {
492
- "content": "<|reserved_55|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "62": {
500
- "content": "<|reserved_56|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "63": {
508
- "content": "<|reserved_57|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "64": {
516
- "content": "<|reserved_58|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "65": {
524
- "content": "<|reserved_59|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "66": {
532
- "content": "<|reserved_60|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "67": {
540
- "content": "<|reserved_61|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "68": {
548
- "content": "<|reserved_62|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "69": {
556
- "content": "<|reserved_63|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "70": {
564
- "content": "<|reserved_64|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "71": {
572
- "content": "<|reserved_65|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "72": {
580
- "content": "<|reserved_66|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "73": {
588
- "content": "<|reserved_67|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "74": {
596
- "content": "<|reserved_68|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "75": {
604
- "content": "<|reserved_69|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "76": {
612
- "content": "<|reserved_70|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "77": {
620
- "content": "<|reserved_71|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "78": {
628
- "content": "<|reserved_72|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "79": {
636
- "content": "<|reserved_73|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "80": {
644
- "content": "<|reserved_74|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "81": {
652
- "content": "<|reserved_75|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "82": {
660
- "content": "<|reserved_76|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "83": {
668
- "content": "<|reserved_77|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "84": {
676
- "content": "<|reserved_78|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "85": {
684
- "content": "<|reserved_79|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "86": {
692
- "content": "<|reserved_80|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "87": {
700
- "content": "<|reserved_81|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "88": {
708
- "content": "<|reserved_82|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "89": {
716
- "content": "<|reserved_83|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "90": {
724
- "content": "<|reserved_84|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "91": {
732
- "content": "<|reserved_85|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "92": {
740
- "content": "<|reserved_86|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "93": {
748
- "content": "<|reserved_87|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "94": {
756
- "content": "<|reserved_88|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "95": {
764
- "content": "<|reserved_89|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "96": {
772
- "content": "<|reserved_90|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "97": {
780
- "content": "<|reserved_91|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "98": {
788
- "content": "<|reserved_92|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "99": {
796
- "content": "<|reserved_93|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "100": {
804
- "content": "<|reserved_94|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "101": {
812
- "content": "<|reserved_95|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "102": {
820
- "content": "<|reserved_96|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "103": {
828
- "content": "<|reserved_97|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "104": {
836
- "content": "<|reserved_98|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "105": {
844
- "content": "<|reserved_99|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "106": {
852
- "content": "<|reserved_100|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "107": {
860
- "content": "<|reserved_101|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "108": {
868
- "content": "<|reserved_102|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "109": {
876
- "content": "<|reserved_103|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "110": {
884
- "content": "<|reserved_104|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "111": {
892
- "content": "<|reserved_105|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "112": {
900
- "content": "<|reserved_106|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "113": {
908
- "content": "<|reserved_107|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "114": {
916
- "content": "<|reserved_108|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "115": {
924
- "content": "<|reserved_109|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "116": {
932
- "content": "<|reserved_110|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "117": {
940
- "content": "<|reserved_111|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "118": {
948
- "content": "<|reserved_112|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "119": {
956
- "content": "<|reserved_113|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "120": {
964
- "content": "<|reserved_114|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "121": {
972
- "content": "<|reserved_115|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "122": {
980
- "content": "<|reserved_116|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "123": {
988
- "content": "<|reserved_117|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "124": {
996
- "content": "<|reserved_118|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "125": {
1004
- "content": "<|reserved_119|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "126": {
1012
- "content": "<|reserved_120|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "127": {
1020
- "content": "<|reserved_121|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128": {
1028
- "content": "<|reserved_122|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "129": {
1036
- "content": "<|reserved_123|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "130": {
1044
- "content": "<|reserved_124|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "131": {
1052
- "content": "<|reserved_125|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "132": {
1060
- "content": "<|reserved_126|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "133": {
1068
- "content": "<|reserved_127|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "134": {
1076
- "content": "<|reserved_128|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "135": {
1084
- "content": "<|reserved_129|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "136": {
1092
- "content": "<|reserved_130|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "137": {
1100
- "content": "<|reserved_131|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "138": {
1108
- "content": "<|reserved_132|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "139": {
1116
- "content": "<|reserved_133|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "140": {
1124
- "content": "<|reserved_134|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "141": {
1132
- "content": "<|reserved_135|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "142": {
1140
- "content": "<|reserved_136|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "143": {
1148
- "content": "<|reserved_137|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "144": {
1156
- "content": "<|reserved_138|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "145": {
1164
- "content": "<|reserved_139|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "146": {
1172
- "content": "<|reserved_140|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "147": {
1180
- "content": "<|reserved_141|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "148": {
1188
- "content": "<|reserved_142|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "149": {
1196
- "content": "<|reserved_143|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "150": {
1204
- "content": "<|reserved_144|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "151": {
1212
- "content": "<|reserved_145|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "152": {
1220
- "content": "<|reserved_146|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "153": {
1228
- "content": "<|reserved_147|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "154": {
1236
- "content": "<|reserved_148|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "155": {
1244
- "content": "<|reserved_149|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "156": {
1252
- "content": "<|reserved_150|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "157": {
1260
- "content": "<|reserved_151|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "158": {
1268
- "content": "<|reserved_152|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "159": {
1276
- "content": "<|reserved_153|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "160": {
1284
- "content": "<|reserved_154|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "161": {
1292
- "content": "<|reserved_155|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "162": {
1300
- "content": "<|reserved_156|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "163": {
1308
- "content": "<|reserved_157|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "164": {
1316
- "content": "<|reserved_158|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "165": {
1324
- "content": "<|reserved_159|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "166": {
1332
- "content": "<|reserved_160|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "167": {
1340
- "content": "<|reserved_161|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "168": {
1348
- "content": "<|reserved_162|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "169": {
1356
- "content": "<|reserved_163|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "170": {
1364
- "content": "<|reserved_164|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "171": {
1372
- "content": "<|reserved_165|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "172": {
1380
- "content": "<|reserved_166|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "173": {
1388
- "content": "<|reserved_167|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "174": {
1396
- "content": "<|reserved_168|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "175": {
1404
- "content": "<|reserved_169|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "176": {
1412
- "content": "<|reserved_170|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "177": {
1420
- "content": "<|reserved_171|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "178": {
1428
- "content": "<|reserved_172|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "179": {
1436
- "content": "<|reserved_173|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "180": {
1444
- "content": "<|reserved_174|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "181": {
1452
- "content": "<|reserved_175|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "182": {
1460
- "content": "<|reserved_176|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "183": {
1468
- "content": "<|reserved_177|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "184": {
1476
- "content": "<|reserved_178|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "185": {
1484
- "content": "<|reserved_179|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "186": {
1492
- "content": "<|reserved_180|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "187": {
1500
- "content": "<|reserved_181|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "188": {
1508
- "content": "<|reserved_182|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "189": {
1516
- "content": "<|reserved_183|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "190": {
1524
- "content": "<|reserved_184|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "191": {
1532
- "content": "<|reserved_185|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "192": {
1540
- "content": "<|reserved_186|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "193": {
1548
- "content": "<|reserved_187|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "194": {
1556
- "content": "<|reserved_188|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "195": {
1564
- "content": "<|reserved_189|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "196": {
1572
- "content": "<|reserved_190|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "197": {
1580
- "content": "<|reserved_191|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "198": {
1588
- "content": "<|reserved_192|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "199": {
1596
- "content": "<|reserved_193|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "200": {
1604
- "content": "<|reserved_194|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "201": {
1612
- "content": "<|reserved_195|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "202": {
1620
- "content": "<|reserved_196|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "203": {
1628
- "content": "<|reserved_197|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "204": {
1636
- "content": "<|reserved_198|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "205": {
1644
- "content": "<|reserved_199|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "206": {
1652
- "content": "<|reserved_200|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "207": {
1660
- "content": "<|reserved_201|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "208": {
1668
- "content": "<|reserved_202|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "209": {
1676
- "content": "<|reserved_203|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "210": {
1684
- "content": "<|reserved_204|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "211": {
1692
- "content": "<|reserved_205|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "212": {
1700
- "content": "<|reserved_206|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "213": {
1708
- "content": "<|reserved_207|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "214": {
1716
- "content": "<|reserved_208|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "215": {
1724
- "content": "<|reserved_209|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "216": {
1732
- "content": "<|reserved_210|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "217": {
1740
- "content": "<|reserved_211|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "218": {
1748
- "content": "<|reserved_212|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "219": {
1756
- "content": "<|reserved_213|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "220": {
1764
- "content": "<|reserved_214|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "221": {
1772
- "content": "<|reserved_215|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "222": {
1780
- "content": "<|reserved_216|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "223": {
1788
- "content": "<|reserved_217|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "224": {
1796
- "content": "<|reserved_218|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "225": {
1804
- "content": "<|reserved_219|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "226": {
1812
- "content": "<|reserved_220|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "227": {
1820
- "content": "<|reserved_221|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "228": {
1828
- "content": "<|reserved_222|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "229": {
1836
- "content": "<|reserved_223|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "230": {
1844
- "content": "<|reserved_224|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "231": {
1852
- "content": "<|reserved_225|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "232": {
1860
- "content": "<|reserved_226|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "233": {
1868
- "content": "<|reserved_227|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "234": {
1876
- "content": "<|reserved_228|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "235": {
1884
- "content": "<|reserved_229|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "236": {
1892
- "content": "<|reserved_230|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "237": {
1900
- "content": "<|reserved_231|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "238": {
1908
- "content": "<|reserved_232|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "239": {
1916
- "content": "<|reserved_233|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "240": {
1924
- "content": "<|reserved_234|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "241": {
1932
- "content": "<|reserved_235|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "242": {
1940
- "content": "<|reserved_236|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "243": {
1948
- "content": "<|reserved_237|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "244": {
1956
- "content": "<|reserved_238|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "245": {
1964
- "content": "<|reserved_239|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "246": {
1972
- "content": "<|reserved_240|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "247": {
1980
- "content": "<|reserved_241|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "248": {
1988
- "content": "<|reserved_242|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "249": {
1996
- "content": "<|reserved_243|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "250": {
2004
- "content": "<|reserved_244|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "251": {
2012
- "content": "<|reserved_245|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "252": {
2020
- "content": "<|reserved_246|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "253": {
2028
- "content": "<|reserved_247|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "254": {
2036
- "content": "<|reserved_248|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "255": {
2044
- "content": "<|reserved_249|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- },
2051
- "256": {
2052
- "content": "<0x00>",
2053
- "lstrip": false,
2054
- "normalized": false,
2055
- "rstrip": false,
2056
- "single_word": false,
2057
- "special": true
2058
- },
2059
- "257": {
2060
- "content": "<0x01>",
2061
- "lstrip": false,
2062
- "normalized": false,
2063
- "rstrip": false,
2064
- "single_word": false,
2065
- "special": true
2066
- },
2067
- "258": {
2068
- "content": "<0x02>",
2069
- "lstrip": false,
2070
- "normalized": false,
2071
- "rstrip": false,
2072
- "single_word": false,
2073
- "special": true
2074
- },
2075
- "259": {
2076
- "content": "<0x03>",
2077
- "lstrip": false,
2078
- "normalized": false,
2079
- "rstrip": false,
2080
- "single_word": false,
2081
- "special": true
2082
- },
2083
- "260": {
2084
- "content": "<0x04>",
2085
- "lstrip": false,
2086
- "normalized": false,
2087
- "rstrip": false,
2088
- "single_word": false,
2089
- "special": true
2090
- },
2091
- "261": {
2092
- "content": "<0x05>",
2093
- "lstrip": false,
2094
- "normalized": false,
2095
- "rstrip": false,
2096
- "single_word": false,
2097
- "special": true
2098
- },
2099
- "262": {
2100
- "content": "<0x06>",
2101
- "lstrip": false,
2102
- "normalized": false,
2103
- "rstrip": false,
2104
- "single_word": false,
2105
- "special": true
2106
- },
2107
- "263": {
2108
- "content": "<0x07>",
2109
- "lstrip": false,
2110
- "normalized": false,
2111
- "rstrip": false,
2112
- "single_word": false,
2113
- "special": true
2114
- },
2115
- "264": {
2116
- "content": "<0x08>",
2117
- "lstrip": false,
2118
- "normalized": false,
2119
- "rstrip": false,
2120
- "single_word": false,
2121
- "special": true
2122
- },
2123
- "265": {
2124
- "content": "<0x09>",
2125
- "lstrip": false,
2126
- "normalized": false,
2127
- "rstrip": false,
2128
- "single_word": false,
2129
- "special": true
2130
- },
2131
- "266": {
2132
- "content": "<0x0A>",
2133
- "lstrip": false,
2134
- "normalized": false,
2135
- "rstrip": false,
2136
- "single_word": false,
2137
- "special": true
2138
- },
2139
- "267": {
2140
- "content": "<0x0B>",
2141
- "lstrip": false,
2142
- "normalized": false,
2143
- "rstrip": false,
2144
- "single_word": false,
2145
- "special": true
2146
- },
2147
- "268": {
2148
- "content": "<0x0C>",
2149
- "lstrip": false,
2150
- "normalized": false,
2151
- "rstrip": false,
2152
- "single_word": false,
2153
- "special": true
2154
- },
2155
- "269": {
2156
- "content": "<0x0D>",
2157
- "lstrip": false,
2158
- "normalized": false,
2159
- "rstrip": false,
2160
- "single_word": false,
2161
- "special": true
2162
- },
2163
- "270": {
2164
- "content": "<0x0E>",
2165
- "lstrip": false,
2166
- "normalized": false,
2167
- "rstrip": false,
2168
- "single_word": false,
2169
- "special": true
2170
- },
2171
- "271": {
2172
- "content": "<0x0F>",
2173
- "lstrip": false,
2174
- "normalized": false,
2175
- "rstrip": false,
2176
- "single_word": false,
2177
- "special": true
2178
- },
2179
- "272": {
2180
- "content": "<0x10>",
2181
- "lstrip": false,
2182
- "normalized": false,
2183
- "rstrip": false,
2184
- "single_word": false,
2185
- "special": true
2186
- },
2187
- "273": {
2188
- "content": "<0x11>",
2189
- "lstrip": false,
2190
- "normalized": false,
2191
- "rstrip": false,
2192
- "single_word": false,
2193
- "special": true
2194
- },
2195
- "274": {
2196
- "content": "<0x12>",
2197
- "lstrip": false,
2198
- "normalized": false,
2199
- "rstrip": false,
2200
- "single_word": false,
2201
- "special": true
2202
- },
2203
- "275": {
2204
- "content": "<0x13>",
2205
- "lstrip": false,
2206
- "normalized": false,
2207
- "rstrip": false,
2208
- "single_word": false,
2209
- "special": true
2210
- },
2211
- "276": {
2212
- "content": "<0x14>",
2213
- "lstrip": false,
2214
- "normalized": false,
2215
- "rstrip": false,
2216
- "single_word": false,
2217
- "special": true
2218
- },
2219
- "277": {
2220
- "content": "<0x15>",
2221
- "lstrip": false,
2222
- "normalized": false,
2223
- "rstrip": false,
2224
- "single_word": false,
2225
- "special": true
2226
- },
2227
- "278": {
2228
- "content": "<0x16>",
2229
- "lstrip": false,
2230
- "normalized": false,
2231
- "rstrip": false,
2232
- "single_word": false,
2233
- "special": true
2234
- },
2235
- "279": {
2236
- "content": "<0x17>",
2237
- "lstrip": false,
2238
- "normalized": false,
2239
- "rstrip": false,
2240
- "single_word": false,
2241
- "special": true
2242
- },
2243
- "280": {
2244
- "content": "<0x18>",
2245
- "lstrip": false,
2246
- "normalized": false,
2247
- "rstrip": false,
2248
- "single_word": false,
2249
- "special": true
2250
- },
2251
- "281": {
2252
- "content": "<0x19>",
2253
- "lstrip": false,
2254
- "normalized": false,
2255
- "rstrip": false,
2256
- "single_word": false,
2257
- "special": true
2258
- },
2259
- "282": {
2260
- "content": "<0x1A>",
2261
- "lstrip": false,
2262
- "normalized": false,
2263
- "rstrip": false,
2264
- "single_word": false,
2265
- "special": true
2266
- },
2267
- "283": {
2268
- "content": "<0x1B>",
2269
- "lstrip": false,
2270
- "normalized": false,
2271
- "rstrip": false,
2272
- "single_word": false,
2273
- "special": true
2274
- },
2275
- "284": {
2276
- "content": "<0x1C>",
2277
- "lstrip": false,
2278
- "normalized": false,
2279
- "rstrip": false,
2280
- "single_word": false,
2281
- "special": true
2282
- },
2283
- "285": {
2284
- "content": "<0x1D>",
2285
- "lstrip": false,
2286
- "normalized": false,
2287
- "rstrip": false,
2288
- "single_word": false,
2289
- "special": true
2290
- },
2291
- "286": {
2292
- "content": "<0x1E>",
2293
- "lstrip": false,
2294
- "normalized": false,
2295
- "rstrip": false,
2296
- "single_word": false,
2297
- "special": true
2298
- },
2299
- "287": {
2300
- "content": "<0x1F>",
2301
- "lstrip": false,
2302
- "normalized": false,
2303
- "rstrip": false,
2304
- "single_word": false,
2305
- "special": true
2306
- },
2307
- "288": {
2308
- "content": "<0x20>",
2309
- "lstrip": false,
2310
- "normalized": false,
2311
- "rstrip": false,
2312
- "single_word": false,
2313
- "special": true
2314
- },
2315
- "289": {
2316
- "content": "<0x21>",
2317
- "lstrip": false,
2318
- "normalized": false,
2319
- "rstrip": false,
2320
- "single_word": false,
2321
- "special": true
2322
- },
2323
- "290": {
2324
- "content": "<0x22>",
2325
- "lstrip": false,
2326
- "normalized": false,
2327
- "rstrip": false,
2328
- "single_word": false,
2329
- "special": true
2330
- },
2331
- "291": {
2332
- "content": "<0x23>",
2333
- "lstrip": false,
2334
- "normalized": false,
2335
- "rstrip": false,
2336
- "single_word": false,
2337
- "special": true
2338
- },
2339
- "292": {
2340
- "content": "<0x24>",
2341
- "lstrip": false,
2342
- "normalized": false,
2343
- "rstrip": false,
2344
- "single_word": false,
2345
- "special": true
2346
- },
2347
- "293": {
2348
- "content": "<0x25>",
2349
- "lstrip": false,
2350
- "normalized": false,
2351
- "rstrip": false,
2352
- "single_word": false,
2353
- "special": true
2354
- },
2355
- "294": {
2356
- "content": "<0x26>",
2357
- "lstrip": false,
2358
- "normalized": false,
2359
- "rstrip": false,
2360
- "single_word": false,
2361
- "special": true
2362
- },
2363
- "295": {
2364
- "content": "<0x27>",
2365
- "lstrip": false,
2366
- "normalized": false,
2367
- "rstrip": false,
2368
- "single_word": false,
2369
- "special": true
2370
- },
2371
- "296": {
2372
- "content": "<0x28>",
2373
- "lstrip": false,
2374
- "normalized": false,
2375
- "rstrip": false,
2376
- "single_word": false,
2377
- "special": true
2378
- },
2379
- "297": {
2380
- "content": "<0x29>",
2381
- "lstrip": false,
2382
- "normalized": false,
2383
- "rstrip": false,
2384
- "single_word": false,
2385
- "special": true
2386
- },
2387
- "298": {
2388
- "content": "<0x2A>",
2389
- "lstrip": false,
2390
- "normalized": false,
2391
- "rstrip": false,
2392
- "single_word": false,
2393
- "special": true
2394
- },
2395
- "299": {
2396
- "content": "<0x2B>",
2397
- "lstrip": false,
2398
- "normalized": false,
2399
- "rstrip": false,
2400
- "single_word": false,
2401
- "special": true
2402
- },
2403
- "300": {
2404
- "content": "<0x2C>",
2405
- "lstrip": false,
2406
- "normalized": false,
2407
- "rstrip": false,
2408
- "single_word": false,
2409
- "special": true
2410
- },
2411
- "301": {
2412
- "content": "<0x2D>",
2413
- "lstrip": false,
2414
- "normalized": false,
2415
- "rstrip": false,
2416
- "single_word": false,
2417
- "special": true
2418
- },
2419
- "302": {
2420
- "content": "<0x2E>",
2421
- "lstrip": false,
2422
- "normalized": false,
2423
- "rstrip": false,
2424
- "single_word": false,
2425
- "special": true
2426
- },
2427
- "303": {
2428
- "content": "<0x2F>",
2429
- "lstrip": false,
2430
- "normalized": false,
2431
- "rstrip": false,
2432
- "single_word": false,
2433
- "special": true
2434
- },
2435
- "304": {
2436
- "content": "<0x30>",
2437
- "lstrip": false,
2438
- "normalized": false,
2439
- "rstrip": false,
2440
- "single_word": false,
2441
- "special": true
2442
- },
2443
- "305": {
2444
- "content": "<0x31>",
2445
- "lstrip": false,
2446
- "normalized": false,
2447
- "rstrip": false,
2448
- "single_word": false,
2449
- "special": true
2450
- },
2451
- "306": {
2452
- "content": "<0x32>",
2453
- "lstrip": false,
2454
- "normalized": false,
2455
- "rstrip": false,
2456
- "single_word": false,
2457
- "special": true
2458
- },
2459
- "307": {
2460
- "content": "<0x33>",
2461
- "lstrip": false,
2462
- "normalized": false,
2463
- "rstrip": false,
2464
- "single_word": false,
2465
- "special": true
2466
- },
2467
- "308": {
2468
- "content": "<0x34>",
2469
- "lstrip": false,
2470
- "normalized": false,
2471
- "rstrip": false,
2472
- "single_word": false,
2473
- "special": true
2474
- },
2475
- "309": {
2476
- "content": "<0x35>",
2477
- "lstrip": false,
2478
- "normalized": false,
2479
- "rstrip": false,
2480
- "single_word": false,
2481
- "special": true
2482
- },
2483
- "310": {
2484
- "content": "<0x36>",
2485
- "lstrip": false,
2486
- "normalized": false,
2487
- "rstrip": false,
2488
- "single_word": false,
2489
- "special": true
2490
- },
2491
- "311": {
2492
- "content": "<0x37>",
2493
- "lstrip": false,
2494
- "normalized": false,
2495
- "rstrip": false,
2496
- "single_word": false,
2497
- "special": true
2498
- },
2499
- "312": {
2500
- "content": "<0x38>",
2501
- "lstrip": false,
2502
- "normalized": false,
2503
- "rstrip": false,
2504
- "single_word": false,
2505
- "special": true
2506
- },
2507
- "313": {
2508
- "content": "<0x39>",
2509
- "lstrip": false,
2510
- "normalized": false,
2511
- "rstrip": false,
2512
- "single_word": false,
2513
- "special": true
2514
- },
2515
- "314": {
2516
- "content": "<0x3A>",
2517
- "lstrip": false,
2518
- "normalized": false,
2519
- "rstrip": false,
2520
- "single_word": false,
2521
- "special": true
2522
- },
2523
- "315": {
2524
- "content": "<0x3B>",
2525
- "lstrip": false,
2526
- "normalized": false,
2527
- "rstrip": false,
2528
- "single_word": false,
2529
- "special": true
2530
- },
2531
- "316": {
2532
- "content": "<0x3C>",
2533
- "lstrip": false,
2534
- "normalized": false,
2535
- "rstrip": false,
2536
- "single_word": false,
2537
- "special": true
2538
- },
2539
- "317": {
2540
- "content": "<0x3D>",
2541
- "lstrip": false,
2542
- "normalized": false,
2543
- "rstrip": false,
2544
- "single_word": false,
2545
- "special": true
2546
- },
2547
- "318": {
2548
- "content": "<0x3E>",
2549
- "lstrip": false,
2550
- "normalized": false,
2551
- "rstrip": false,
2552
- "single_word": false,
2553
- "special": true
2554
- },
2555
- "319": {
2556
- "content": "<0x3F>",
2557
- "lstrip": false,
2558
- "normalized": false,
2559
- "rstrip": false,
2560
- "single_word": false,
2561
- "special": true
2562
- },
2563
- "320": {
2564
- "content": "<0x40>",
2565
- "lstrip": false,
2566
- "normalized": false,
2567
- "rstrip": false,
2568
- "single_word": false,
2569
- "special": true
2570
- },
2571
- "321": {
2572
- "content": "<0x41>",
2573
- "lstrip": false,
2574
- "normalized": false,
2575
- "rstrip": false,
2576
- "single_word": false,
2577
- "special": true
2578
- },
2579
- "322": {
2580
- "content": "<0x42>",
2581
- "lstrip": false,
2582
- "normalized": false,
2583
- "rstrip": false,
2584
- "single_word": false,
2585
- "special": true
2586
- },
2587
- "323": {
2588
- "content": "<0x43>",
2589
- "lstrip": false,
2590
- "normalized": false,
2591
- "rstrip": false,
2592
- "single_word": false,
2593
- "special": true
2594
- },
2595
- "324": {
2596
- "content": "<0x44>",
2597
- "lstrip": false,
2598
- "normalized": false,
2599
- "rstrip": false,
2600
- "single_word": false,
2601
- "special": true
2602
- },
2603
- "325": {
2604
- "content": "<0x45>",
2605
- "lstrip": false,
2606
- "normalized": false,
2607
- "rstrip": false,
2608
- "single_word": false,
2609
- "special": true
2610
- },
2611
- "326": {
2612
- "content": "<0x46>",
2613
- "lstrip": false,
2614
- "normalized": false,
2615
- "rstrip": false,
2616
- "single_word": false,
2617
- "special": true
2618
- },
2619
- "327": {
2620
- "content": "<0x47>",
2621
- "lstrip": false,
2622
- "normalized": false,
2623
- "rstrip": false,
2624
- "single_word": false,
2625
- "special": true
2626
- },
2627
- "328": {
2628
- "content": "<0x48>",
2629
- "lstrip": false,
2630
- "normalized": false,
2631
- "rstrip": false,
2632
- "single_word": false,
2633
- "special": true
2634
- },
2635
- "329": {
2636
- "content": "<0x49>",
2637
- "lstrip": false,
2638
- "normalized": false,
2639
- "rstrip": false,
2640
- "single_word": false,
2641
- "special": true
2642
- },
2643
- "330": {
2644
- "content": "<0x4A>",
2645
- "lstrip": false,
2646
- "normalized": false,
2647
- "rstrip": false,
2648
- "single_word": false,
2649
- "special": true
2650
- },
2651
- "331": {
2652
- "content": "<0x4B>",
2653
- "lstrip": false,
2654
- "normalized": false,
2655
- "rstrip": false,
2656
- "single_word": false,
2657
- "special": true
2658
- },
2659
- "332": {
2660
- "content": "<0x4C>",
2661
- "lstrip": false,
2662
- "normalized": false,
2663
- "rstrip": false,
2664
- "single_word": false,
2665
- "special": true
2666
- },
2667
- "333": {
2668
- "content": "<0x4D>",
2669
- "lstrip": false,
2670
- "normalized": false,
2671
- "rstrip": false,
2672
- "single_word": false,
2673
- "special": true
2674
- },
2675
- "334": {
2676
- "content": "<0x4E>",
2677
- "lstrip": false,
2678
- "normalized": false,
2679
- "rstrip": false,
2680
- "single_word": false,
2681
- "special": true
2682
- },
2683
- "335": {
2684
- "content": "<0x4F>",
2685
- "lstrip": false,
2686
- "normalized": false,
2687
- "rstrip": false,
2688
- "single_word": false,
2689
- "special": true
2690
- },
2691
- "336": {
2692
- "content": "<0x50>",
2693
- "lstrip": false,
2694
- "normalized": false,
2695
- "rstrip": false,
2696
- "single_word": false,
2697
- "special": true
2698
- },
2699
- "337": {
2700
- "content": "<0x51>",
2701
- "lstrip": false,
2702
- "normalized": false,
2703
- "rstrip": false,
2704
- "single_word": false,
2705
- "special": true
2706
- },
2707
- "338": {
2708
- "content": "<0x52>",
2709
- "lstrip": false,
2710
- "normalized": false,
2711
- "rstrip": false,
2712
- "single_word": false,
2713
- "special": true
2714
- },
2715
- "339": {
2716
- "content": "<0x53>",
2717
- "lstrip": false,
2718
- "normalized": false,
2719
- "rstrip": false,
2720
- "single_word": false,
2721
- "special": true
2722
- },
2723
- "340": {
2724
- "content": "<0x54>",
2725
- "lstrip": false,
2726
- "normalized": false,
2727
- "rstrip": false,
2728
- "single_word": false,
2729
- "special": true
2730
- },
2731
- "341": {
2732
- "content": "<0x55>",
2733
- "lstrip": false,
2734
- "normalized": false,
2735
- "rstrip": false,
2736
- "single_word": false,
2737
- "special": true
2738
- },
2739
- "342": {
2740
- "content": "<0x56>",
2741
- "lstrip": false,
2742
- "normalized": false,
2743
- "rstrip": false,
2744
- "single_word": false,
2745
- "special": true
2746
- },
2747
- "343": {
2748
- "content": "<0x57>",
2749
- "lstrip": false,
2750
- "normalized": false,
2751
- "rstrip": false,
2752
- "single_word": false,
2753
- "special": true
2754
- },
2755
- "344": {
2756
- "content": "<0x58>",
2757
- "lstrip": false,
2758
- "normalized": false,
2759
- "rstrip": false,
2760
- "single_word": false,
2761
- "special": true
2762
- },
2763
- "345": {
2764
- "content": "<0x59>",
2765
- "lstrip": false,
2766
- "normalized": false,
2767
- "rstrip": false,
2768
- "single_word": false,
2769
- "special": true
2770
- },
2771
- "346": {
2772
- "content": "<0x5A>",
2773
- "lstrip": false,
2774
- "normalized": false,
2775
- "rstrip": false,
2776
- "single_word": false,
2777
- "special": true
2778
- },
2779
- "347": {
2780
- "content": "<0x5B>",
2781
- "lstrip": false,
2782
- "normalized": false,
2783
- "rstrip": false,
2784
- "single_word": false,
2785
- "special": true
2786
- },
2787
- "348": {
2788
- "content": "<0x5C>",
2789
- "lstrip": false,
2790
- "normalized": false,
2791
- "rstrip": false,
2792
- "single_word": false,
2793
- "special": true
2794
- },
2795
- "349": {
2796
- "content": "<0x5D>",
2797
- "lstrip": false,
2798
- "normalized": false,
2799
- "rstrip": false,
2800
- "single_word": false,
2801
- "special": true
2802
- },
2803
- "350": {
2804
- "content": "<0x5E>",
2805
- "lstrip": false,
2806
- "normalized": false,
2807
- "rstrip": false,
2808
- "single_word": false,
2809
- "special": true
2810
- },
2811
- "351": {
2812
- "content": "<0x5F>",
2813
- "lstrip": false,
2814
- "normalized": false,
2815
- "rstrip": false,
2816
- "single_word": false,
2817
- "special": true
2818
- },
2819
- "352": {
2820
- "content": "<0x60>",
2821
- "lstrip": false,
2822
- "normalized": false,
2823
- "rstrip": false,
2824
- "single_word": false,
2825
- "special": true
2826
- },
2827
- "353": {
2828
- "content": "<0x61>",
2829
- "lstrip": false,
2830
- "normalized": false,
2831
- "rstrip": false,
2832
- "single_word": false,
2833
- "special": true
2834
- },
2835
- "354": {
2836
- "content": "<0x62>",
2837
- "lstrip": false,
2838
- "normalized": false,
2839
- "rstrip": false,
2840
- "single_word": false,
2841
- "special": true
2842
- },
2843
- "355": {
2844
- "content": "<0x63>",
2845
- "lstrip": false,
2846
- "normalized": false,
2847
- "rstrip": false,
2848
- "single_word": false,
2849
- "special": true
2850
- },
2851
- "356": {
2852
- "content": "<0x64>",
2853
- "lstrip": false,
2854
- "normalized": false,
2855
- "rstrip": false,
2856
- "single_word": false,
2857
- "special": true
2858
- },
2859
- "357": {
2860
- "content": "<0x65>",
2861
- "lstrip": false,
2862
- "normalized": false,
2863
- "rstrip": false,
2864
- "single_word": false,
2865
- "special": true
2866
- },
2867
- "358": {
2868
- "content": "<0x66>",
2869
- "lstrip": false,
2870
- "normalized": false,
2871
- "rstrip": false,
2872
- "single_word": false,
2873
- "special": true
2874
- },
2875
- "359": {
2876
- "content": "<0x67>",
2877
- "lstrip": false,
2878
- "normalized": false,
2879
- "rstrip": false,
2880
- "single_word": false,
2881
- "special": true
2882
- },
2883
- "360": {
2884
- "content": "<0x68>",
2885
- "lstrip": false,
2886
- "normalized": false,
2887
- "rstrip": false,
2888
- "single_word": false,
2889
- "special": true
2890
- },
2891
- "361": {
2892
- "content": "<0x69>",
2893
- "lstrip": false,
2894
- "normalized": false,
2895
- "rstrip": false,
2896
- "single_word": false,
2897
- "special": true
2898
- },
2899
- "362": {
2900
- "content": "<0x6A>",
2901
- "lstrip": false,
2902
- "normalized": false,
2903
- "rstrip": false,
2904
- "single_word": false,
2905
- "special": true
2906
- },
2907
- "363": {
2908
- "content": "<0x6B>",
2909
- "lstrip": false,
2910
- "normalized": false,
2911
- "rstrip": false,
2912
- "single_word": false,
2913
- "special": true
2914
- },
2915
- "364": {
2916
- "content": "<0x6C>",
2917
- "lstrip": false,
2918
- "normalized": false,
2919
- "rstrip": false,
2920
- "single_word": false,
2921
- "special": true
2922
- },
2923
- "365": {
2924
- "content": "<0x6D>",
2925
- "lstrip": false,
2926
- "normalized": false,
2927
- "rstrip": false,
2928
- "single_word": false,
2929
- "special": true
2930
- },
2931
- "366": {
2932
- "content": "<0x6E>",
2933
- "lstrip": false,
2934
- "normalized": false,
2935
- "rstrip": false,
2936
- "single_word": false,
2937
- "special": true
2938
- },
2939
- "367": {
2940
- "content": "<0x6F>",
2941
- "lstrip": false,
2942
- "normalized": false,
2943
- "rstrip": false,
2944
- "single_word": false,
2945
- "special": true
2946
- },
2947
- "368": {
2948
- "content": "<0x70>",
2949
- "lstrip": false,
2950
- "normalized": false,
2951
- "rstrip": false,
2952
- "single_word": false,
2953
- "special": true
2954
- },
2955
- "369": {
2956
- "content": "<0x71>",
2957
- "lstrip": false,
2958
- "normalized": false,
2959
- "rstrip": false,
2960
- "single_word": false,
2961
- "special": true
2962
- },
2963
- "370": {
2964
- "content": "<0x72>",
2965
- "lstrip": false,
2966
- "normalized": false,
2967
- "rstrip": false,
2968
- "single_word": false,
2969
- "special": true
2970
- },
2971
- "371": {
2972
- "content": "<0x73>",
2973
- "lstrip": false,
2974
- "normalized": false,
2975
- "rstrip": false,
2976
- "single_word": false,
2977
- "special": true
2978
- },
2979
- "372": {
2980
- "content": "<0x74>",
2981
- "lstrip": false,
2982
- "normalized": false,
2983
- "rstrip": false,
2984
- "single_word": false,
2985
- "special": true
2986
- },
2987
- "373": {
2988
- "content": "<0x75>",
2989
- "lstrip": false,
2990
- "normalized": false,
2991
- "rstrip": false,
2992
- "single_word": false,
2993
- "special": true
2994
- },
2995
- "374": {
2996
- "content": "<0x76>",
2997
- "lstrip": false,
2998
- "normalized": false,
2999
- "rstrip": false,
3000
- "single_word": false,
3001
- "special": true
3002
- },
3003
- "375": {
3004
- "content": "<0x77>",
3005
- "lstrip": false,
3006
- "normalized": false,
3007
- "rstrip": false,
3008
- "single_word": false,
3009
- "special": true
3010
- },
3011
- "376": {
3012
- "content": "<0x78>",
3013
- "lstrip": false,
3014
- "normalized": false,
3015
- "rstrip": false,
3016
- "single_word": false,
3017
- "special": true
3018
- },
3019
- "377": {
3020
- "content": "<0x79>",
3021
- "lstrip": false,
3022
- "normalized": false,
3023
- "rstrip": false,
3024
- "single_word": false,
3025
- "special": true
3026
- },
3027
- "378": {
3028
- "content": "<0x7A>",
3029
- "lstrip": false,
3030
- "normalized": false,
3031
- "rstrip": false,
3032
- "single_word": false,
3033
- "special": true
3034
- },
3035
- "379": {
3036
- "content": "<0x7B>",
3037
- "lstrip": false,
3038
- "normalized": false,
3039
- "rstrip": false,
3040
- "single_word": false,
3041
- "special": true
3042
- },
3043
- "380": {
3044
- "content": "<0x7C>",
3045
- "lstrip": false,
3046
- "normalized": false,
3047
- "rstrip": false,
3048
- "single_word": false,
3049
- "special": true
3050
- },
3051
- "381": {
3052
- "content": "<0x7D>",
3053
- "lstrip": false,
3054
- "normalized": false,
3055
- "rstrip": false,
3056
- "single_word": false,
3057
- "special": true
3058
- },
3059
- "382": {
3060
- "content": "<0x7E>",
3061
- "lstrip": false,
3062
- "normalized": false,
3063
- "rstrip": false,
3064
- "single_word": false,
3065
- "special": true
3066
- },
3067
- "383": {
3068
- "content": "<0x7F>",
3069
- "lstrip": false,
3070
- "normalized": false,
3071
- "rstrip": false,
3072
- "single_word": false,
3073
- "special": true
3074
- },
3075
- "384": {
3076
- "content": "<0x80>",
3077
- "lstrip": false,
3078
- "normalized": false,
3079
- "rstrip": false,
3080
- "single_word": false,
3081
- "special": true
3082
- },
3083
- "385": {
3084
- "content": "<0x81>",
3085
- "lstrip": false,
3086
- "normalized": false,
3087
- "rstrip": false,
3088
- "single_word": false,
3089
- "special": true
3090
- },
3091
- "386": {
3092
- "content": "<0x82>",
3093
- "lstrip": false,
3094
- "normalized": false,
3095
- "rstrip": false,
3096
- "single_word": false,
3097
- "special": true
3098
- },
3099
- "387": {
3100
- "content": "<0x83>",
3101
- "lstrip": false,
3102
- "normalized": false,
3103
- "rstrip": false,
3104
- "single_word": false,
3105
- "special": true
3106
- },
3107
- "388": {
3108
- "content": "<0x84>",
3109
- "lstrip": false,
3110
- "normalized": false,
3111
- "rstrip": false,
3112
- "single_word": false,
3113
- "special": true
3114
- },
3115
- "389": {
3116
- "content": "<0x85>",
3117
- "lstrip": false,
3118
- "normalized": false,
3119
- "rstrip": false,
3120
- "single_word": false,
3121
- "special": true
3122
- },
3123
- "390": {
3124
- "content": "<0x86>",
3125
- "lstrip": false,
3126
- "normalized": false,
3127
- "rstrip": false,
3128
- "single_word": false,
3129
- "special": true
3130
- },
3131
- "391": {
3132
- "content": "<0x87>",
3133
- "lstrip": false,
3134
- "normalized": false,
3135
- "rstrip": false,
3136
- "single_word": false,
3137
- "special": true
3138
- },
3139
- "392": {
3140
- "content": "<0x88>",
3141
- "lstrip": false,
3142
- "normalized": false,
3143
- "rstrip": false,
3144
- "single_word": false,
3145
- "special": true
3146
- },
3147
- "393": {
3148
- "content": "<0x89>",
3149
- "lstrip": false,
3150
- "normalized": false,
3151
- "rstrip": false,
3152
- "single_word": false,
3153
- "special": true
3154
- },
3155
- "394": {
3156
- "content": "<0x8A>",
3157
- "lstrip": false,
3158
- "normalized": false,
3159
- "rstrip": false,
3160
- "single_word": false,
3161
- "special": true
3162
- },
3163
- "395": {
3164
- "content": "<0x8B>",
3165
- "lstrip": false,
3166
- "normalized": false,
3167
- "rstrip": false,
3168
- "single_word": false,
3169
- "special": true
3170
- },
3171
- "396": {
3172
- "content": "<0x8C>",
3173
- "lstrip": false,
3174
- "normalized": false,
3175
- "rstrip": false,
3176
- "single_word": false,
3177
- "special": true
3178
- },
3179
- "397": {
3180
- "content": "<0x8D>",
3181
- "lstrip": false,
3182
- "normalized": false,
3183
- "rstrip": false,
3184
- "single_word": false,
3185
- "special": true
3186
- },
3187
- "398": {
3188
- "content": "<0x8E>",
3189
- "lstrip": false,
3190
- "normalized": false,
3191
- "rstrip": false,
3192
- "single_word": false,
3193
- "special": true
3194
- },
3195
- "399": {
3196
- "content": "<0x8F>",
3197
- "lstrip": false,
3198
- "normalized": false,
3199
- "rstrip": false,
3200
- "single_word": false,
3201
- "special": true
3202
- },
3203
- "400": {
3204
- "content": "<0x90>",
3205
- "lstrip": false,
3206
- "normalized": false,
3207
- "rstrip": false,
3208
- "single_word": false,
3209
- "special": true
3210
- },
3211
- "401": {
3212
- "content": "<0x91>",
3213
- "lstrip": false,
3214
- "normalized": false,
3215
- "rstrip": false,
3216
- "single_word": false,
3217
- "special": true
3218
- },
3219
- "402": {
3220
- "content": "<0x92>",
3221
- "lstrip": false,
3222
- "normalized": false,
3223
- "rstrip": false,
3224
- "single_word": false,
3225
- "special": true
3226
- },
3227
- "403": {
3228
- "content": "<0x93>",
3229
- "lstrip": false,
3230
- "normalized": false,
3231
- "rstrip": false,
3232
- "single_word": false,
3233
- "special": true
3234
- },
3235
- "404": {
3236
- "content": "<0x94>",
3237
- "lstrip": false,
3238
- "normalized": false,
3239
- "rstrip": false,
3240
- "single_word": false,
3241
- "special": true
3242
- },
3243
- "405": {
3244
- "content": "<0x95>",
3245
- "lstrip": false,
3246
- "normalized": false,
3247
- "rstrip": false,
3248
- "single_word": false,
3249
- "special": true
3250
- },
3251
- "406": {
3252
- "content": "<0x96>",
3253
- "lstrip": false,
3254
- "normalized": false,
3255
- "rstrip": false,
3256
- "single_word": false,
3257
- "special": true
3258
- },
3259
- "407": {
3260
- "content": "<0x97>",
3261
- "lstrip": false,
3262
- "normalized": false,
3263
- "rstrip": false,
3264
- "single_word": false,
3265
- "special": true
3266
- },
3267
- "408": {
3268
- "content": "<0x98>",
3269
- "lstrip": false,
3270
- "normalized": false,
3271
- "rstrip": false,
3272
- "single_word": false,
3273
- "special": true
3274
- },
3275
- "409": {
3276
- "content": "<0x99>",
3277
- "lstrip": false,
3278
- "normalized": false,
3279
- "rstrip": false,
3280
- "single_word": false,
3281
- "special": true
3282
- },
3283
- "410": {
3284
- "content": "<0x9A>",
3285
- "lstrip": false,
3286
- "normalized": false,
3287
- "rstrip": false,
3288
- "single_word": false,
3289
- "special": true
3290
- },
3291
- "411": {
3292
- "content": "<0x9B>",
3293
- "lstrip": false,
3294
- "normalized": false,
3295
- "rstrip": false,
3296
- "single_word": false,
3297
- "special": true
3298
- },
3299
- "412": {
3300
- "content": "<0x9C>",
3301
- "lstrip": false,
3302
- "normalized": false,
3303
- "rstrip": false,
3304
- "single_word": false,
3305
- "special": true
3306
- },
3307
- "413": {
3308
- "content": "<0x9D>",
3309
- "lstrip": false,
3310
- "normalized": false,
3311
- "rstrip": false,
3312
- "single_word": false,
3313
- "special": true
3314
- },
3315
- "414": {
3316
- "content": "<0x9E>",
3317
- "lstrip": false,
3318
- "normalized": false,
3319
- "rstrip": false,
3320
- "single_word": false,
3321
- "special": true
3322
- },
3323
- "415": {
3324
- "content": "<0x9F>",
3325
- "lstrip": false,
3326
- "normalized": false,
3327
- "rstrip": false,
3328
- "single_word": false,
3329
- "special": true
3330
- },
3331
- "416": {
3332
- "content": "<0xA0>",
3333
- "lstrip": false,
3334
- "normalized": false,
3335
- "rstrip": false,
3336
- "single_word": false,
3337
- "special": true
3338
- },
3339
- "417": {
3340
- "content": "<0xA1>",
3341
- "lstrip": false,
3342
- "normalized": false,
3343
- "rstrip": false,
3344
- "single_word": false,
3345
- "special": true
3346
- },
3347
- "418": {
3348
- "content": "<0xA2>",
3349
- "lstrip": false,
3350
- "normalized": false,
3351
- "rstrip": false,
3352
- "single_word": false,
3353
- "special": true
3354
- },
3355
- "419": {
3356
- "content": "<0xA3>",
3357
- "lstrip": false,
3358
- "normalized": false,
3359
- "rstrip": false,
3360
- "single_word": false,
3361
- "special": true
3362
- },
3363
- "420": {
3364
- "content": "<0xA4>",
3365
- "lstrip": false,
3366
- "normalized": false,
3367
- "rstrip": false,
3368
- "single_word": false,
3369
- "special": true
3370
- },
3371
- "421": {
3372
- "content": "<0xA5>",
3373
- "lstrip": false,
3374
- "normalized": false,
3375
- "rstrip": false,
3376
- "single_word": false,
3377
- "special": true
3378
- },
3379
- "422": {
3380
- "content": "<0xA6>",
3381
- "lstrip": false,
3382
- "normalized": false,
3383
- "rstrip": false,
3384
- "single_word": false,
3385
- "special": true
3386
- },
3387
- "423": {
3388
- "content": "<0xA7>",
3389
- "lstrip": false,
3390
- "normalized": false,
3391
- "rstrip": false,
3392
- "single_word": false,
3393
- "special": true
3394
- },
3395
- "424": {
3396
- "content": "<0xA8>",
3397
- "lstrip": false,
3398
- "normalized": false,
3399
- "rstrip": false,
3400
- "single_word": false,
3401
- "special": true
3402
- },
3403
- "425": {
3404
- "content": "<0xA9>",
3405
- "lstrip": false,
3406
- "normalized": false,
3407
- "rstrip": false,
3408
- "single_word": false,
3409
- "special": true
3410
- },
3411
- "426": {
3412
- "content": "<0xAA>",
3413
- "lstrip": false,
3414
- "normalized": false,
3415
- "rstrip": false,
3416
- "single_word": false,
3417
- "special": true
3418
- },
3419
- "427": {
3420
- "content": "<0xAB>",
3421
- "lstrip": false,
3422
- "normalized": false,
3423
- "rstrip": false,
3424
- "single_word": false,
3425
- "special": true
3426
- },
3427
- "428": {
3428
- "content": "<0xAC>",
3429
- "lstrip": false,
3430
- "normalized": false,
3431
- "rstrip": false,
3432
- "single_word": false,
3433
- "special": true
3434
- },
3435
- "429": {
3436
- "content": "<0xAD>",
3437
- "lstrip": false,
3438
- "normalized": false,
3439
- "rstrip": false,
3440
- "single_word": false,
3441
- "special": true
3442
- },
3443
- "430": {
3444
- "content": "<0xAE>",
3445
- "lstrip": false,
3446
- "normalized": false,
3447
- "rstrip": false,
3448
- "single_word": false,
3449
- "special": true
3450
- },
3451
- "431": {
3452
- "content": "<0xAF>",
3453
- "lstrip": false,
3454
- "normalized": false,
3455
- "rstrip": false,
3456
- "single_word": false,
3457
- "special": true
3458
- },
3459
- "432": {
3460
- "content": "<0xB0>",
3461
- "lstrip": false,
3462
- "normalized": false,
3463
- "rstrip": false,
3464
- "single_word": false,
3465
- "special": true
3466
- },
3467
- "433": {
3468
- "content": "<0xB1>",
3469
- "lstrip": false,
3470
- "normalized": false,
3471
- "rstrip": false,
3472
- "single_word": false,
3473
- "special": true
3474
- },
3475
- "434": {
3476
- "content": "<0xB2>",
3477
- "lstrip": false,
3478
- "normalized": false,
3479
- "rstrip": false,
3480
- "single_word": false,
3481
- "special": true
3482
- },
3483
- "435": {
3484
- "content": "<0xB3>",
3485
- "lstrip": false,
3486
- "normalized": false,
3487
- "rstrip": false,
3488
- "single_word": false,
3489
- "special": true
3490
- },
3491
- "436": {
3492
- "content": "<0xB4>",
3493
- "lstrip": false,
3494
- "normalized": false,
3495
- "rstrip": false,
3496
- "single_word": false,
3497
- "special": true
3498
- },
3499
- "437": {
3500
- "content": "<0xB5>",
3501
- "lstrip": false,
3502
- "normalized": false,
3503
- "rstrip": false,
3504
- "single_word": false,
3505
- "special": true
3506
- },
3507
- "438": {
3508
- "content": "<0xB6>",
3509
- "lstrip": false,
3510
- "normalized": false,
3511
- "rstrip": false,
3512
- "single_word": false,
3513
- "special": true
3514
- },
3515
- "439": {
3516
- "content": "<0xB7>",
3517
- "lstrip": false,
3518
- "normalized": false,
3519
- "rstrip": false,
3520
- "single_word": false,
3521
- "special": true
3522
- },
3523
- "440": {
3524
- "content": "<0xB8>",
3525
- "lstrip": false,
3526
- "normalized": false,
3527
- "rstrip": false,
3528
- "single_word": false,
3529
- "special": true
3530
- },
3531
- "441": {
3532
- "content": "<0xB9>",
3533
- "lstrip": false,
3534
- "normalized": false,
3535
- "rstrip": false,
3536
- "single_word": false,
3537
- "special": true
3538
- },
3539
- "442": {
3540
- "content": "<0xBA>",
3541
- "lstrip": false,
3542
- "normalized": false,
3543
- "rstrip": false,
3544
- "single_word": false,
3545
- "special": true
3546
- },
3547
- "443": {
3548
- "content": "<0xBB>",
3549
- "lstrip": false,
3550
- "normalized": false,
3551
- "rstrip": false,
3552
- "single_word": false,
3553
- "special": true
3554
- },
3555
- "444": {
3556
- "content": "<0xBC>",
3557
- "lstrip": false,
3558
- "normalized": false,
3559
- "rstrip": false,
3560
- "single_word": false,
3561
- "special": true
3562
- },
3563
- "445": {
3564
- "content": "<0xBD>",
3565
- "lstrip": false,
3566
- "normalized": false,
3567
- "rstrip": false,
3568
- "single_word": false,
3569
- "special": true
3570
- },
3571
- "446": {
3572
- "content": "<0xBE>",
3573
- "lstrip": false,
3574
- "normalized": false,
3575
- "rstrip": false,
3576
- "single_word": false,
3577
- "special": true
3578
- },
3579
- "447": {
3580
- "content": "<0xBF>",
3581
- "lstrip": false,
3582
- "normalized": false,
3583
- "rstrip": false,
3584
- "single_word": false,
3585
- "special": true
3586
- },
3587
- "448": {
3588
- "content": "<0xC0>",
3589
- "lstrip": false,
3590
- "normalized": false,
3591
- "rstrip": false,
3592
- "single_word": false,
3593
- "special": true
3594
- },
3595
- "449": {
3596
- "content": "<0xC1>",
3597
- "lstrip": false,
3598
- "normalized": false,
3599
- "rstrip": false,
3600
- "single_word": false,
3601
- "special": true
3602
- },
3603
- "450": {
3604
- "content": "<0xC2>",
3605
- "lstrip": false,
3606
- "normalized": false,
3607
- "rstrip": false,
3608
- "single_word": false,
3609
- "special": true
3610
- },
3611
- "451": {
3612
- "content": "<0xC3>",
3613
- "lstrip": false,
3614
- "normalized": false,
3615
- "rstrip": false,
3616
- "single_word": false,
3617
- "special": true
3618
- },
3619
- "452": {
3620
- "content": "<0xC4>",
3621
- "lstrip": false,
3622
- "normalized": false,
3623
- "rstrip": false,
3624
- "single_word": false,
3625
- "special": true
3626
- },
3627
- "453": {
3628
- "content": "<0xC5>",
3629
- "lstrip": false,
3630
- "normalized": false,
3631
- "rstrip": false,
3632
- "single_word": false,
3633
- "special": true
3634
- },
3635
- "454": {
3636
- "content": "<0xC6>",
3637
- "lstrip": false,
3638
- "normalized": false,
3639
- "rstrip": false,
3640
- "single_word": false,
3641
- "special": true
3642
- },
3643
- "455": {
3644
- "content": "<0xC7>",
3645
- "lstrip": false,
3646
- "normalized": false,
3647
- "rstrip": false,
3648
- "single_word": false,
3649
- "special": true
3650
- },
3651
- "456": {
3652
- "content": "<0xC8>",
3653
- "lstrip": false,
3654
- "normalized": false,
3655
- "rstrip": false,
3656
- "single_word": false,
3657
- "special": true
3658
- },
3659
- "457": {
3660
- "content": "<0xC9>",
3661
- "lstrip": false,
3662
- "normalized": false,
3663
- "rstrip": false,
3664
- "single_word": false,
3665
- "special": true
3666
- },
3667
- "458": {
3668
- "content": "<0xCA>",
3669
- "lstrip": false,
3670
- "normalized": false,
3671
- "rstrip": false,
3672
- "single_word": false,
3673
- "special": true
3674
- },
3675
- "459": {
3676
- "content": "<0xCB>",
3677
- "lstrip": false,
3678
- "normalized": false,
3679
- "rstrip": false,
3680
- "single_word": false,
3681
- "special": true
3682
- },
3683
- "460": {
3684
- "content": "<0xCC>",
3685
- "lstrip": false,
3686
- "normalized": false,
3687
- "rstrip": false,
3688
- "single_word": false,
3689
- "special": true
3690
- },
3691
- "461": {
3692
- "content": "<0xCD>",
3693
- "lstrip": false,
3694
- "normalized": false,
3695
- "rstrip": false,
3696
- "single_word": false,
3697
- "special": true
3698
- },
3699
- "462": {
3700
- "content": "<0xCE>",
3701
- "lstrip": false,
3702
- "normalized": false,
3703
- "rstrip": false,
3704
- "single_word": false,
3705
- "special": true
3706
- },
3707
- "463": {
3708
- "content": "<0xCF>",
3709
- "lstrip": false,
3710
- "normalized": false,
3711
- "rstrip": false,
3712
- "single_word": false,
3713
- "special": true
3714
- },
3715
- "464": {
3716
- "content": "<0xD0>",
3717
- "lstrip": false,
3718
- "normalized": false,
3719
- "rstrip": false,
3720
- "single_word": false,
3721
- "special": true
3722
- },
3723
- "465": {
3724
- "content": "<0xD1>",
3725
- "lstrip": false,
3726
- "normalized": false,
3727
- "rstrip": false,
3728
- "single_word": false,
3729
- "special": true
3730
- },
3731
- "466": {
3732
- "content": "<0xD2>",
3733
- "lstrip": false,
3734
- "normalized": false,
3735
- "rstrip": false,
3736
- "single_word": false,
3737
- "special": true
3738
- },
3739
- "467": {
3740
- "content": "<0xD3>",
3741
- "lstrip": false,
3742
- "normalized": false,
3743
- "rstrip": false,
3744
- "single_word": false,
3745
- "special": true
3746
- },
3747
- "468": {
3748
- "content": "<0xD4>",
3749
- "lstrip": false,
3750
- "normalized": false,
3751
- "rstrip": false,
3752
- "single_word": false,
3753
- "special": true
3754
- },
3755
- "469": {
3756
- "content": "<0xD5>",
3757
- "lstrip": false,
3758
- "normalized": false,
3759
- "rstrip": false,
3760
- "single_word": false,
3761
- "special": true
3762
- },
3763
- "470": {
3764
- "content": "<0xD6>",
3765
- "lstrip": false,
3766
- "normalized": false,
3767
- "rstrip": false,
3768
- "single_word": false,
3769
- "special": true
3770
- },
3771
- "471": {
3772
- "content": "<0xD7>",
3773
- "lstrip": false,
3774
- "normalized": false,
3775
- "rstrip": false,
3776
- "single_word": false,
3777
- "special": true
3778
- },
3779
- "472": {
3780
- "content": "<0xD8>",
3781
- "lstrip": false,
3782
- "normalized": false,
3783
- "rstrip": false,
3784
- "single_word": false,
3785
- "special": true
3786
- },
3787
- "473": {
3788
- "content": "<0xD9>",
3789
- "lstrip": false,
3790
- "normalized": false,
3791
- "rstrip": false,
3792
- "single_word": false,
3793
- "special": true
3794
- },
3795
- "474": {
3796
- "content": "<0xDA>",
3797
- "lstrip": false,
3798
- "normalized": false,
3799
- "rstrip": false,
3800
- "single_word": false,
3801
- "special": true
3802
- },
3803
- "475": {
3804
- "content": "<0xDB>",
3805
- "lstrip": false,
3806
- "normalized": false,
3807
- "rstrip": false,
3808
- "single_word": false,
3809
- "special": true
3810
- },
3811
- "476": {
3812
- "content": "<0xDC>",
3813
- "lstrip": false,
3814
- "normalized": false,
3815
- "rstrip": false,
3816
- "single_word": false,
3817
- "special": true
3818
- },
3819
- "477": {
3820
- "content": "<0xDD>",
3821
- "lstrip": false,
3822
- "normalized": false,
3823
- "rstrip": false,
3824
- "single_word": false,
3825
- "special": true
3826
- },
3827
- "478": {
3828
- "content": "<0xDE>",
3829
- "lstrip": false,
3830
- "normalized": false,
3831
- "rstrip": false,
3832
- "single_word": false,
3833
- "special": true
3834
- },
3835
- "479": {
3836
- "content": "<0xDF>",
3837
- "lstrip": false,
3838
- "normalized": false,
3839
- "rstrip": false,
3840
- "single_word": false,
3841
- "special": true
3842
- },
3843
- "480": {
3844
- "content": "<0xE0>",
3845
- "lstrip": false,
3846
- "normalized": false,
3847
- "rstrip": false,
3848
- "single_word": false,
3849
- "special": true
3850
- },
3851
- "481": {
3852
- "content": "<0xE1>",
3853
- "lstrip": false,
3854
- "normalized": false,
3855
- "rstrip": false,
3856
- "single_word": false,
3857
- "special": true
3858
- },
3859
- "482": {
3860
- "content": "<0xE2>",
3861
- "lstrip": false,
3862
- "normalized": false,
3863
- "rstrip": false,
3864
- "single_word": false,
3865
- "special": true
3866
- },
3867
- "483": {
3868
- "content": "<0xE3>",
3869
- "lstrip": false,
3870
- "normalized": false,
3871
- "rstrip": false,
3872
- "single_word": false,
3873
- "special": true
3874
- },
3875
- "484": {
3876
- "content": "<0xE4>",
3877
- "lstrip": false,
3878
- "normalized": false,
3879
- "rstrip": false,
3880
- "single_word": false,
3881
- "special": true
3882
- },
3883
- "485": {
3884
- "content": "<0xE5>",
3885
- "lstrip": false,
3886
- "normalized": false,
3887
- "rstrip": false,
3888
- "single_word": false,
3889
- "special": true
3890
- },
3891
- "486": {
3892
- "content": "<0xE6>",
3893
- "lstrip": false,
3894
- "normalized": false,
3895
- "rstrip": false,
3896
- "single_word": false,
3897
- "special": true
3898
- },
3899
- "487": {
3900
- "content": "<0xE7>",
3901
- "lstrip": false,
3902
- "normalized": false,
3903
- "rstrip": false,
3904
- "single_word": false,
3905
- "special": true
3906
- },
3907
- "488": {
3908
- "content": "<0xE8>",
3909
- "lstrip": false,
3910
- "normalized": false,
3911
- "rstrip": false,
3912
- "single_word": false,
3913
- "special": true
3914
- },
3915
- "489": {
3916
- "content": "<0xE9>",
3917
- "lstrip": false,
3918
- "normalized": false,
3919
- "rstrip": false,
3920
- "single_word": false,
3921
- "special": true
3922
- },
3923
- "490": {
3924
- "content": "<0xEA>",
3925
- "lstrip": false,
3926
- "normalized": false,
3927
- "rstrip": false,
3928
- "single_word": false,
3929
- "special": true
3930
- },
3931
- "491": {
3932
- "content": "<0xEB>",
3933
- "lstrip": false,
3934
- "normalized": false,
3935
- "rstrip": false,
3936
- "single_word": false,
3937
- "special": true
3938
- },
3939
- "492": {
3940
- "content": "<0xEC>",
3941
- "lstrip": false,
3942
- "normalized": false,
3943
- "rstrip": false,
3944
- "single_word": false,
3945
- "special": true
3946
- },
3947
- "493": {
3948
- "content": "<0xED>",
3949
- "lstrip": false,
3950
- "normalized": false,
3951
- "rstrip": false,
3952
- "single_word": false,
3953
- "special": true
3954
- },
3955
- "494": {
3956
- "content": "<0xEE>",
3957
- "lstrip": false,
3958
- "normalized": false,
3959
- "rstrip": false,
3960
- "single_word": false,
3961
- "special": true
3962
- },
3963
- "495": {
3964
- "content": "<0xEF>",
3965
- "lstrip": false,
3966
- "normalized": false,
3967
- "rstrip": false,
3968
- "single_word": false,
3969
- "special": true
3970
- },
3971
- "496": {
3972
- "content": "<0xF0>",
3973
- "lstrip": false,
3974
- "normalized": false,
3975
- "rstrip": false,
3976
- "single_word": false,
3977
- "special": true
3978
- },
3979
- "497": {
3980
- "content": "<0xF1>",
3981
- "lstrip": false,
3982
- "normalized": false,
3983
- "rstrip": false,
3984
- "single_word": false,
3985
- "special": true
3986
- },
3987
- "498": {
3988
- "content": "<0xF2>",
3989
- "lstrip": false,
3990
- "normalized": false,
3991
- "rstrip": false,
3992
- "single_word": false,
3993
- "special": true
3994
- },
3995
- "499": {
3996
- "content": "<0xF3>",
3997
- "lstrip": false,
3998
- "normalized": false,
3999
- "rstrip": false,
4000
- "single_word": false,
4001
- "special": true
4002
- },
4003
- "500": {
4004
- "content": "<0xF4>",
4005
- "lstrip": false,
4006
- "normalized": false,
4007
- "rstrip": false,
4008
- "single_word": false,
4009
- "special": true
4010
- },
4011
- "501": {
4012
- "content": "<0xF5>",
4013
- "lstrip": false,
4014
- "normalized": false,
4015
- "rstrip": false,
4016
- "single_word": false,
4017
- "special": true
4018
- },
4019
- "502": {
4020
- "content": "<0xF6>",
4021
- "lstrip": false,
4022
- "normalized": false,
4023
- "rstrip": false,
4024
- "single_word": false,
4025
- "special": true
4026
- },
4027
- "503": {
4028
- "content": "<0xF7>",
4029
- "lstrip": false,
4030
- "normalized": false,
4031
- "rstrip": false,
4032
- "single_word": false,
4033
- "special": true
4034
- },
4035
- "504": {
4036
- "content": "<0xF8>",
4037
- "lstrip": false,
4038
- "normalized": false,
4039
- "rstrip": false,
4040
- "single_word": false,
4041
- "special": true
4042
- },
4043
- "505": {
4044
- "content": "<0xF9>",
4045
- "lstrip": false,
4046
- "normalized": false,
4047
- "rstrip": false,
4048
- "single_word": false,
4049
- "special": true
4050
- },
4051
- "506": {
4052
- "content": "<0xFA>",
4053
- "lstrip": false,
4054
- "normalized": false,
4055
- "rstrip": false,
4056
- "single_word": false,
4057
- "special": true
4058
- },
4059
- "507": {
4060
- "content": "<0xFB>",
4061
- "lstrip": false,
4062
- "normalized": false,
4063
- "rstrip": false,
4064
- "single_word": false,
4065
- "special": true
4066
- },
4067
- "508": {
4068
- "content": "<0xFC>",
4069
- "lstrip": false,
4070
- "normalized": false,
4071
- "rstrip": false,
4072
- "single_word": false,
4073
- "special": true
4074
- },
4075
- "509": {
4076
- "content": "<0xFD>",
4077
- "lstrip": false,
4078
- "normalized": false,
4079
- "rstrip": false,
4080
- "single_word": false,
4081
- "special": true
4082
- },
4083
- "510": {
4084
- "content": "<0xFE>",
4085
- "lstrip": false,
4086
- "normalized": false,
4087
- "rstrip": false,
4088
- "single_word": false,
4089
- "special": true
4090
- },
4091
- "511": {
4092
- "content": "<0xFF>",
4093
- "lstrip": false,
4094
- "normalized": false,
4095
- "rstrip": false,
4096
- "single_word": false,
4097
- "special": true
4098
- }
4099
- },
4100
- "bos_token": "<|endoftext|>",
4101
- "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% else %}{{ eos_token }}{% endif %}",
4102
- "clean_up_tokenization_spaces": false,
4103
- "eos_token": "<|endoftext|>",
4104
- "extra_special_tokens": {},
4105
- "model_max_length": 1000000000000000019884624838656,
4106
- "pad_token": "<|endoftext|>",
4107
- "tokenizer_class": "PreTrainedTokenizerFast"
4108
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.json DELETED
The diff for this file is too large to render. See raw diff