hf-transformers-bot commited on
Commit
b397932
·
verified ·
1 Parent(s): 754218d

Add tiny processor fixture for testing

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {% set system_query = 'You should follow the instructions carefully and explain your answers in detail.' %}
2
+ {% set num_patches = 16 %}
3
+ <|im_start|>system
4
+ {{ system_query }}<|im_end|>{% for message in messages %}{% if message['role'] == 'user' %}<|im_start|>user
5
+ <img>{% for _ in range(num_patches * num_patches) %}<imgpad>{% endfor %}</img>
6
+
7
+ Chart to table<|im_end|>{% elif message['role'] == 'assistant' %}<|im_start|>assistant
8
+ {{ message.get('content', '') }}<|im_end|>{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
9
+ {% endif %}
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "pp_chart2table",
3
+ "architectures": [
4
+ "GotOcr2ForConditionalGeneration"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_pp_chart2table.PPChart2TableConfig",
8
+ "AutoModel": "modeling_pp_chart2table.PPChart2TableForConditionalGeneration"
9
+ },
10
+ "freeze_vision_tower": false,
11
+ "image_seq_length": 256,
12
+ "use_im_start_end": true,
13
+ "bos_token_id": 500,
14
+ "eos_token_id": 500,
15
+ "im_start_token": 151857,
16
+ "im_end_token": 151858,
17
+ "image_token_index": 151859,
18
+ "vocab_size": 500,
19
+ "initializer_range": 0.02,
20
+ "max_window_layers": 21,
21
+ "tie_word_embeddings": true,
22
+ "dtype": "bfloat16",
23
+ "use_cache": true,
24
+ "use_sliding_window": false,
25
+ "vision_config": {
26
+ "architectures": [
27
+ "PPChart2TableVisionModel"
28
+ ],
29
+ "auto_map": {
30
+ "AutoConfig": "configuration_pp_chart2table.PPChart2TableConfig",
31
+ "AutoModel": "modeling_pp_chart2table.PPChart2TableVisionModel"
32
+ },
33
+ "num_hidden_layers": 12,
34
+ "hidden_size": 768,
35
+ "output_channels": 256,
36
+ "hidden_act": "gelu",
37
+ "num_channels": 3,
38
+ "image_size": 1024,
39
+ "mlp_ratio": 4.0,
40
+ "mlp_dim": 3072,
41
+ "layer_norm_eps": 1e-05,
42
+ "num_attention_heads": 12,
43
+ "patch_size": 16,
44
+ "qkv_bias": true,
45
+ "use_rel_pos": true,
46
+ "use_abs_pos": true,
47
+ "global_attn_indexes": [
48
+ 2,
49
+ 5,
50
+ 8,
51
+ 11
52
+ ],
53
+ "window_size": 14,
54
+ "attention_dropout": 0.0
55
+ },
56
+ "text_config": {
57
+ "architectures": [
58
+ "PPChart2TableTextModel"
59
+ ],
60
+ "auto_map": {
61
+ "AutoConfig": "configuration_qwen2.Qwen2Config",
62
+ "AutoModel": "modeling_qwen2.Qwen2Model"
63
+ },
64
+ "hidden_size": 1024,
65
+ "hidden_act": "silu",
66
+ "num_hidden_layers": 24,
67
+ "num_attention_heads": 16,
68
+ "num_key_value_heads": 16,
69
+ "intermediate_size": 2816,
70
+ "attention_dropout": 0.0,
71
+ "sliding_window": 32768,
72
+ "rms_norm_eps": 1e-06,
73
+ "vocab_size": 151860,
74
+ "max_position_embeddings": 32768,
75
+ "rope_parameters": {
76
+ "rope_theta": 1000000.0,
77
+ "rope_type": "default"
78
+ }
79
+ }
80
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": 151645,
3
+ "pad_token_id": 151643,
4
+ "max_new_tokens": 2048
5
+ }
inference.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ mode: paddle
2
+ Global:
3
+ model_name: PP-Chart2Table
preprocessor_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_processor_type": "PPChart2TableImageProcessor",
20
+ "model_input_names": ["pixel_values", "original_image_size"],
21
+ "image_mode": "RGB",
22
+ "channel_first": false,
23
+ "image_mean": [0.48145466, 0.4578275, 0.40821073],
24
+ "image_std": [0.26862954, 0.26130258, 0.27577711],
25
+ "rescale_factor": 0.00392156862745098,
26
+ "resample": 3,
27
+ "normalize_order": "hwc",
28
+ "do_to_chw": true,
29
+ "size": {
30
+ "height": 1024,
31
+ "width": 1024
32
+ },
33
+ "keep_keys": ["image", "shape", "polys", "ignore_tags"]
34
+ }
qwen.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3504 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|extra_0|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": true,
40
+ "special": false
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|extra_1|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": true,
49
+ "special": false
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|extra_2|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": true,
58
+ "special": false
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|extra_3|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": true,
67
+ "special": false
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|extra_4|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": true,
76
+ "special": false
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|extra_5|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|extra_6|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|extra_7|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|extra_8|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|extra_9|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|extra_10|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<|extra_11|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "<|extra_12|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|extra_13|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": true,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|extra_14|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": true,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|extra_15|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": true,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|extra_16|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": true,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|extra_17|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": true,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|extra_18|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": true,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<|extra_19|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": true,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "<|extra_20|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": true,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<|extra_21|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": true,
229
+ "special": false
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "<|extra_22|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": true,
238
+ "special": false
239
+ },
240
+ {
241
+ "id": 526,
242
+ "content": "<|extra_23|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": true,
247
+ "special": false
248
+ },
249
+ {
250
+ "id": 527,
251
+ "content": "<|extra_24|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": true,
256
+ "special": false
257
+ },
258
+ {
259
+ "id": 528,
260
+ "content": "<|extra_25|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": true,
265
+ "special": false
266
+ },
267
+ {
268
+ "id": 529,
269
+ "content": "<|extra_26|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": true,
274
+ "special": false
275
+ },
276
+ {
277
+ "id": 530,
278
+ "content": "<|extra_27|>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": true,
283
+ "special": false
284
+ },
285
+ {
286
+ "id": 531,
287
+ "content": "<|extra_28|>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": true,
292
+ "special": false
293
+ },
294
+ {
295
+ "id": 532,
296
+ "content": "<|extra_29|>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": true,
301
+ "special": false
302
+ },
303
+ {
304
+ "id": 533,
305
+ "content": "<|extra_30|>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": true,
310
+ "special": false
311
+ },
312
+ {
313
+ "id": 534,
314
+ "content": "<|extra_31|>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": true,
319
+ "special": false
320
+ },
321
+ {
322
+ "id": 535,
323
+ "content": "<|extra_32|>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": true,
328
+ "special": false
329
+ },
330
+ {
331
+ "id": 536,
332
+ "content": "<|extra_33|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": true,
337
+ "special": false
338
+ },
339
+ {
340
+ "id": 537,
341
+ "content": "<|extra_34|>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": true,
346
+ "special": false
347
+ },
348
+ {
349
+ "id": 538,
350
+ "content": "<|extra_35|>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": true,
355
+ "special": false
356
+ },
357
+ {
358
+ "id": 539,
359
+ "content": "<|extra_36|>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": true,
364
+ "special": false
365
+ },
366
+ {
367
+ "id": 540,
368
+ "content": "<|extra_37|>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": true,
373
+ "special": false
374
+ },
375
+ {
376
+ "id": 541,
377
+ "content": "<|extra_38|>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": true,
382
+ "special": false
383
+ },
384
+ {
385
+ "id": 542,
386
+ "content": "<|extra_39|>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": true,
391
+ "special": false
392
+ },
393
+ {
394
+ "id": 543,
395
+ "content": "<|extra_40|>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": true,
400
+ "special": false
401
+ },
402
+ {
403
+ "id": 544,
404
+ "content": "<|extra_41|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": true,
409
+ "special": false
410
+ },
411
+ {
412
+ "id": 545,
413
+ "content": "<|extra_42|>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": true,
418
+ "special": false
419
+ },
420
+ {
421
+ "id": 546,
422
+ "content": "<|extra_43|>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": true,
427
+ "special": false
428
+ },
429
+ {
430
+ "id": 547,
431
+ "content": "<|extra_44|>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": true,
436
+ "special": false
437
+ },
438
+ {
439
+ "id": 548,
440
+ "content": "<|extra_45|>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": true,
445
+ "special": false
446
+ },
447
+ {
448
+ "id": 549,
449
+ "content": "<|extra_46|>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": true,
454
+ "special": false
455
+ },
456
+ {
457
+ "id": 550,
458
+ "content": "<|extra_47|>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": true,
463
+ "special": false
464
+ },
465
+ {
466
+ "id": 551,
467
+ "content": "<|extra_48|>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": true,
472
+ "special": false
473
+ },
474
+ {
475
+ "id": 552,
476
+ "content": "<|extra_49|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": true,
481
+ "special": false
482
+ },
483
+ {
484
+ "id": 553,
485
+ "content": "<|extra_50|>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": true,
490
+ "special": false
491
+ },
492
+ {
493
+ "id": 554,
494
+ "content": "<|extra_51|>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": true,
499
+ "special": false
500
+ },
501
+ {
502
+ "id": 555,
503
+ "content": "<|extra_52|>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": true,
508
+ "special": false
509
+ },
510
+ {
511
+ "id": 556,
512
+ "content": "<|extra_53|>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": true,
517
+ "special": false
518
+ },
519
+ {
520
+ "id": 557,
521
+ "content": "<|extra_54|>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": true,
526
+ "special": false
527
+ },
528
+ {
529
+ "id": 558,
530
+ "content": "<|extra_55|>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": true,
535
+ "special": false
536
+ },
537
+ {
538
+ "id": 559,
539
+ "content": "<|extra_56|>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": true,
544
+ "special": false
545
+ },
546
+ {
547
+ "id": 560,
548
+ "content": "<|extra_57|>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": true,
553
+ "special": false
554
+ },
555
+ {
556
+ "id": 561,
557
+ "content": "<|extra_58|>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": true,
562
+ "special": false
563
+ },
564
+ {
565
+ "id": 562,
566
+ "content": "<|extra_59|>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": true,
571
+ "special": false
572
+ },
573
+ {
574
+ "id": 563,
575
+ "content": "<|extra_60|>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": true,
580
+ "special": false
581
+ },
582
+ {
583
+ "id": 564,
584
+ "content": "<|extra_61|>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": true,
589
+ "special": false
590
+ },
591
+ {
592
+ "id": 565,
593
+ "content": "<|extra_62|>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": true,
598
+ "special": false
599
+ },
600
+ {
601
+ "id": 566,
602
+ "content": "<|extra_63|>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": true,
607
+ "special": false
608
+ },
609
+ {
610
+ "id": 567,
611
+ "content": "<|extra_64|>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": true,
616
+ "special": false
617
+ },
618
+ {
619
+ "id": 568,
620
+ "content": "<|extra_65|>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": true,
625
+ "special": false
626
+ },
627
+ {
628
+ "id": 569,
629
+ "content": "<|extra_66|>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": true,
634
+ "special": false
635
+ },
636
+ {
637
+ "id": 570,
638
+ "content": "<|extra_67|>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": true,
643
+ "special": false
644
+ },
645
+ {
646
+ "id": 571,
647
+ "content": "<|extra_68|>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": true,
652
+ "special": false
653
+ },
654
+ {
655
+ "id": 572,
656
+ "content": "<|extra_69|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": true,
661
+ "special": false
662
+ },
663
+ {
664
+ "id": 573,
665
+ "content": "<|extra_70|>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": true,
670
+ "special": false
671
+ },
672
+ {
673
+ "id": 574,
674
+ "content": "<|extra_71|>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": true,
679
+ "special": false
680
+ },
681
+ {
682
+ "id": 575,
683
+ "content": "<|extra_72|>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": true,
688
+ "special": false
689
+ },
690
+ {
691
+ "id": 576,
692
+ "content": "<|extra_73|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": true,
697
+ "special": false
698
+ },
699
+ {
700
+ "id": 577,
701
+ "content": "<|extra_74|>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": true,
706
+ "special": false
707
+ },
708
+ {
709
+ "id": 578,
710
+ "content": "<|extra_75|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": true,
715
+ "special": false
716
+ },
717
+ {
718
+ "id": 579,
719
+ "content": "<|extra_76|>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": true,
724
+ "special": false
725
+ },
726
+ {
727
+ "id": 580,
728
+ "content": "<|extra_77|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": true,
733
+ "special": false
734
+ },
735
+ {
736
+ "id": 581,
737
+ "content": "<|extra_78|>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": true,
742
+ "special": false
743
+ },
744
+ {
745
+ "id": 582,
746
+ "content": "<|extra_79|>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": true,
751
+ "special": false
752
+ },
753
+ {
754
+ "id": 583,
755
+ "content": "<|extra_80|>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": true,
760
+ "special": false
761
+ },
762
+ {
763
+ "id": 584,
764
+ "content": "<|extra_81|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": true,
769
+ "special": false
770
+ },
771
+ {
772
+ "id": 585,
773
+ "content": "<|extra_82|>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": true,
778
+ "special": false
779
+ },
780
+ {
781
+ "id": 586,
782
+ "content": "<|extra_83|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": true,
787
+ "special": false
788
+ },
789
+ {
790
+ "id": 587,
791
+ "content": "<|extra_84|>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": true,
796
+ "special": false
797
+ },
798
+ {
799
+ "id": 588,
800
+ "content": "<|extra_85|>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": true,
805
+ "special": false
806
+ },
807
+ {
808
+ "id": 589,
809
+ "content": "<|extra_86|>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": true,
814
+ "special": false
815
+ },
816
+ {
817
+ "id": 590,
818
+ "content": "<|extra_87|>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": true,
823
+ "special": false
824
+ },
825
+ {
826
+ "id": 591,
827
+ "content": "<|extra_88|>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": true,
832
+ "special": false
833
+ },
834
+ {
835
+ "id": 592,
836
+ "content": "<|extra_89|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": true,
841
+ "special": false
842
+ },
843
+ {
844
+ "id": 593,
845
+ "content": "<|extra_90|>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": true,
850
+ "special": false
851
+ },
852
+ {
853
+ "id": 594,
854
+ "content": "<|extra_91|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": true,
859
+ "special": false
860
+ },
861
+ {
862
+ "id": 595,
863
+ "content": "<|extra_92|>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": true,
868
+ "special": false
869
+ },
870
+ {
871
+ "id": 596,
872
+ "content": "<|extra_93|>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": true,
877
+ "special": false
878
+ },
879
+ {
880
+ "id": 597,
881
+ "content": "<|extra_94|>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": true,
886
+ "special": false
887
+ },
888
+ {
889
+ "id": 598,
890
+ "content": "<|extra_95|>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": true,
895
+ "special": false
896
+ },
897
+ {
898
+ "id": 599,
899
+ "content": "<|extra_96|>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": true,
904
+ "special": false
905
+ },
906
+ {
907
+ "id": 600,
908
+ "content": "<|extra_97|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": true,
913
+ "special": false
914
+ },
915
+ {
916
+ "id": 601,
917
+ "content": "<|extra_98|>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": true,
922
+ "special": false
923
+ },
924
+ {
925
+ "id": 602,
926
+ "content": "<|extra_99|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": true,
931
+ "special": false
932
+ },
933
+ {
934
+ "id": 603,
935
+ "content": "<|extra_100|>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": true,
940
+ "special": false
941
+ },
942
+ {
943
+ "id": 604,
944
+ "content": "<|extra_101|>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": true,
949
+ "special": false
950
+ },
951
+ {
952
+ "id": 605,
953
+ "content": "<|extra_102|>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": true,
958
+ "special": false
959
+ },
960
+ {
961
+ "id": 606,
962
+ "content": "<|extra_103|>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": true,
967
+ "special": false
968
+ },
969
+ {
970
+ "id": 607,
971
+ "content": "<|extra_104|>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": true,
976
+ "special": false
977
+ },
978
+ {
979
+ "id": 608,
980
+ "content": "<|extra_105|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": true,
985
+ "special": false
986
+ },
987
+ {
988
+ "id": 609,
989
+ "content": "<|extra_106|>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": true,
994
+ "special": false
995
+ },
996
+ {
997
+ "id": 610,
998
+ "content": "<|extra_107|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": true,
1003
+ "special": false
1004
+ },
1005
+ {
1006
+ "id": 611,
1007
+ "content": "<|extra_108|>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": true,
1012
+ "special": false
1013
+ },
1014
+ {
1015
+ "id": 612,
1016
+ "content": "<|extra_109|>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": true,
1021
+ "special": false
1022
+ },
1023
+ {
1024
+ "id": 613,
1025
+ "content": "<|extra_110|>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": true,
1030
+ "special": false
1031
+ },
1032
+ {
1033
+ "id": 614,
1034
+ "content": "<|extra_111|>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": true,
1039
+ "special": false
1040
+ },
1041
+ {
1042
+ "id": 615,
1043
+ "content": "<|extra_112|>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": true,
1048
+ "special": false
1049
+ },
1050
+ {
1051
+ "id": 616,
1052
+ "content": "<|extra_113|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": true,
1057
+ "special": false
1058
+ },
1059
+ {
1060
+ "id": 617,
1061
+ "content": "<|extra_114|>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": true,
1066
+ "special": false
1067
+ },
1068
+ {
1069
+ "id": 618,
1070
+ "content": "<|extra_115|>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": true,
1075
+ "special": false
1076
+ },
1077
+ {
1078
+ "id": 619,
1079
+ "content": "<|extra_116|>",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": true,
1084
+ "special": false
1085
+ },
1086
+ {
1087
+ "id": 620,
1088
+ "content": "<|extra_117|>",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": true,
1093
+ "special": false
1094
+ },
1095
+ {
1096
+ "id": 621,
1097
+ "content": "<|extra_118|>",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": true,
1102
+ "special": false
1103
+ },
1104
+ {
1105
+ "id": 622,
1106
+ "content": "<|extra_119|>",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": true,
1111
+ "special": false
1112
+ },
1113
+ {
1114
+ "id": 623,
1115
+ "content": "<|extra_120|>",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": true,
1120
+ "special": false
1121
+ },
1122
+ {
1123
+ "id": 624,
1124
+ "content": "<|extra_121|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": true,
1129
+ "special": false
1130
+ },
1131
+ {
1132
+ "id": 625,
1133
+ "content": "<|extra_122|>",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": true,
1138
+ "special": false
1139
+ },
1140
+ {
1141
+ "id": 626,
1142
+ "content": "<|extra_123|>",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": true,
1147
+ "special": false
1148
+ },
1149
+ {
1150
+ "id": 627,
1151
+ "content": "<|extra_124|>",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": true,
1156
+ "special": false
1157
+ },
1158
+ {
1159
+ "id": 628,
1160
+ "content": "<|extra_125|>",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": true,
1165
+ "special": false
1166
+ },
1167
+ {
1168
+ "id": 629,
1169
+ "content": "<|extra_126|>",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": true,
1174
+ "special": false
1175
+ },
1176
+ {
1177
+ "id": 630,
1178
+ "content": "<|extra_127|>",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": true,
1183
+ "special": false
1184
+ },
1185
+ {
1186
+ "id": 631,
1187
+ "content": "<|extra_128|>",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": true,
1192
+ "special": false
1193
+ },
1194
+ {
1195
+ "id": 632,
1196
+ "content": "<|extra_129|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": true,
1201
+ "special": false
1202
+ },
1203
+ {
1204
+ "id": 633,
1205
+ "content": "<|extra_130|>",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": true,
1210
+ "special": false
1211
+ },
1212
+ {
1213
+ "id": 634,
1214
+ "content": "<|extra_131|>",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": true,
1219
+ "special": false
1220
+ },
1221
+ {
1222
+ "id": 635,
1223
+ "content": "<|extra_132|>",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": true,
1228
+ "special": false
1229
+ },
1230
+ {
1231
+ "id": 636,
1232
+ "content": "<|extra_133|>",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": true,
1237
+ "special": false
1238
+ },
1239
+ {
1240
+ "id": 637,
1241
+ "content": "<|extra_134|>",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": true,
1246
+ "special": false
1247
+ },
1248
+ {
1249
+ "id": 638,
1250
+ "content": "<|extra_135|>",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": true,
1255
+ "special": false
1256
+ },
1257
+ {
1258
+ "id": 639,
1259
+ "content": "<|extra_136|>",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": true,
1264
+ "special": false
1265
+ },
1266
+ {
1267
+ "id": 640,
1268
+ "content": "<|extra_137|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": true,
1273
+ "special": false
1274
+ },
1275
+ {
1276
+ "id": 641,
1277
+ "content": "<|extra_138|>",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": true,
1282
+ "special": false
1283
+ },
1284
+ {
1285
+ "id": 642,
1286
+ "content": "<|extra_139|>",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": true,
1291
+ "special": false
1292
+ },
1293
+ {
1294
+ "id": 643,
1295
+ "content": "<|extra_140|>",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": true,
1300
+ "special": false
1301
+ },
1302
+ {
1303
+ "id": 644,
1304
+ "content": "<|extra_141|>",
1305
+ "single_word": false,
1306
+ "lstrip": false,
1307
+ "rstrip": false,
1308
+ "normalized": true,
1309
+ "special": false
1310
+ },
1311
+ {
1312
+ "id": 645,
1313
+ "content": "<|extra_142|>",
1314
+ "single_word": false,
1315
+ "lstrip": false,
1316
+ "rstrip": false,
1317
+ "normalized": true,
1318
+ "special": false
1319
+ },
1320
+ {
1321
+ "id": 646,
1322
+ "content": "<|extra_143|>",
1323
+ "single_word": false,
1324
+ "lstrip": false,
1325
+ "rstrip": false,
1326
+ "normalized": true,
1327
+ "special": false
1328
+ },
1329
+ {
1330
+ "id": 647,
1331
+ "content": "<|extra_144|>",
1332
+ "single_word": false,
1333
+ "lstrip": false,
1334
+ "rstrip": false,
1335
+ "normalized": true,
1336
+ "special": false
1337
+ },
1338
+ {
1339
+ "id": 648,
1340
+ "content": "<|extra_145|>",
1341
+ "single_word": false,
1342
+ "lstrip": false,
1343
+ "rstrip": false,
1344
+ "normalized": true,
1345
+ "special": false
1346
+ },
1347
+ {
1348
+ "id": 649,
1349
+ "content": "<|extra_146|>",
1350
+ "single_word": false,
1351
+ "lstrip": false,
1352
+ "rstrip": false,
1353
+ "normalized": true,
1354
+ "special": false
1355
+ },
1356
+ {
1357
+ "id": 650,
1358
+ "content": "<|extra_147|>",
1359
+ "single_word": false,
1360
+ "lstrip": false,
1361
+ "rstrip": false,
1362
+ "normalized": true,
1363
+ "special": false
1364
+ },
1365
+ {
1366
+ "id": 651,
1367
+ "content": "<|extra_148|>",
1368
+ "single_word": false,
1369
+ "lstrip": false,
1370
+ "rstrip": false,
1371
+ "normalized": true,
1372
+ "special": false
1373
+ },
1374
+ {
1375
+ "id": 652,
1376
+ "content": "<|extra_149|>",
1377
+ "single_word": false,
1378
+ "lstrip": false,
1379
+ "rstrip": false,
1380
+ "normalized": true,
1381
+ "special": false
1382
+ },
1383
+ {
1384
+ "id": 653,
1385
+ "content": "<|extra_150|>",
1386
+ "single_word": false,
1387
+ "lstrip": false,
1388
+ "rstrip": false,
1389
+ "normalized": true,
1390
+ "special": false
1391
+ },
1392
+ {
1393
+ "id": 654,
1394
+ "content": "<|extra_151|>",
1395
+ "single_word": false,
1396
+ "lstrip": false,
1397
+ "rstrip": false,
1398
+ "normalized": true,
1399
+ "special": false
1400
+ },
1401
+ {
1402
+ "id": 655,
1403
+ "content": "<|extra_152|>",
1404
+ "single_word": false,
1405
+ "lstrip": false,
1406
+ "rstrip": false,
1407
+ "normalized": true,
1408
+ "special": false
1409
+ },
1410
+ {
1411
+ "id": 656,
1412
+ "content": "<|extra_153|>",
1413
+ "single_word": false,
1414
+ "lstrip": false,
1415
+ "rstrip": false,
1416
+ "normalized": true,
1417
+ "special": false
1418
+ },
1419
+ {
1420
+ "id": 657,
1421
+ "content": "<|extra_154|>",
1422
+ "single_word": false,
1423
+ "lstrip": false,
1424
+ "rstrip": false,
1425
+ "normalized": true,
1426
+ "special": false
1427
+ },
1428
+ {
1429
+ "id": 658,
1430
+ "content": "<|extra_155|>",
1431
+ "single_word": false,
1432
+ "lstrip": false,
1433
+ "rstrip": false,
1434
+ "normalized": true,
1435
+ "special": false
1436
+ },
1437
+ {
1438
+ "id": 659,
1439
+ "content": "<|extra_156|>",
1440
+ "single_word": false,
1441
+ "lstrip": false,
1442
+ "rstrip": false,
1443
+ "normalized": true,
1444
+ "special": false
1445
+ },
1446
+ {
1447
+ "id": 660,
1448
+ "content": "<|extra_157|>",
1449
+ "single_word": false,
1450
+ "lstrip": false,
1451
+ "rstrip": false,
1452
+ "normalized": true,
1453
+ "special": false
1454
+ },
1455
+ {
1456
+ "id": 661,
1457
+ "content": "<|extra_158|>",
1458
+ "single_word": false,
1459
+ "lstrip": false,
1460
+ "rstrip": false,
1461
+ "normalized": true,
1462
+ "special": false
1463
+ },
1464
+ {
1465
+ "id": 662,
1466
+ "content": "<|extra_159|>",
1467
+ "single_word": false,
1468
+ "lstrip": false,
1469
+ "rstrip": false,
1470
+ "normalized": true,
1471
+ "special": false
1472
+ },
1473
+ {
1474
+ "id": 663,
1475
+ "content": "<|extra_160|>",
1476
+ "single_word": false,
1477
+ "lstrip": false,
1478
+ "rstrip": false,
1479
+ "normalized": true,
1480
+ "special": false
1481
+ },
1482
+ {
1483
+ "id": 664,
1484
+ "content": "<|extra_161|>",
1485
+ "single_word": false,
1486
+ "lstrip": false,
1487
+ "rstrip": false,
1488
+ "normalized": true,
1489
+ "special": false
1490
+ },
1491
+ {
1492
+ "id": 665,
1493
+ "content": "<|extra_162|>",
1494
+ "single_word": false,
1495
+ "lstrip": false,
1496
+ "rstrip": false,
1497
+ "normalized": true,
1498
+ "special": false
1499
+ },
1500
+ {
1501
+ "id": 666,
1502
+ "content": "<|extra_163|>",
1503
+ "single_word": false,
1504
+ "lstrip": false,
1505
+ "rstrip": false,
1506
+ "normalized": true,
1507
+ "special": false
1508
+ },
1509
+ {
1510
+ "id": 667,
1511
+ "content": "<|extra_164|>",
1512
+ "single_word": false,
1513
+ "lstrip": false,
1514
+ "rstrip": false,
1515
+ "normalized": true,
1516
+ "special": false
1517
+ },
1518
+ {
1519
+ "id": 668,
1520
+ "content": "<|extra_165|>",
1521
+ "single_word": false,
1522
+ "lstrip": false,
1523
+ "rstrip": false,
1524
+ "normalized": true,
1525
+ "special": false
1526
+ },
1527
+ {
1528
+ "id": 669,
1529
+ "content": "<|extra_166|>",
1530
+ "single_word": false,
1531
+ "lstrip": false,
1532
+ "rstrip": false,
1533
+ "normalized": true,
1534
+ "special": false
1535
+ },
1536
+ {
1537
+ "id": 670,
1538
+ "content": "<|extra_167|>",
1539
+ "single_word": false,
1540
+ "lstrip": false,
1541
+ "rstrip": false,
1542
+ "normalized": true,
1543
+ "special": false
1544
+ },
1545
+ {
1546
+ "id": 671,
1547
+ "content": "<|extra_168|>",
1548
+ "single_word": false,
1549
+ "lstrip": false,
1550
+ "rstrip": false,
1551
+ "normalized": true,
1552
+ "special": false
1553
+ },
1554
+ {
1555
+ "id": 672,
1556
+ "content": "<|extra_169|>",
1557
+ "single_word": false,
1558
+ "lstrip": false,
1559
+ "rstrip": false,
1560
+ "normalized": true,
1561
+ "special": false
1562
+ },
1563
+ {
1564
+ "id": 673,
1565
+ "content": "<|extra_170|>",
1566
+ "single_word": false,
1567
+ "lstrip": false,
1568
+ "rstrip": false,
1569
+ "normalized": true,
1570
+ "special": false
1571
+ },
1572
+ {
1573
+ "id": 674,
1574
+ "content": "<|extra_171|>",
1575
+ "single_word": false,
1576
+ "lstrip": false,
1577
+ "rstrip": false,
1578
+ "normalized": true,
1579
+ "special": false
1580
+ },
1581
+ {
1582
+ "id": 675,
1583
+ "content": "<|extra_172|>",
1584
+ "single_word": false,
1585
+ "lstrip": false,
1586
+ "rstrip": false,
1587
+ "normalized": true,
1588
+ "special": false
1589
+ },
1590
+ {
1591
+ "id": 676,
1592
+ "content": "<|extra_173|>",
1593
+ "single_word": false,
1594
+ "lstrip": false,
1595
+ "rstrip": false,
1596
+ "normalized": true,
1597
+ "special": false
1598
+ },
1599
+ {
1600
+ "id": 677,
1601
+ "content": "<|extra_174|>",
1602
+ "single_word": false,
1603
+ "lstrip": false,
1604
+ "rstrip": false,
1605
+ "normalized": true,
1606
+ "special": false
1607
+ },
1608
+ {
1609
+ "id": 678,
1610
+ "content": "<|extra_175|>",
1611
+ "single_word": false,
1612
+ "lstrip": false,
1613
+ "rstrip": false,
1614
+ "normalized": true,
1615
+ "special": false
1616
+ },
1617
+ {
1618
+ "id": 679,
1619
+ "content": "<|extra_176|>",
1620
+ "single_word": false,
1621
+ "lstrip": false,
1622
+ "rstrip": false,
1623
+ "normalized": true,
1624
+ "special": false
1625
+ },
1626
+ {
1627
+ "id": 680,
1628
+ "content": "<|extra_177|>",
1629
+ "single_word": false,
1630
+ "lstrip": false,
1631
+ "rstrip": false,
1632
+ "normalized": true,
1633
+ "special": false
1634
+ },
1635
+ {
1636
+ "id": 681,
1637
+ "content": "<|extra_178|>",
1638
+ "single_word": false,
1639
+ "lstrip": false,
1640
+ "rstrip": false,
1641
+ "normalized": true,
1642
+ "special": false
1643
+ },
1644
+ {
1645
+ "id": 682,
1646
+ "content": "<|extra_179|>",
1647
+ "single_word": false,
1648
+ "lstrip": false,
1649
+ "rstrip": false,
1650
+ "normalized": true,
1651
+ "special": false
1652
+ },
1653
+ {
1654
+ "id": 683,
1655
+ "content": "<|extra_180|>",
1656
+ "single_word": false,
1657
+ "lstrip": false,
1658
+ "rstrip": false,
1659
+ "normalized": true,
1660
+ "special": false
1661
+ },
1662
+ {
1663
+ "id": 684,
1664
+ "content": "<|extra_181|>",
1665
+ "single_word": false,
1666
+ "lstrip": false,
1667
+ "rstrip": false,
1668
+ "normalized": true,
1669
+ "special": false
1670
+ },
1671
+ {
1672
+ "id": 685,
1673
+ "content": "<|extra_182|>",
1674
+ "single_word": false,
1675
+ "lstrip": false,
1676
+ "rstrip": false,
1677
+ "normalized": true,
1678
+ "special": false
1679
+ },
1680
+ {
1681
+ "id": 686,
1682
+ "content": "<|extra_183|>",
1683
+ "single_word": false,
1684
+ "lstrip": false,
1685
+ "rstrip": false,
1686
+ "normalized": true,
1687
+ "special": false
1688
+ },
1689
+ {
1690
+ "id": 687,
1691
+ "content": "<|extra_184|>",
1692
+ "single_word": false,
1693
+ "lstrip": false,
1694
+ "rstrip": false,
1695
+ "normalized": true,
1696
+ "special": false
1697
+ },
1698
+ {
1699
+ "id": 688,
1700
+ "content": "<|extra_185|>",
1701
+ "single_word": false,
1702
+ "lstrip": false,
1703
+ "rstrip": false,
1704
+ "normalized": true,
1705
+ "special": false
1706
+ },
1707
+ {
1708
+ "id": 689,
1709
+ "content": "<|extra_186|>",
1710
+ "single_word": false,
1711
+ "lstrip": false,
1712
+ "rstrip": false,
1713
+ "normalized": true,
1714
+ "special": false
1715
+ },
1716
+ {
1717
+ "id": 690,
1718
+ "content": "<|extra_187|>",
1719
+ "single_word": false,
1720
+ "lstrip": false,
1721
+ "rstrip": false,
1722
+ "normalized": true,
1723
+ "special": false
1724
+ },
1725
+ {
1726
+ "id": 691,
1727
+ "content": "<|extra_188|>",
1728
+ "single_word": false,
1729
+ "lstrip": false,
1730
+ "rstrip": false,
1731
+ "normalized": true,
1732
+ "special": false
1733
+ },
1734
+ {
1735
+ "id": 692,
1736
+ "content": "<|extra_189|>",
1737
+ "single_word": false,
1738
+ "lstrip": false,
1739
+ "rstrip": false,
1740
+ "normalized": true,
1741
+ "special": false
1742
+ },
1743
+ {
1744
+ "id": 693,
1745
+ "content": "<|extra_190|>",
1746
+ "single_word": false,
1747
+ "lstrip": false,
1748
+ "rstrip": false,
1749
+ "normalized": true,
1750
+ "special": false
1751
+ },
1752
+ {
1753
+ "id": 694,
1754
+ "content": "<|extra_191|>",
1755
+ "single_word": false,
1756
+ "lstrip": false,
1757
+ "rstrip": false,
1758
+ "normalized": true,
1759
+ "special": false
1760
+ },
1761
+ {
1762
+ "id": 695,
1763
+ "content": "<|extra_192|>",
1764
+ "single_word": false,
1765
+ "lstrip": false,
1766
+ "rstrip": false,
1767
+ "normalized": true,
1768
+ "special": false
1769
+ },
1770
+ {
1771
+ "id": 696,
1772
+ "content": "<|extra_193|>",
1773
+ "single_word": false,
1774
+ "lstrip": false,
1775
+ "rstrip": false,
1776
+ "normalized": true,
1777
+ "special": false
1778
+ },
1779
+ {
1780
+ "id": 697,
1781
+ "content": "<|extra_194|>",
1782
+ "single_word": false,
1783
+ "lstrip": false,
1784
+ "rstrip": false,
1785
+ "normalized": true,
1786
+ "special": false
1787
+ },
1788
+ {
1789
+ "id": 698,
1790
+ "content": "<|extra_195|>",
1791
+ "single_word": false,
1792
+ "lstrip": false,
1793
+ "rstrip": false,
1794
+ "normalized": true,
1795
+ "special": false
1796
+ },
1797
+ {
1798
+ "id": 699,
1799
+ "content": "<|extra_196|>",
1800
+ "single_word": false,
1801
+ "lstrip": false,
1802
+ "rstrip": false,
1803
+ "normalized": true,
1804
+ "special": false
1805
+ },
1806
+ {
1807
+ "id": 700,
1808
+ "content": "<|extra_197|>",
1809
+ "single_word": false,
1810
+ "lstrip": false,
1811
+ "rstrip": false,
1812
+ "normalized": true,
1813
+ "special": false
1814
+ },
1815
+ {
1816
+ "id": 701,
1817
+ "content": "<|extra_198|>",
1818
+ "single_word": false,
1819
+ "lstrip": false,
1820
+ "rstrip": false,
1821
+ "normalized": true,
1822
+ "special": false
1823
+ },
1824
+ {
1825
+ "id": 702,
1826
+ "content": "<|extra_199|>",
1827
+ "single_word": false,
1828
+ "lstrip": false,
1829
+ "rstrip": false,
1830
+ "normalized": true,
1831
+ "special": false
1832
+ },
1833
+ {
1834
+ "id": 703,
1835
+ "content": "<|extra_200|>",
1836
+ "single_word": false,
1837
+ "lstrip": false,
1838
+ "rstrip": false,
1839
+ "normalized": true,
1840
+ "special": false
1841
+ },
1842
+ {
1843
+ "id": 704,
1844
+ "content": "<|extra_201|>",
1845
+ "single_word": false,
1846
+ "lstrip": false,
1847
+ "rstrip": false,
1848
+ "normalized": true,
1849
+ "special": false
1850
+ },
1851
+ {
1852
+ "id": 705,
1853
+ "content": "<|extra_202|>",
1854
+ "single_word": false,
1855
+ "lstrip": false,
1856
+ "rstrip": false,
1857
+ "normalized": true,
1858
+ "special": false
1859
+ },
1860
+ {
1861
+ "id": 706,
1862
+ "content": "<|extra_203|>",
1863
+ "single_word": false,
1864
+ "lstrip": false,
1865
+ "rstrip": false,
1866
+ "normalized": true,
1867
+ "special": false
1868
+ },
1869
+ {
1870
+ "id": 707,
1871
+ "content": "<|extra_204|>",
1872
+ "single_word": false,
1873
+ "lstrip": false,
1874
+ "rstrip": false,
1875
+ "normalized": true,
1876
+ "special": false
1877
+ },
1878
+ {
1879
+ "id": 708,
1880
+ "content": "<ref>",
1881
+ "single_word": false,
1882
+ "lstrip": false,
1883
+ "rstrip": false,
1884
+ "normalized": false,
1885
+ "special": true
1886
+ },
1887
+ {
1888
+ "id": 709,
1889
+ "content": "</ref>",
1890
+ "single_word": false,
1891
+ "lstrip": false,
1892
+ "rstrip": false,
1893
+ "normalized": false,
1894
+ "special": true
1895
+ },
1896
+ {
1897
+ "id": 710,
1898
+ "content": "<box>",
1899
+ "single_word": false,
1900
+ "lstrip": false,
1901
+ "rstrip": false,
1902
+ "normalized": false,
1903
+ "special": true
1904
+ },
1905
+ {
1906
+ "id": 711,
1907
+ "content": "</box>",
1908
+ "single_word": false,
1909
+ "lstrip": false,
1910
+ "rstrip": false,
1911
+ "normalized": false,
1912
+ "special": true
1913
+ },
1914
+ {
1915
+ "id": 712,
1916
+ "content": "<quad>",
1917
+ "single_word": false,
1918
+ "lstrip": false,
1919
+ "rstrip": false,
1920
+ "normalized": false,
1921
+ "special": true
1922
+ },
1923
+ {
1924
+ "id": 713,
1925
+ "content": "</quad>",
1926
+ "single_word": false,
1927
+ "lstrip": false,
1928
+ "rstrip": false,
1929
+ "normalized": false,
1930
+ "special": true
1931
+ },
1932
+ {
1933
+ "id": 714,
1934
+ "content": "<img>",
1935
+ "single_word": false,
1936
+ "lstrip": false,
1937
+ "rstrip": false,
1938
+ "normalized": false,
1939
+ "special": true
1940
+ },
1941
+ {
1942
+ "id": 715,
1943
+ "content": "</img>",
1944
+ "single_word": false,
1945
+ "lstrip": false,
1946
+ "rstrip": false,
1947
+ "normalized": false,
1948
+ "special": true
1949
+ },
1950
+ {
1951
+ "id": 716,
1952
+ "content": "<imgpad>",
1953
+ "single_word": false,
1954
+ "lstrip": false,
1955
+ "rstrip": false,
1956
+ "normalized": false,
1957
+ "special": true
1958
+ }
1959
+ ],
1960
+ "normalizer": {
1961
+ "type": "NFC"
1962
+ },
1963
+ "pre_tokenizer": {
1964
+ "type": "Sequence",
1965
+ "pretokenizers": [
1966
+ {
1967
+ "type": "Split",
1968
+ "pattern": {
1969
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
1970
+ },
1971
+ "behavior": "Isolated",
1972
+ "invert": false
1973
+ },
1974
+ {
1975
+ "type": "ByteLevel",
1976
+ "add_prefix_space": false,
1977
+ "trim_offsets": true,
1978
+ "use_regex": false
1979
+ }
1980
+ ]
1981
+ },
1982
+ "post_processor": {
1983
+ "type": "TemplateProcessing",
1984
+ "single": [
1985
+ {
1986
+ "Sequence": {
1987
+ "id": "A",
1988
+ "type_id": 0
1989
+ }
1990
+ }
1991
+ ],
1992
+ "pair": [
1993
+ {
1994
+ "Sequence": {
1995
+ "id": "A",
1996
+ "type_id": 0
1997
+ }
1998
+ },
1999
+ {
2000
+ "Sequence": {
2001
+ "id": "B",
2002
+ "type_id": 1
2003
+ }
2004
+ }
2005
+ ],
2006
+ "special_tokens": {}
2007
+ },
2008
+ "decoder": {
2009
+ "type": "ByteLevel",
2010
+ "add_prefix_space": true,
2011
+ "trim_offsets": true,
2012
+ "use_regex": true
2013
+ },
2014
+ "model": {
2015
+ "type": "BPE",
2016
+ "dropout": null,
2017
+ "unk_token": null,
2018
+ "continuing_subword_prefix": "",
2019
+ "end_of_word_suffix": "",
2020
+ "fuse_unk": false,
2021
+ "byte_fallback": false,
2022
+ "ignore_merges": false,
2023
+ "vocab": {
2024
+ "!": 0,
2025
+ "\"": 1,
2026
+ "#": 2,
2027
+ "$": 3,
2028
+ "%": 4,
2029
+ "&": 5,
2030
+ "'": 6,
2031
+ "(": 7,
2032
+ ")": 8,
2033
+ "*": 9,
2034
+ "+": 10,
2035
+ ",": 11,
2036
+ "-": 12,
2037
+ ".": 13,
2038
+ "/": 14,
2039
+ "0": 15,
2040
+ "1": 16,
2041
+ "2": 17,
2042
+ "3": 18,
2043
+ "4": 19,
2044
+ "5": 20,
2045
+ "6": 21,
2046
+ "7": 22,
2047
+ "8": 23,
2048
+ "9": 24,
2049
+ ":": 25,
2050
+ ";": 26,
2051
+ "<": 27,
2052
+ "=": 28,
2053
+ ">": 29,
2054
+ "?": 30,
2055
+ "@": 31,
2056
+ "A": 32,
2057
+ "B": 33,
2058
+ "C": 34,
2059
+ "D": 35,
2060
+ "E": 36,
2061
+ "F": 37,
2062
+ "G": 38,
2063
+ "H": 39,
2064
+ "I": 40,
2065
+ "J": 41,
2066
+ "K": 42,
2067
+ "L": 43,
2068
+ "M": 44,
2069
+ "N": 45,
2070
+ "O": 46,
2071
+ "P": 47,
2072
+ "Q": 48,
2073
+ "R": 49,
2074
+ "S": 50,
2075
+ "T": 51,
2076
+ "U": 52,
2077
+ "V": 53,
2078
+ "W": 54,
2079
+ "X": 55,
2080
+ "Y": 56,
2081
+ "Z": 57,
2082
+ "[": 58,
2083
+ "\\": 59,
2084
+ "]": 60,
2085
+ "^": 61,
2086
+ "_": 62,
2087
+ "`": 63,
2088
+ "a": 64,
2089
+ "b": 65,
2090
+ "c": 66,
2091
+ "d": 67,
2092
+ "e": 68,
2093
+ "f": 69,
2094
+ "g": 70,
2095
+ "h": 71,
2096
+ "i": 72,
2097
+ "j": 73,
2098
+ "k": 74,
2099
+ "l": 75,
2100
+ "m": 76,
2101
+ "n": 77,
2102
+ "o": 78,
2103
+ "p": 79,
2104
+ "q": 80,
2105
+ "r": 81,
2106
+ "s": 82,
2107
+ "t": 83,
2108
+ "u": 84,
2109
+ "v": 85,
2110
+ "w": 86,
2111
+ "x": 87,
2112
+ "y": 88,
2113
+ "z": 89,
2114
+ "{": 90,
2115
+ "|": 91,
2116
+ "}": 92,
2117
+ "~": 93,
2118
+ "¡": 94,
2119
+ "¢": 95,
2120
+ "£": 96,
2121
+ "¤": 97,
2122
+ "¥": 98,
2123
+ "¦": 99,
2124
+ "§": 100,
2125
+ "¨": 101,
2126
+ "©": 102,
2127
+ "ª": 103,
2128
+ "«": 104,
2129
+ "¬": 105,
2130
+ "®": 106,
2131
+ "¯": 107,
2132
+ "°": 108,
2133
+ "±": 109,
2134
+ "²": 110,
2135
+ "³": 111,
2136
+ "´": 112,
2137
+ "µ": 113,
2138
+ "¶": 114,
2139
+ "·": 115,
2140
+ "¸": 116,
2141
+ "¹": 117,
2142
+ "º": 118,
2143
+ "»": 119,
2144
+ "¼": 120,
2145
+ "½": 121,
2146
+ "¾": 122,
2147
+ "¿": 123,
2148
+ "À": 124,
2149
+ "Á": 125,
2150
+ "Â": 126,
2151
+ "Ã": 127,
2152
+ "Ä": 128,
2153
+ "Å": 129,
2154
+ "Æ": 130,
2155
+ "Ç": 131,
2156
+ "È": 132,
2157
+ "É": 133,
2158
+ "Ê": 134,
2159
+ "Ë": 135,
2160
+ "Ì": 136,
2161
+ "Í": 137,
2162
+ "Î": 138,
2163
+ "Ï": 139,
2164
+ "Ð": 140,
2165
+ "Ñ": 141,
2166
+ "Ò": 142,
2167
+ "Ó": 143,
2168
+ "Ô": 144,
2169
+ "Õ": 145,
2170
+ "Ö": 146,
2171
+ "×": 147,
2172
+ "Ø": 148,
2173
+ "Ù": 149,
2174
+ "Ú": 150,
2175
+ "Û": 151,
2176
+ "Ü": 152,
2177
+ "Ý": 153,
2178
+ "Þ": 154,
2179
+ "ß": 155,
2180
+ "à": 156,
2181
+ "á": 157,
2182
+ "â": 158,
2183
+ "ã": 159,
2184
+ "ä": 160,
2185
+ "å": 161,
2186
+ "æ": 162,
2187
+ "ç": 163,
2188
+ "è": 164,
2189
+ "é": 165,
2190
+ "ê": 166,
2191
+ "ë": 167,
2192
+ "ì": 168,
2193
+ "í": 169,
2194
+ "î": 170,
2195
+ "ï": 171,
2196
+ "ð": 172,
2197
+ "ñ": 173,
2198
+ "ò": 174,
2199
+ "ó": 175,
2200
+ "ô": 176,
2201
+ "õ": 177,
2202
+ "ö": 178,
2203
+ "÷": 179,
2204
+ "ø": 180,
2205
+ "ù": 181,
2206
+ "ú": 182,
2207
+ "û": 183,
2208
+ "ü": 184,
2209
+ "ý": 185,
2210
+ "þ": 186,
2211
+ "ÿ": 187,
2212
+ "Ā": 188,
2213
+ "ā": 189,
2214
+ "Ă": 190,
2215
+ "ă": 191,
2216
+ "Ą": 192,
2217
+ "ą": 193,
2218
+ "Ć": 194,
2219
+ "ć": 195,
2220
+ "Ĉ": 196,
2221
+ "ĉ": 197,
2222
+ "Ċ": 198,
2223
+ "ċ": 199,
2224
+ "Č": 200,
2225
+ "č": 201,
2226
+ "Ď": 202,
2227
+ "ď": 203,
2228
+ "Đ": 204,
2229
+ "đ": 205,
2230
+ "Ē": 206,
2231
+ "ē": 207,
2232
+ "Ĕ": 208,
2233
+ "ĕ": 209,
2234
+ "Ė": 210,
2235
+ "ė": 211,
2236
+ "Ę": 212,
2237
+ "ę": 213,
2238
+ "Ě": 214,
2239
+ "ě": 215,
2240
+ "Ĝ": 216,
2241
+ "ĝ": 217,
2242
+ "Ğ": 218,
2243
+ "ğ": 219,
2244
+ "Ġ": 220,
2245
+ "ġ": 221,
2246
+ "Ģ": 222,
2247
+ "ģ": 223,
2248
+ "Ĥ": 224,
2249
+ "ĥ": 225,
2250
+ "Ħ": 226,
2251
+ "ħ": 227,
2252
+ "Ĩ": 228,
2253
+ "ĩ": 229,
2254
+ "Ī": 230,
2255
+ "ī": 231,
2256
+ "Ĭ": 232,
2257
+ "ĭ": 233,
2258
+ "Į": 234,
2259
+ "į": 235,
2260
+ "İ": 236,
2261
+ "ı": 237,
2262
+ "IJ": 238,
2263
+ "ij": 239,
2264
+ "Ĵ": 240,
2265
+ "ĵ": 241,
2266
+ "Ķ": 242,
2267
+ "ķ": 243,
2268
+ "ĸ": 244,
2269
+ "Ĺ": 245,
2270
+ "ĺ": 246,
2271
+ "Ļ": 247,
2272
+ "ļ": 248,
2273
+ "Ľ": 249,
2274
+ "ľ": 250,
2275
+ "Ŀ": 251,
2276
+ "ŀ": 252,
2277
+ "Ł": 253,
2278
+ "ł": 254,
2279
+ "Ń": 255,
2280
+ "ĠĠ": 256,
2281
+ "ĠĠĠĠ": 257,
2282
+ "in": 258,
2283
+ "Ġt": 259,
2284
+ "ĠĠĠĠĠĠĠĠ": 260,
2285
+ "er": 261,
2286
+ "ĠĠĠ": 262,
2287
+ "on": 263,
2288
+ "Ġa": 264,
2289
+ "re": 265,
2290
+ "at": 266,
2291
+ "st": 267,
2292
+ "en": 268,
2293
+ "or": 269,
2294
+ "Ġth": 270,
2295
+ "ĊĊ": 271,
2296
+ "Ġc": 272,
2297
+ "le": 273,
2298
+ "Ġs": 274,
2299
+ "it": 275,
2300
+ "an": 276,
2301
+ "ar": 277,
2302
+ "al": 278,
2303
+ "Ġthe": 279,
2304
+ ";Ċ": 280,
2305
+ "Ġp": 281,
2306
+ "Ġf": 282,
2307
+ "ou": 283,
2308
+ "Ġ=": 284,
2309
+ "is": 285,
2310
+ "ĠĠĠĠĠĠĠ": 286,
2311
+ "ing": 287,
2312
+ "es": 288,
2313
+ "Ġw": 289,
2314
+ "ion": 290,
2315
+ "ed": 291,
2316
+ "ic": 292,
2317
+ "Ġb": 293,
2318
+ "Ġd": 294,
2319
+ "et": 295,
2320
+ "Ġm": 296,
2321
+ "Ġo": 297,
2322
+ "ĉĉ": 298,
2323
+ "ro": 299,
2324
+ "as": 300,
2325
+ "el": 301,
2326
+ "ct": 302,
2327
+ "nd": 303,
2328
+ "Ġin": 304,
2329
+ "Ġh": 305,
2330
+ "ent": 306,
2331
+ "id": 307,
2332
+ "Ġn": 308,
2333
+ "am": 309,
2334
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
2335
+ "Ġto": 311,
2336
+ "Ġre": 312,
2337
+ "--": 313,
2338
+ "Ġ{": 314,
2339
+ "Ġof": 315,
2340
+ "om": 316,
2341
+ ");Ċ": 317,
2342
+ "im": 318,
2343
+ "čĊ": 319,
2344
+ "Ġ(": 320,
2345
+ "il": 321,
2346
+ "//": 322,
2347
+ "Ġand": 323,
2348
+ "ur": 324,
2349
+ "se": 325,
2350
+ "Ġl": 326,
2351
+ "ex": 327,
2352
+ "ĠS": 328,
2353
+ "ad": 329,
2354
+ "Ġ\"": 330,
2355
+ "ch": 331,
2356
+ "ut": 332,
2357
+ "if": 333,
2358
+ "**": 334,
2359
+ "Ġ}": 335,
2360
+ "em": 336,
2361
+ "ol": 337,
2362
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
2363
+ "th": 339,
2364
+ ")Ċ": 340,
2365
+ "Ġ{Ċ": 341,
2366
+ "Ġg": 342,
2367
+ "ig": 343,
2368
+ "iv": 344,
2369
+ ",Ċ": 345,
2370
+ "ce": 346,
2371
+ "od": 347,
2372
+ "Ġv": 348,
2373
+ "ate": 349,
2374
+ "ĠT": 350,
2375
+ "ag": 351,
2376
+ "ay": 352,
2377
+ "Ġ*": 353,
2378
+ "ot": 354,
2379
+ "us": 355,
2380
+ "ĠC": 356,
2381
+ "Ġst": 357,
2382
+ "ĠI": 358,
2383
+ "un": 359,
2384
+ "ul": 360,
2385
+ "ue": 361,
2386
+ "ĠA": 362,
2387
+ "ow": 363,
2388
+ "Ġ'": 364,
2389
+ "ew": 365,
2390
+ "Ġ<": 366,
2391
+ "ation": 367,
2392
+ "()": 368,
2393
+ "Ġfor": 369,
2394
+ "ab": 370,
2395
+ "ort": 371,
2396
+ "um": 372,
2397
+ "ame": 373,
2398
+ "Ġis": 374,
2399
+ "pe": 375,
2400
+ "tr": 376,
2401
+ "ck": 377,
2402
+ "âĢ": 378,
2403
+ "Ġy": 379,
2404
+ "ist": 380,
2405
+ "----": 381,
2406
+ ".ĊĊ": 382,
2407
+ "he": 383,
2408
+ "Ġe": 384,
2409
+ "lo": 385,
2410
+ "ĠM": 386,
2411
+ "Ġbe": 387,
2412
+ "ers": 388,
2413
+ "Ġon": 389,
2414
+ "Ġcon": 390,
2415
+ "ap": 391,
2416
+ "ub": 392,
2417
+ "ĠP": 393,
2418
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
2419
+ "ass": 395,
2420
+ "int": 396,
2421
+ ">Ċ": 397,
2422
+ "ly": 398,
2423
+ "urn": 399,
2424
+ "Ġ$": 400,
2425
+ ";ĊĊ": 401,
2426
+ "av": 402,
2427
+ "port": 403,
2428
+ "ir": 404,
2429
+ "->": 405,
2430
+ "nt": 406,
2431
+ "ction": 407,
2432
+ "end": 408,
2433
+ "Ġde": 409,
2434
+ "ith": 410,
2435
+ "out": 411,
2436
+ "turn": 412,
2437
+ "our": 413,
2438
+ "ĠĠĠĠĠ": 414,
2439
+ "lic": 415,
2440
+ "res": 416,
2441
+ "pt": 417,
2442
+ "==": 418,
2443
+ "Ġthis": 419,
2444
+ "Ġwh": 420,
2445
+ "Ġif": 421,
2446
+ "ĠD": 422,
2447
+ "ver": 423,
2448
+ "age": 424,
2449
+ "ĠB": 425,
2450
+ "ht": 426,
2451
+ "ext": 427,
2452
+ "=\"": 428,
2453
+ "Ġthat": 429,
2454
+ "****": 430,
2455
+ "ĠR": 431,
2456
+ "Ġit": 432,
2457
+ "ess": 433,
2458
+ "ĠF": 434,
2459
+ "Ġr": 435,
2460
+ "os": 436,
2461
+ "and": 437,
2462
+ "Ġas": 438,
2463
+ "ect": 439,
2464
+ "ke": 440,
2465
+ "rom": 441,
2466
+ "Ġ//": 442,
2467
+ "con": 443,
2468
+ "ĠL": 444,
2469
+ "(\"": 445,
2470
+ "qu": 446,
2471
+ "lass": 447,
2472
+ "Ġwith": 448,
2473
+ "iz": 449,
2474
+ "de": 450,
2475
+ "ĠN": 451,
2476
+ "Ġal": 452,
2477
+ "op": 453,
2478
+ "up": 454,
2479
+ "get": 455,
2480
+ "Ġ}Ċ": 456,
2481
+ "ile": 457,
2482
+ "Ġan": 458,
2483
+ "ata": 459,
2484
+ "ore": 460,
2485
+ "ri": 461,
2486
+ "Ġpro": 462,
2487
+ ";čĊ": 463,
2488
+ "ĉĉĉĉ": 464,
2489
+ "ter": 465,
2490
+ "ain": 466,
2491
+ "ĠW": 467,
2492
+ "ĠE": 468,
2493
+ "Ġcom": 469,
2494
+ "Ġreturn": 470,
2495
+ "art": 471,
2496
+ "ĠH": 472,
2497
+ "ack": 473,
2498
+ "import": 474,
2499
+ "ublic": 475,
2500
+ "Ġor": 476,
2501
+ "est": 477,
2502
+ "ment": 478,
2503
+ "ĠG": 479,
2504
+ "able": 480,
2505
+ "Ġ-": 481,
2506
+ "ine": 482,
2507
+ "ill": 483,
2508
+ "ind": 484,
2509
+ "ere": 485,
2510
+ "::": 486,
2511
+ "ity": 487,
2512
+ "Ġ+": 488,
2513
+ "Ġtr": 489,
2514
+ "elf": 490,
2515
+ "ight": 491,
2516
+ "('": 492,
2517
+ "orm": 493,
2518
+ "ult": 494,
2519
+ "str": 495,
2520
+ "..": 496,
2521
+ "\",": 497,
2522
+ "Ġyou": 498,
2523
+ "ype": 499
2524
+ },
2525
+ "merges": [
2526
+ [
2527
+ "Ġ",
2528
+ "Ġ"
2529
+ ],
2530
+ [
2531
+ "ĠĠ",
2532
+ "ĠĠ"
2533
+ ],
2534
+ [
2535
+ "i",
2536
+ "n"
2537
+ ],
2538
+ [
2539
+ "Ġ",
2540
+ "t"
2541
+ ],
2542
+ [
2543
+ "ĠĠĠĠ",
2544
+ "ĠĠĠĠ"
2545
+ ],
2546
+ [
2547
+ "e",
2548
+ "r"
2549
+ ],
2550
+ [
2551
+ "ĠĠ",
2552
+ "Ġ"
2553
+ ],
2554
+ [
2555
+ "o",
2556
+ "n"
2557
+ ],
2558
+ [
2559
+ "Ġ",
2560
+ "a"
2561
+ ],
2562
+ [
2563
+ "r",
2564
+ "e"
2565
+ ],
2566
+ [
2567
+ "a",
2568
+ "t"
2569
+ ],
2570
+ [
2571
+ "s",
2572
+ "t"
2573
+ ],
2574
+ [
2575
+ "e",
2576
+ "n"
2577
+ ],
2578
+ [
2579
+ "o",
2580
+ "r"
2581
+ ],
2582
+ [
2583
+ "Ġt",
2584
+ "h"
2585
+ ],
2586
+ [
2587
+ "Ċ",
2588
+ "Ċ"
2589
+ ],
2590
+ [
2591
+ "Ġ",
2592
+ "c"
2593
+ ],
2594
+ [
2595
+ "l",
2596
+ "e"
2597
+ ],
2598
+ [
2599
+ "Ġ",
2600
+ "s"
2601
+ ],
2602
+ [
2603
+ "i",
2604
+ "t"
2605
+ ],
2606
+ [
2607
+ "a",
2608
+ "n"
2609
+ ],
2610
+ [
2611
+ "a",
2612
+ "r"
2613
+ ],
2614
+ [
2615
+ "a",
2616
+ "l"
2617
+ ],
2618
+ [
2619
+ "Ġth",
2620
+ "e"
2621
+ ],
2622
+ [
2623
+ ";",
2624
+ "Ċ"
2625
+ ],
2626
+ [
2627
+ "Ġ",
2628
+ "p"
2629
+ ],
2630
+ [
2631
+ "Ġ",
2632
+ "f"
2633
+ ],
2634
+ [
2635
+ "o",
2636
+ "u"
2637
+ ],
2638
+ [
2639
+ "Ġ",
2640
+ "="
2641
+ ],
2642
+ [
2643
+ "i",
2644
+ "s"
2645
+ ],
2646
+ [
2647
+ "ĠĠĠĠ",
2648
+ "ĠĠĠ"
2649
+ ],
2650
+ [
2651
+ "in",
2652
+ "g"
2653
+ ],
2654
+ [
2655
+ "e",
2656
+ "s"
2657
+ ],
2658
+ [
2659
+ "Ġ",
2660
+ "w"
2661
+ ],
2662
+ [
2663
+ "i",
2664
+ "on"
2665
+ ],
2666
+ [
2667
+ "e",
2668
+ "d"
2669
+ ],
2670
+ [
2671
+ "i",
2672
+ "c"
2673
+ ],
2674
+ [
2675
+ "Ġ",
2676
+ "b"
2677
+ ],
2678
+ [
2679
+ "Ġ",
2680
+ "d"
2681
+ ],
2682
+ [
2683
+ "e",
2684
+ "t"
2685
+ ],
2686
+ [
2687
+ "Ġ",
2688
+ "m"
2689
+ ],
2690
+ [
2691
+ "Ġ",
2692
+ "o"
2693
+ ],
2694
+ [
2695
+ "ĉ",
2696
+ "ĉ"
2697
+ ],
2698
+ [
2699
+ "r",
2700
+ "o"
2701
+ ],
2702
+ [
2703
+ "a",
2704
+ "s"
2705
+ ],
2706
+ [
2707
+ "e",
2708
+ "l"
2709
+ ],
2710
+ [
2711
+ "c",
2712
+ "t"
2713
+ ],
2714
+ [
2715
+ "n",
2716
+ "d"
2717
+ ],
2718
+ [
2719
+ "Ġ",
2720
+ "in"
2721
+ ],
2722
+ [
2723
+ "Ġ",
2724
+ "h"
2725
+ ],
2726
+ [
2727
+ "en",
2728
+ "t"
2729
+ ],
2730
+ [
2731
+ "i",
2732
+ "d"
2733
+ ],
2734
+ [
2735
+ "Ġ",
2736
+ "n"
2737
+ ],
2738
+ [
2739
+ "a",
2740
+ "m"
2741
+ ],
2742
+ [
2743
+ "ĠĠĠĠĠĠĠĠ",
2744
+ "ĠĠĠ"
2745
+ ],
2746
+ [
2747
+ "Ġt",
2748
+ "o"
2749
+ ],
2750
+ [
2751
+ "Ġ",
2752
+ "re"
2753
+ ],
2754
+ [
2755
+ "-",
2756
+ "-"
2757
+ ],
2758
+ [
2759
+ "Ġ",
2760
+ "{"
2761
+ ],
2762
+ [
2763
+ "Ġo",
2764
+ "f"
2765
+ ],
2766
+ [
2767
+ "o",
2768
+ "m"
2769
+ ],
2770
+ [
2771
+ ")",
2772
+ ";Ċ"
2773
+ ],
2774
+ [
2775
+ "i",
2776
+ "m"
2777
+ ],
2778
+ [
2779
+ "č",
2780
+ "Ċ"
2781
+ ],
2782
+ [
2783
+ "Ġ",
2784
+ "("
2785
+ ],
2786
+ [
2787
+ "i",
2788
+ "l"
2789
+ ],
2790
+ [
2791
+ "/",
2792
+ "/"
2793
+ ],
2794
+ [
2795
+ "Ġa",
2796
+ "nd"
2797
+ ],
2798
+ [
2799
+ "u",
2800
+ "r"
2801
+ ],
2802
+ [
2803
+ "s",
2804
+ "e"
2805
+ ],
2806
+ [
2807
+ "Ġ",
2808
+ "l"
2809
+ ],
2810
+ [
2811
+ "e",
2812
+ "x"
2813
+ ],
2814
+ [
2815
+ "Ġ",
2816
+ "S"
2817
+ ],
2818
+ [
2819
+ "a",
2820
+ "d"
2821
+ ],
2822
+ [
2823
+ "Ġ",
2824
+ "\""
2825
+ ],
2826
+ [
2827
+ "c",
2828
+ "h"
2829
+ ],
2830
+ [
2831
+ "u",
2832
+ "t"
2833
+ ],
2834
+ [
2835
+ "i",
2836
+ "f"
2837
+ ],
2838
+ [
2839
+ "*",
2840
+ "*"
2841
+ ],
2842
+ [
2843
+ "Ġ",
2844
+ "}"
2845
+ ],
2846
+ [
2847
+ "e",
2848
+ "m"
2849
+ ],
2850
+ [
2851
+ "o",
2852
+ "l"
2853
+ ],
2854
+ [
2855
+ "ĠĠĠĠĠĠĠĠ",
2856
+ "ĠĠĠĠĠĠĠĠ"
2857
+ ],
2858
+ [
2859
+ "t",
2860
+ "h"
2861
+ ],
2862
+ [
2863
+ ")",
2864
+ "Ċ"
2865
+ ],
2866
+ [
2867
+ "Ġ{",
2868
+ "Ċ"
2869
+ ],
2870
+ [
2871
+ "Ġ",
2872
+ "g"
2873
+ ],
2874
+ [
2875
+ "i",
2876
+ "g"
2877
+ ],
2878
+ [
2879
+ "i",
2880
+ "v"
2881
+ ],
2882
+ [
2883
+ ",",
2884
+ "Ċ"
2885
+ ],
2886
+ [
2887
+ "c",
2888
+ "e"
2889
+ ],
2890
+ [
2891
+ "o",
2892
+ "d"
2893
+ ],
2894
+ [
2895
+ "Ġ",
2896
+ "v"
2897
+ ],
2898
+ [
2899
+ "at",
2900
+ "e"
2901
+ ],
2902
+ [
2903
+ "Ġ",
2904
+ "T"
2905
+ ],
2906
+ [
2907
+ "a",
2908
+ "g"
2909
+ ],
2910
+ [
2911
+ "a",
2912
+ "y"
2913
+ ],
2914
+ [
2915
+ "Ġ",
2916
+ "*"
2917
+ ],
2918
+ [
2919
+ "o",
2920
+ "t"
2921
+ ],
2922
+ [
2923
+ "u",
2924
+ "s"
2925
+ ],
2926
+ [
2927
+ "Ġ",
2928
+ "C"
2929
+ ],
2930
+ [
2931
+ "Ġ",
2932
+ "st"
2933
+ ],
2934
+ [
2935
+ "Ġ",
2936
+ "I"
2937
+ ],
2938
+ [
2939
+ "u",
2940
+ "n"
2941
+ ],
2942
+ [
2943
+ "u",
2944
+ "l"
2945
+ ],
2946
+ [
2947
+ "u",
2948
+ "e"
2949
+ ],
2950
+ [
2951
+ "Ġ",
2952
+ "A"
2953
+ ],
2954
+ [
2955
+ "o",
2956
+ "w"
2957
+ ],
2958
+ [
2959
+ "Ġ",
2960
+ "'"
2961
+ ],
2962
+ [
2963
+ "e",
2964
+ "w"
2965
+ ],
2966
+ [
2967
+ "Ġ",
2968
+ "<"
2969
+ ],
2970
+ [
2971
+ "at",
2972
+ "ion"
2973
+ ],
2974
+ [
2975
+ "(",
2976
+ ")"
2977
+ ],
2978
+ [
2979
+ "Ġf",
2980
+ "or"
2981
+ ],
2982
+ [
2983
+ "a",
2984
+ "b"
2985
+ ],
2986
+ [
2987
+ "or",
2988
+ "t"
2989
+ ],
2990
+ [
2991
+ "u",
2992
+ "m"
2993
+ ],
2994
+ [
2995
+ "am",
2996
+ "e"
2997
+ ],
2998
+ [
2999
+ "Ġ",
3000
+ "is"
3001
+ ],
3002
+ [
3003
+ "p",
3004
+ "e"
3005
+ ],
3006
+ [
3007
+ "t",
3008
+ "r"
3009
+ ],
3010
+ [
3011
+ "c",
3012
+ "k"
3013
+ ],
3014
+ [
3015
+ "â",
3016
+ "Ģ"
3017
+ ],
3018
+ [
3019
+ "Ġ",
3020
+ "y"
3021
+ ],
3022
+ [
3023
+ "i",
3024
+ "st"
3025
+ ],
3026
+ [
3027
+ "--",
3028
+ "--"
3029
+ ],
3030
+ [
3031
+ ".",
3032
+ "ĊĊ"
3033
+ ],
3034
+ [
3035
+ "h",
3036
+ "e"
3037
+ ],
3038
+ [
3039
+ "Ġ",
3040
+ "e"
3041
+ ],
3042
+ [
3043
+ "l",
3044
+ "o"
3045
+ ],
3046
+ [
3047
+ "Ġ",
3048
+ "M"
3049
+ ],
3050
+ [
3051
+ "Ġb",
3052
+ "e"
3053
+ ],
3054
+ [
3055
+ "er",
3056
+ "s"
3057
+ ],
3058
+ [
3059
+ "Ġ",
3060
+ "on"
3061
+ ],
3062
+ [
3063
+ "Ġc",
3064
+ "on"
3065
+ ],
3066
+ [
3067
+ "a",
3068
+ "p"
3069
+ ],
3070
+ [
3071
+ "u",
3072
+ "b"
3073
+ ],
3074
+ [
3075
+ "Ġ",
3076
+ "P"
3077
+ ],
3078
+ [
3079
+ "ĠĠĠĠĠĠĠĠ",
3080
+ "ĠĠĠĠĠĠĠ"
3081
+ ],
3082
+ [
3083
+ "as",
3084
+ "s"
3085
+ ],
3086
+ [
3087
+ "in",
3088
+ "t"
3089
+ ],
3090
+ [
3091
+ ">",
3092
+ "Ċ"
3093
+ ],
3094
+ [
3095
+ "l",
3096
+ "y"
3097
+ ],
3098
+ [
3099
+ "ur",
3100
+ "n"
3101
+ ],
3102
+ [
3103
+ "Ġ",
3104
+ "$"
3105
+ ],
3106
+ [
3107
+ ";",
3108
+ "ĊĊ"
3109
+ ],
3110
+ [
3111
+ "a",
3112
+ "v"
3113
+ ],
3114
+ [
3115
+ "p",
3116
+ "ort"
3117
+ ],
3118
+ [
3119
+ "i",
3120
+ "r"
3121
+ ],
3122
+ [
3123
+ "-",
3124
+ ">"
3125
+ ],
3126
+ [
3127
+ "n",
3128
+ "t"
3129
+ ],
3130
+ [
3131
+ "ct",
3132
+ "ion"
3133
+ ],
3134
+ [
3135
+ "en",
3136
+ "d"
3137
+ ],
3138
+ [
3139
+ "Ġd",
3140
+ "e"
3141
+ ],
3142
+ [
3143
+ "it",
3144
+ "h"
3145
+ ],
3146
+ [
3147
+ "ou",
3148
+ "t"
3149
+ ],
3150
+ [
3151
+ "t",
3152
+ "urn"
3153
+ ],
3154
+ [
3155
+ "ou",
3156
+ "r"
3157
+ ],
3158
+ [
3159
+ "ĠĠĠĠ",
3160
+ "Ġ"
3161
+ ],
3162
+ [
3163
+ "l",
3164
+ "ic"
3165
+ ],
3166
+ [
3167
+ "re",
3168
+ "s"
3169
+ ],
3170
+ [
3171
+ "p",
3172
+ "t"
3173
+ ],
3174
+ [
3175
+ "=",
3176
+ "="
3177
+ ],
3178
+ [
3179
+ "Ġth",
3180
+ "is"
3181
+ ],
3182
+ [
3183
+ "Ġw",
3184
+ "h"
3185
+ ],
3186
+ [
3187
+ "Ġ",
3188
+ "if"
3189
+ ],
3190
+ [
3191
+ "Ġ",
3192
+ "D"
3193
+ ],
3194
+ [
3195
+ "v",
3196
+ "er"
3197
+ ],
3198
+ [
3199
+ "ag",
3200
+ "e"
3201
+ ],
3202
+ [
3203
+ "Ġ",
3204
+ "B"
3205
+ ],
3206
+ [
3207
+ "h",
3208
+ "t"
3209
+ ],
3210
+ [
3211
+ "ex",
3212
+ "t"
3213
+ ],
3214
+ [
3215
+ "=",
3216
+ "\""
3217
+ ],
3218
+ [
3219
+ "Ġth",
3220
+ "at"
3221
+ ],
3222
+ [
3223
+ "**",
3224
+ "**"
3225
+ ],
3226
+ [
3227
+ "Ġ",
3228
+ "R"
3229
+ ],
3230
+ [
3231
+ "Ġ",
3232
+ "it"
3233
+ ],
3234
+ [
3235
+ "es",
3236
+ "s"
3237
+ ],
3238
+ [
3239
+ "Ġ",
3240
+ "F"
3241
+ ],
3242
+ [
3243
+ "Ġ",
3244
+ "r"
3245
+ ],
3246
+ [
3247
+ "o",
3248
+ "s"
3249
+ ],
3250
+ [
3251
+ "an",
3252
+ "d"
3253
+ ],
3254
+ [
3255
+ "Ġa",
3256
+ "s"
3257
+ ],
3258
+ [
3259
+ "e",
3260
+ "ct"
3261
+ ],
3262
+ [
3263
+ "k",
3264
+ "e"
3265
+ ],
3266
+ [
3267
+ "ro",
3268
+ "m"
3269
+ ],
3270
+ [
3271
+ "Ġ",
3272
+ "//"
3273
+ ],
3274
+ [
3275
+ "c",
3276
+ "on"
3277
+ ],
3278
+ [
3279
+ "Ġ",
3280
+ "L"
3281
+ ],
3282
+ [
3283
+ "(",
3284
+ "\""
3285
+ ],
3286
+ [
3287
+ "q",
3288
+ "u"
3289
+ ],
3290
+ [
3291
+ "l",
3292
+ "ass"
3293
+ ],
3294
+ [
3295
+ "Ġw",
3296
+ "ith"
3297
+ ],
3298
+ [
3299
+ "i",
3300
+ "z"
3301
+ ],
3302
+ [
3303
+ "d",
3304
+ "e"
3305
+ ],
3306
+ [
3307
+ "Ġ",
3308
+ "N"
3309
+ ],
3310
+ [
3311
+ "Ġa",
3312
+ "l"
3313
+ ],
3314
+ [
3315
+ "o",
3316
+ "p"
3317
+ ],
3318
+ [
3319
+ "u",
3320
+ "p"
3321
+ ],
3322
+ [
3323
+ "g",
3324
+ "et"
3325
+ ],
3326
+ [
3327
+ "Ġ}",
3328
+ "Ċ"
3329
+ ],
3330
+ [
3331
+ "i",
3332
+ "le"
3333
+ ],
3334
+ [
3335
+ "Ġa",
3336
+ "n"
3337
+ ],
3338
+ [
3339
+ "at",
3340
+ "a"
3341
+ ],
3342
+ [
3343
+ "o",
3344
+ "re"
3345
+ ],
3346
+ [
3347
+ "r",
3348
+ "i"
3349
+ ],
3350
+ [
3351
+ "Ġp",
3352
+ "ro"
3353
+ ],
3354
+ [
3355
+ ";",
3356
+ "čĊ"
3357
+ ],
3358
+ [
3359
+ "ĉĉ",
3360
+ "ĉĉ"
3361
+ ],
3362
+ [
3363
+ "t",
3364
+ "er"
3365
+ ],
3366
+ [
3367
+ "a",
3368
+ "in"
3369
+ ],
3370
+ [
3371
+ "Ġ",
3372
+ "W"
3373
+ ],
3374
+ [
3375
+ "Ġ",
3376
+ "E"
3377
+ ],
3378
+ [
3379
+ "Ġc",
3380
+ "om"
3381
+ ],
3382
+ [
3383
+ "Ġre",
3384
+ "turn"
3385
+ ],
3386
+ [
3387
+ "ar",
3388
+ "t"
3389
+ ],
3390
+ [
3391
+ "Ġ",
3392
+ "H"
3393
+ ],
3394
+ [
3395
+ "a",
3396
+ "ck"
3397
+ ],
3398
+ [
3399
+ "im",
3400
+ "port"
3401
+ ],
3402
+ [
3403
+ "ub",
3404
+ "lic"
3405
+ ],
3406
+ [
3407
+ "Ġ",
3408
+ "or"
3409
+ ],
3410
+ [
3411
+ "e",
3412
+ "st"
3413
+ ],
3414
+ [
3415
+ "m",
3416
+ "ent"
3417
+ ],
3418
+ [
3419
+ "Ġ",
3420
+ "G"
3421
+ ],
3422
+ [
3423
+ "ab",
3424
+ "le"
3425
+ ],
3426
+ [
3427
+ "Ġ",
3428
+ "-"
3429
+ ],
3430
+ [
3431
+ "in",
3432
+ "e"
3433
+ ],
3434
+ [
3435
+ "il",
3436
+ "l"
3437
+ ],
3438
+ [
3439
+ "in",
3440
+ "d"
3441
+ ],
3442
+ [
3443
+ "er",
3444
+ "e"
3445
+ ],
3446
+ [
3447
+ ":",
3448
+ ":"
3449
+ ],
3450
+ [
3451
+ "it",
3452
+ "y"
3453
+ ],
3454
+ [
3455
+ "Ġ",
3456
+ "+"
3457
+ ],
3458
+ [
3459
+ "Ġt",
3460
+ "r"
3461
+ ],
3462
+ [
3463
+ "el",
3464
+ "f"
3465
+ ],
3466
+ [
3467
+ "ig",
3468
+ "ht"
3469
+ ],
3470
+ [
3471
+ "(",
3472
+ "'"
3473
+ ],
3474
+ [
3475
+ "or",
3476
+ "m"
3477
+ ],
3478
+ [
3479
+ "ul",
3480
+ "t"
3481
+ ],
3482
+ [
3483
+ "st",
3484
+ "r"
3485
+ ],
3486
+ [
3487
+ ".",
3488
+ "."
3489
+ ],
3490
+ [
3491
+ "\"",
3492
+ ","
3493
+ ],
3494
+ [
3495
+ "Ġy",
3496
+ "ou"
3497
+ ],
3498
+ [
3499
+ "y",
3500
+ "pe"
3501
+ ]
3502
+ ]
3503
+ }
3504
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,1748 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<|endoftext|>",
8
+ "tokenizer_class": "Qwen2Tokenizer",
9
+ "unk_token": "<|endoftext|>",
10
+ "added_tokens_decoder": {
11
+ "500": {
12
+ "content": "<|endoftext|>",
13
+ "single_word": false,
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "normalized": false,
17
+ "special": true
18
+ },
19
+ "501": {
20
+ "content": "<|im_start|>",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "special": true
26
+ },
27
+ "502": {
28
+ "content": "<|im_end|>",
29
+ "single_word": false,
30
+ "lstrip": false,
31
+ "rstrip": false,
32
+ "normalized": false,
33
+ "special": true
34
+ },
35
+ "503": {
36
+ "content": "<|extra_0|>",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": true,
41
+ "special": false
42
+ },
43
+ "504": {
44
+ "content": "<|extra_1|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": true,
49
+ "special": false
50
+ },
51
+ "505": {
52
+ "content": "<|extra_2|>",
53
+ "single_word": false,
54
+ "lstrip": false,
55
+ "rstrip": false,
56
+ "normalized": true,
57
+ "special": false
58
+ },
59
+ "506": {
60
+ "content": "<|extra_3|>",
61
+ "single_word": false,
62
+ "lstrip": false,
63
+ "rstrip": false,
64
+ "normalized": true,
65
+ "special": false
66
+ },
67
+ "507": {
68
+ "content": "<|extra_4|>",
69
+ "single_word": false,
70
+ "lstrip": false,
71
+ "rstrip": false,
72
+ "normalized": true,
73
+ "special": false
74
+ },
75
+ "508": {
76
+ "content": "<|extra_5|>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": true,
81
+ "special": false
82
+ },
83
+ "509": {
84
+ "content": "<|extra_6|>",
85
+ "single_word": false,
86
+ "lstrip": false,
87
+ "rstrip": false,
88
+ "normalized": true,
89
+ "special": false
90
+ },
91
+ "510": {
92
+ "content": "<|extra_7|>",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": true,
97
+ "special": false
98
+ },
99
+ "511": {
100
+ "content": "<|extra_8|>",
101
+ "single_word": false,
102
+ "lstrip": false,
103
+ "rstrip": false,
104
+ "normalized": true,
105
+ "special": false
106
+ },
107
+ "512": {
108
+ "content": "<|extra_9|>",
109
+ "single_word": false,
110
+ "lstrip": false,
111
+ "rstrip": false,
112
+ "normalized": true,
113
+ "special": false
114
+ },
115
+ "513": {
116
+ "content": "<|extra_10|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ "514": {
124
+ "content": "<|extra_11|>",
125
+ "single_word": false,
126
+ "lstrip": false,
127
+ "rstrip": false,
128
+ "normalized": true,
129
+ "special": false
130
+ },
131
+ "515": {
132
+ "content": "<|extra_12|>",
133
+ "single_word": false,
134
+ "lstrip": false,
135
+ "rstrip": false,
136
+ "normalized": true,
137
+ "special": false
138
+ },
139
+ "516": {
140
+ "content": "<|extra_13|>",
141
+ "single_word": false,
142
+ "lstrip": false,
143
+ "rstrip": false,
144
+ "normalized": true,
145
+ "special": false
146
+ },
147
+ "517": {
148
+ "content": "<|extra_14|>",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": true,
153
+ "special": false
154
+ },
155
+ "518": {
156
+ "content": "<|extra_15|>",
157
+ "single_word": false,
158
+ "lstrip": false,
159
+ "rstrip": false,
160
+ "normalized": true,
161
+ "special": false
162
+ },
163
+ "519": {
164
+ "content": "<|extra_16|>",
165
+ "single_word": false,
166
+ "lstrip": false,
167
+ "rstrip": false,
168
+ "normalized": true,
169
+ "special": false
170
+ },
171
+ "520": {
172
+ "content": "<|extra_17|>",
173
+ "single_word": false,
174
+ "lstrip": false,
175
+ "rstrip": false,
176
+ "normalized": true,
177
+ "special": false
178
+ },
179
+ "521": {
180
+ "content": "<|extra_18|>",
181
+ "single_word": false,
182
+ "lstrip": false,
183
+ "rstrip": false,
184
+ "normalized": true,
185
+ "special": false
186
+ },
187
+ "522": {
188
+ "content": "<|extra_19|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": true,
193
+ "special": false
194
+ },
195
+ "523": {
196
+ "content": "<|extra_20|>",
197
+ "single_word": false,
198
+ "lstrip": false,
199
+ "rstrip": false,
200
+ "normalized": true,
201
+ "special": false
202
+ },
203
+ "524": {
204
+ "content": "<|extra_21|>",
205
+ "single_word": false,
206
+ "lstrip": false,
207
+ "rstrip": false,
208
+ "normalized": true,
209
+ "special": false
210
+ },
211
+ "525": {
212
+ "content": "<|extra_22|>",
213
+ "single_word": false,
214
+ "lstrip": false,
215
+ "rstrip": false,
216
+ "normalized": true,
217
+ "special": false
218
+ },
219
+ "526": {
220
+ "content": "<|extra_23|>",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": true,
225
+ "special": false
226
+ },
227
+ "527": {
228
+ "content": "<|extra_24|>",
229
+ "single_word": false,
230
+ "lstrip": false,
231
+ "rstrip": false,
232
+ "normalized": true,
233
+ "special": false
234
+ },
235
+ "528": {
236
+ "content": "<|extra_25|>",
237
+ "single_word": false,
238
+ "lstrip": false,
239
+ "rstrip": false,
240
+ "normalized": true,
241
+ "special": false
242
+ },
243
+ "529": {
244
+ "content": "<|extra_26|>",
245
+ "single_word": false,
246
+ "lstrip": false,
247
+ "rstrip": false,
248
+ "normalized": true,
249
+ "special": false
250
+ },
251
+ "530": {
252
+ "content": "<|extra_27|>",
253
+ "single_word": false,
254
+ "lstrip": false,
255
+ "rstrip": false,
256
+ "normalized": true,
257
+ "special": false
258
+ },
259
+ "531": {
260
+ "content": "<|extra_28|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": true,
265
+ "special": false
266
+ },
267
+ "532": {
268
+ "content": "<|extra_29|>",
269
+ "single_word": false,
270
+ "lstrip": false,
271
+ "rstrip": false,
272
+ "normalized": true,
273
+ "special": false
274
+ },
275
+ "533": {
276
+ "content": "<|extra_30|>",
277
+ "single_word": false,
278
+ "lstrip": false,
279
+ "rstrip": false,
280
+ "normalized": true,
281
+ "special": false
282
+ },
283
+ "534": {
284
+ "content": "<|extra_31|>",
285
+ "single_word": false,
286
+ "lstrip": false,
287
+ "rstrip": false,
288
+ "normalized": true,
289
+ "special": false
290
+ },
291
+ "535": {
292
+ "content": "<|extra_32|>",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": true,
297
+ "special": false
298
+ },
299
+ "536": {
300
+ "content": "<|extra_33|>",
301
+ "single_word": false,
302
+ "lstrip": false,
303
+ "rstrip": false,
304
+ "normalized": true,
305
+ "special": false
306
+ },
307
+ "537": {
308
+ "content": "<|extra_34|>",
309
+ "single_word": false,
310
+ "lstrip": false,
311
+ "rstrip": false,
312
+ "normalized": true,
313
+ "special": false
314
+ },
315
+ "538": {
316
+ "content": "<|extra_35|>",
317
+ "single_word": false,
318
+ "lstrip": false,
319
+ "rstrip": false,
320
+ "normalized": true,
321
+ "special": false
322
+ },
323
+ "539": {
324
+ "content": "<|extra_36|>",
325
+ "single_word": false,
326
+ "lstrip": false,
327
+ "rstrip": false,
328
+ "normalized": true,
329
+ "special": false
330
+ },
331
+ "540": {
332
+ "content": "<|extra_37|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": true,
337
+ "special": false
338
+ },
339
+ "541": {
340
+ "content": "<|extra_38|>",
341
+ "single_word": false,
342
+ "lstrip": false,
343
+ "rstrip": false,
344
+ "normalized": true,
345
+ "special": false
346
+ },
347
+ "542": {
348
+ "content": "<|extra_39|>",
349
+ "single_word": false,
350
+ "lstrip": false,
351
+ "rstrip": false,
352
+ "normalized": true,
353
+ "special": false
354
+ },
355
+ "543": {
356
+ "content": "<|extra_40|>",
357
+ "single_word": false,
358
+ "lstrip": false,
359
+ "rstrip": false,
360
+ "normalized": true,
361
+ "special": false
362
+ },
363
+ "544": {
364
+ "content": "<|extra_41|>",
365
+ "single_word": false,
366
+ "lstrip": false,
367
+ "rstrip": false,
368
+ "normalized": true,
369
+ "special": false
370
+ },
371
+ "545": {
372
+ "content": "<|extra_42|>",
373
+ "single_word": false,
374
+ "lstrip": false,
375
+ "rstrip": false,
376
+ "normalized": true,
377
+ "special": false
378
+ },
379
+ "546": {
380
+ "content": "<|extra_43|>",
381
+ "single_word": false,
382
+ "lstrip": false,
383
+ "rstrip": false,
384
+ "normalized": true,
385
+ "special": false
386
+ },
387
+ "547": {
388
+ "content": "<|extra_44|>",
389
+ "single_word": false,
390
+ "lstrip": false,
391
+ "rstrip": false,
392
+ "normalized": true,
393
+ "special": false
394
+ },
395
+ "548": {
396
+ "content": "<|extra_45|>",
397
+ "single_word": false,
398
+ "lstrip": false,
399
+ "rstrip": false,
400
+ "normalized": true,
401
+ "special": false
402
+ },
403
+ "549": {
404
+ "content": "<|extra_46|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": true,
409
+ "special": false
410
+ },
411
+ "550": {
412
+ "content": "<|extra_47|>",
413
+ "single_word": false,
414
+ "lstrip": false,
415
+ "rstrip": false,
416
+ "normalized": true,
417
+ "special": false
418
+ },
419
+ "551": {
420
+ "content": "<|extra_48|>",
421
+ "single_word": false,
422
+ "lstrip": false,
423
+ "rstrip": false,
424
+ "normalized": true,
425
+ "special": false
426
+ },
427
+ "552": {
428
+ "content": "<|extra_49|>",
429
+ "single_word": false,
430
+ "lstrip": false,
431
+ "rstrip": false,
432
+ "normalized": true,
433
+ "special": false
434
+ },
435
+ "553": {
436
+ "content": "<|extra_50|>",
437
+ "single_word": false,
438
+ "lstrip": false,
439
+ "rstrip": false,
440
+ "normalized": true,
441
+ "special": false
442
+ },
443
+ "554": {
444
+ "content": "<|extra_51|>",
445
+ "single_word": false,
446
+ "lstrip": false,
447
+ "rstrip": false,
448
+ "normalized": true,
449
+ "special": false
450
+ },
451
+ "555": {
452
+ "content": "<|extra_52|>",
453
+ "single_word": false,
454
+ "lstrip": false,
455
+ "rstrip": false,
456
+ "normalized": true,
457
+ "special": false
458
+ },
459
+ "556": {
460
+ "content": "<|extra_53|>",
461
+ "single_word": false,
462
+ "lstrip": false,
463
+ "rstrip": false,
464
+ "normalized": true,
465
+ "special": false
466
+ },
467
+ "557": {
468
+ "content": "<|extra_54|>",
469
+ "single_word": false,
470
+ "lstrip": false,
471
+ "rstrip": false,
472
+ "normalized": true,
473
+ "special": false
474
+ },
475
+ "558": {
476
+ "content": "<|extra_55|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": true,
481
+ "special": false
482
+ },
483
+ "559": {
484
+ "content": "<|extra_56|>",
485
+ "single_word": false,
486
+ "lstrip": false,
487
+ "rstrip": false,
488
+ "normalized": true,
489
+ "special": false
490
+ },
491
+ "560": {
492
+ "content": "<|extra_57|>",
493
+ "single_word": false,
494
+ "lstrip": false,
495
+ "rstrip": false,
496
+ "normalized": true,
497
+ "special": false
498
+ },
499
+ "561": {
500
+ "content": "<|extra_58|>",
501
+ "single_word": false,
502
+ "lstrip": false,
503
+ "rstrip": false,
504
+ "normalized": true,
505
+ "special": false
506
+ },
507
+ "562": {
508
+ "content": "<|extra_59|>",
509
+ "single_word": false,
510
+ "lstrip": false,
511
+ "rstrip": false,
512
+ "normalized": true,
513
+ "special": false
514
+ },
515
+ "563": {
516
+ "content": "<|extra_60|>",
517
+ "single_word": false,
518
+ "lstrip": false,
519
+ "rstrip": false,
520
+ "normalized": true,
521
+ "special": false
522
+ },
523
+ "564": {
524
+ "content": "<|extra_61|>",
525
+ "single_word": false,
526
+ "lstrip": false,
527
+ "rstrip": false,
528
+ "normalized": true,
529
+ "special": false
530
+ },
531
+ "565": {
532
+ "content": "<|extra_62|>",
533
+ "single_word": false,
534
+ "lstrip": false,
535
+ "rstrip": false,
536
+ "normalized": true,
537
+ "special": false
538
+ },
539
+ "566": {
540
+ "content": "<|extra_63|>",
541
+ "single_word": false,
542
+ "lstrip": false,
543
+ "rstrip": false,
544
+ "normalized": true,
545
+ "special": false
546
+ },
547
+ "567": {
548
+ "content": "<|extra_64|>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": true,
553
+ "special": false
554
+ },
555
+ "568": {
556
+ "content": "<|extra_65|>",
557
+ "single_word": false,
558
+ "lstrip": false,
559
+ "rstrip": false,
560
+ "normalized": true,
561
+ "special": false
562
+ },
563
+ "569": {
564
+ "content": "<|extra_66|>",
565
+ "single_word": false,
566
+ "lstrip": false,
567
+ "rstrip": false,
568
+ "normalized": true,
569
+ "special": false
570
+ },
571
+ "570": {
572
+ "content": "<|extra_67|>",
573
+ "single_word": false,
574
+ "lstrip": false,
575
+ "rstrip": false,
576
+ "normalized": true,
577
+ "special": false
578
+ },
579
+ "571": {
580
+ "content": "<|extra_68|>",
581
+ "single_word": false,
582
+ "lstrip": false,
583
+ "rstrip": false,
584
+ "normalized": true,
585
+ "special": false
586
+ },
587
+ "572": {
588
+ "content": "<|extra_69|>",
589
+ "single_word": false,
590
+ "lstrip": false,
591
+ "rstrip": false,
592
+ "normalized": true,
593
+ "special": false
594
+ },
595
+ "573": {
596
+ "content": "<|extra_70|>",
597
+ "single_word": false,
598
+ "lstrip": false,
599
+ "rstrip": false,
600
+ "normalized": true,
601
+ "special": false
602
+ },
603
+ "574": {
604
+ "content": "<|extra_71|>",
605
+ "single_word": false,
606
+ "lstrip": false,
607
+ "rstrip": false,
608
+ "normalized": true,
609
+ "special": false
610
+ },
611
+ "575": {
612
+ "content": "<|extra_72|>",
613
+ "single_word": false,
614
+ "lstrip": false,
615
+ "rstrip": false,
616
+ "normalized": true,
617
+ "special": false
618
+ },
619
+ "576": {
620
+ "content": "<|extra_73|>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": true,
625
+ "special": false
626
+ },
627
+ "577": {
628
+ "content": "<|extra_74|>",
629
+ "single_word": false,
630
+ "lstrip": false,
631
+ "rstrip": false,
632
+ "normalized": true,
633
+ "special": false
634
+ },
635
+ "578": {
636
+ "content": "<|extra_75|>",
637
+ "single_word": false,
638
+ "lstrip": false,
639
+ "rstrip": false,
640
+ "normalized": true,
641
+ "special": false
642
+ },
643
+ "579": {
644
+ "content": "<|extra_76|>",
645
+ "single_word": false,
646
+ "lstrip": false,
647
+ "rstrip": false,
648
+ "normalized": true,
649
+ "special": false
650
+ },
651
+ "580": {
652
+ "content": "<|extra_77|>",
653
+ "single_word": false,
654
+ "lstrip": false,
655
+ "rstrip": false,
656
+ "normalized": true,
657
+ "special": false
658
+ },
659
+ "581": {
660
+ "content": "<|extra_78|>",
661
+ "single_word": false,
662
+ "lstrip": false,
663
+ "rstrip": false,
664
+ "normalized": true,
665
+ "special": false
666
+ },
667
+ "582": {
668
+ "content": "<|extra_79|>",
669
+ "single_word": false,
670
+ "lstrip": false,
671
+ "rstrip": false,
672
+ "normalized": true,
673
+ "special": false
674
+ },
675
+ "583": {
676
+ "content": "<|extra_80|>",
677
+ "single_word": false,
678
+ "lstrip": false,
679
+ "rstrip": false,
680
+ "normalized": true,
681
+ "special": false
682
+ },
683
+ "584": {
684
+ "content": "<|extra_81|>",
685
+ "single_word": false,
686
+ "lstrip": false,
687
+ "rstrip": false,
688
+ "normalized": true,
689
+ "special": false
690
+ },
691
+ "585": {
692
+ "content": "<|extra_82|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": true,
697
+ "special": false
698
+ },
699
+ "586": {
700
+ "content": "<|extra_83|>",
701
+ "single_word": false,
702
+ "lstrip": false,
703
+ "rstrip": false,
704
+ "normalized": true,
705
+ "special": false
706
+ },
707
+ "587": {
708
+ "content": "<|extra_84|>",
709
+ "single_word": false,
710
+ "lstrip": false,
711
+ "rstrip": false,
712
+ "normalized": true,
713
+ "special": false
714
+ },
715
+ "588": {
716
+ "content": "<|extra_85|>",
717
+ "single_word": false,
718
+ "lstrip": false,
719
+ "rstrip": false,
720
+ "normalized": true,
721
+ "special": false
722
+ },
723
+ "589": {
724
+ "content": "<|extra_86|>",
725
+ "single_word": false,
726
+ "lstrip": false,
727
+ "rstrip": false,
728
+ "normalized": true,
729
+ "special": false
730
+ },
731
+ "590": {
732
+ "content": "<|extra_87|>",
733
+ "single_word": false,
734
+ "lstrip": false,
735
+ "rstrip": false,
736
+ "normalized": true,
737
+ "special": false
738
+ },
739
+ "591": {
740
+ "content": "<|extra_88|>",
741
+ "single_word": false,
742
+ "lstrip": false,
743
+ "rstrip": false,
744
+ "normalized": true,
745
+ "special": false
746
+ },
747
+ "592": {
748
+ "content": "<|extra_89|>",
749
+ "single_word": false,
750
+ "lstrip": false,
751
+ "rstrip": false,
752
+ "normalized": true,
753
+ "special": false
754
+ },
755
+ "593": {
756
+ "content": "<|extra_90|>",
757
+ "single_word": false,
758
+ "lstrip": false,
759
+ "rstrip": false,
760
+ "normalized": true,
761
+ "special": false
762
+ },
763
+ "594": {
764
+ "content": "<|extra_91|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": true,
769
+ "special": false
770
+ },
771
+ "595": {
772
+ "content": "<|extra_92|>",
773
+ "single_word": false,
774
+ "lstrip": false,
775
+ "rstrip": false,
776
+ "normalized": true,
777
+ "special": false
778
+ },
779
+ "596": {
780
+ "content": "<|extra_93|>",
781
+ "single_word": false,
782
+ "lstrip": false,
783
+ "rstrip": false,
784
+ "normalized": true,
785
+ "special": false
786
+ },
787
+ "597": {
788
+ "content": "<|extra_94|>",
789
+ "single_word": false,
790
+ "lstrip": false,
791
+ "rstrip": false,
792
+ "normalized": true,
793
+ "special": false
794
+ },
795
+ "598": {
796
+ "content": "<|extra_95|>",
797
+ "single_word": false,
798
+ "lstrip": false,
799
+ "rstrip": false,
800
+ "normalized": true,
801
+ "special": false
802
+ },
803
+ "599": {
804
+ "content": "<|extra_96|>",
805
+ "single_word": false,
806
+ "lstrip": false,
807
+ "rstrip": false,
808
+ "normalized": true,
809
+ "special": false
810
+ },
811
+ "600": {
812
+ "content": "<|extra_97|>",
813
+ "single_word": false,
814
+ "lstrip": false,
815
+ "rstrip": false,
816
+ "normalized": true,
817
+ "special": false
818
+ },
819
+ "601": {
820
+ "content": "<|extra_98|>",
821
+ "single_word": false,
822
+ "lstrip": false,
823
+ "rstrip": false,
824
+ "normalized": true,
825
+ "special": false
826
+ },
827
+ "602": {
828
+ "content": "<|extra_99|>",
829
+ "single_word": false,
830
+ "lstrip": false,
831
+ "rstrip": false,
832
+ "normalized": true,
833
+ "special": false
834
+ },
835
+ "603": {
836
+ "content": "<|extra_100|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": true,
841
+ "special": false
842
+ },
843
+ "604": {
844
+ "content": "<|extra_101|>",
845
+ "single_word": false,
846
+ "lstrip": false,
847
+ "rstrip": false,
848
+ "normalized": true,
849
+ "special": false
850
+ },
851
+ "605": {
852
+ "content": "<|extra_102|>",
853
+ "single_word": false,
854
+ "lstrip": false,
855
+ "rstrip": false,
856
+ "normalized": true,
857
+ "special": false
858
+ },
859
+ "606": {
860
+ "content": "<|extra_103|>",
861
+ "single_word": false,
862
+ "lstrip": false,
863
+ "rstrip": false,
864
+ "normalized": true,
865
+ "special": false
866
+ },
867
+ "607": {
868
+ "content": "<|extra_104|>",
869
+ "single_word": false,
870
+ "lstrip": false,
871
+ "rstrip": false,
872
+ "normalized": true,
873
+ "special": false
874
+ },
875
+ "608": {
876
+ "content": "<|extra_105|>",
877
+ "single_word": false,
878
+ "lstrip": false,
879
+ "rstrip": false,
880
+ "normalized": true,
881
+ "special": false
882
+ },
883
+ "609": {
884
+ "content": "<|extra_106|>",
885
+ "single_word": false,
886
+ "lstrip": false,
887
+ "rstrip": false,
888
+ "normalized": true,
889
+ "special": false
890
+ },
891
+ "610": {
892
+ "content": "<|extra_107|>",
893
+ "single_word": false,
894
+ "lstrip": false,
895
+ "rstrip": false,
896
+ "normalized": true,
897
+ "special": false
898
+ },
899
+ "611": {
900
+ "content": "<|extra_108|>",
901
+ "single_word": false,
902
+ "lstrip": false,
903
+ "rstrip": false,
904
+ "normalized": true,
905
+ "special": false
906
+ },
907
+ "612": {
908
+ "content": "<|extra_109|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": true,
913
+ "special": false
914
+ },
915
+ "613": {
916
+ "content": "<|extra_110|>",
917
+ "single_word": false,
918
+ "lstrip": false,
919
+ "rstrip": false,
920
+ "normalized": true,
921
+ "special": false
922
+ },
923
+ "614": {
924
+ "content": "<|extra_111|>",
925
+ "single_word": false,
926
+ "lstrip": false,
927
+ "rstrip": false,
928
+ "normalized": true,
929
+ "special": false
930
+ },
931
+ "615": {
932
+ "content": "<|extra_112|>",
933
+ "single_word": false,
934
+ "lstrip": false,
935
+ "rstrip": false,
936
+ "normalized": true,
937
+ "special": false
938
+ },
939
+ "616": {
940
+ "content": "<|extra_113|>",
941
+ "single_word": false,
942
+ "lstrip": false,
943
+ "rstrip": false,
944
+ "normalized": true,
945
+ "special": false
946
+ },
947
+ "617": {
948
+ "content": "<|extra_114|>",
949
+ "single_word": false,
950
+ "lstrip": false,
951
+ "rstrip": false,
952
+ "normalized": true,
953
+ "special": false
954
+ },
955
+ "618": {
956
+ "content": "<|extra_115|>",
957
+ "single_word": false,
958
+ "lstrip": false,
959
+ "rstrip": false,
960
+ "normalized": true,
961
+ "special": false
962
+ },
963
+ "619": {
964
+ "content": "<|extra_116|>",
965
+ "single_word": false,
966
+ "lstrip": false,
967
+ "rstrip": false,
968
+ "normalized": true,
969
+ "special": false
970
+ },
971
+ "620": {
972
+ "content": "<|extra_117|>",
973
+ "single_word": false,
974
+ "lstrip": false,
975
+ "rstrip": false,
976
+ "normalized": true,
977
+ "special": false
978
+ },
979
+ "621": {
980
+ "content": "<|extra_118|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": true,
985
+ "special": false
986
+ },
987
+ "622": {
988
+ "content": "<|extra_119|>",
989
+ "single_word": false,
990
+ "lstrip": false,
991
+ "rstrip": false,
992
+ "normalized": true,
993
+ "special": false
994
+ },
995
+ "623": {
996
+ "content": "<|extra_120|>",
997
+ "single_word": false,
998
+ "lstrip": false,
999
+ "rstrip": false,
1000
+ "normalized": true,
1001
+ "special": false
1002
+ },
1003
+ "624": {
1004
+ "content": "<|extra_121|>",
1005
+ "single_word": false,
1006
+ "lstrip": false,
1007
+ "rstrip": false,
1008
+ "normalized": true,
1009
+ "special": false
1010
+ },
1011
+ "625": {
1012
+ "content": "<|extra_122|>",
1013
+ "single_word": false,
1014
+ "lstrip": false,
1015
+ "rstrip": false,
1016
+ "normalized": true,
1017
+ "special": false
1018
+ },
1019
+ "626": {
1020
+ "content": "<|extra_123|>",
1021
+ "single_word": false,
1022
+ "lstrip": false,
1023
+ "rstrip": false,
1024
+ "normalized": true,
1025
+ "special": false
1026
+ },
1027
+ "627": {
1028
+ "content": "<|extra_124|>",
1029
+ "single_word": false,
1030
+ "lstrip": false,
1031
+ "rstrip": false,
1032
+ "normalized": true,
1033
+ "special": false
1034
+ },
1035
+ "628": {
1036
+ "content": "<|extra_125|>",
1037
+ "single_word": false,
1038
+ "lstrip": false,
1039
+ "rstrip": false,
1040
+ "normalized": true,
1041
+ "special": false
1042
+ },
1043
+ "629": {
1044
+ "content": "<|extra_126|>",
1045
+ "single_word": false,
1046
+ "lstrip": false,
1047
+ "rstrip": false,
1048
+ "normalized": true,
1049
+ "special": false
1050
+ },
1051
+ "630": {
1052
+ "content": "<|extra_127|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": true,
1057
+ "special": false
1058
+ },
1059
+ "631": {
1060
+ "content": "<|extra_128|>",
1061
+ "single_word": false,
1062
+ "lstrip": false,
1063
+ "rstrip": false,
1064
+ "normalized": true,
1065
+ "special": false
1066
+ },
1067
+ "632": {
1068
+ "content": "<|extra_129|>",
1069
+ "single_word": false,
1070
+ "lstrip": false,
1071
+ "rstrip": false,
1072
+ "normalized": true,
1073
+ "special": false
1074
+ },
1075
+ "633": {
1076
+ "content": "<|extra_130|>",
1077
+ "single_word": false,
1078
+ "lstrip": false,
1079
+ "rstrip": false,
1080
+ "normalized": true,
1081
+ "special": false
1082
+ },
1083
+ "634": {
1084
+ "content": "<|extra_131|>",
1085
+ "single_word": false,
1086
+ "lstrip": false,
1087
+ "rstrip": false,
1088
+ "normalized": true,
1089
+ "special": false
1090
+ },
1091
+ "635": {
1092
+ "content": "<|extra_132|>",
1093
+ "single_word": false,
1094
+ "lstrip": false,
1095
+ "rstrip": false,
1096
+ "normalized": true,
1097
+ "special": false
1098
+ },
1099
+ "636": {
1100
+ "content": "<|extra_133|>",
1101
+ "single_word": false,
1102
+ "lstrip": false,
1103
+ "rstrip": false,
1104
+ "normalized": true,
1105
+ "special": false
1106
+ },
1107
+ "637": {
1108
+ "content": "<|extra_134|>",
1109
+ "single_word": false,
1110
+ "lstrip": false,
1111
+ "rstrip": false,
1112
+ "normalized": true,
1113
+ "special": false
1114
+ },
1115
+ "638": {
1116
+ "content": "<|extra_135|>",
1117
+ "single_word": false,
1118
+ "lstrip": false,
1119
+ "rstrip": false,
1120
+ "normalized": true,
1121
+ "special": false
1122
+ },
1123
+ "639": {
1124
+ "content": "<|extra_136|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": true,
1129
+ "special": false
1130
+ },
1131
+ "640": {
1132
+ "content": "<|extra_137|>",
1133
+ "single_word": false,
1134
+ "lstrip": false,
1135
+ "rstrip": false,
1136
+ "normalized": true,
1137
+ "special": false
1138
+ },
1139
+ "641": {
1140
+ "content": "<|extra_138|>",
1141
+ "single_word": false,
1142
+ "lstrip": false,
1143
+ "rstrip": false,
1144
+ "normalized": true,
1145
+ "special": false
1146
+ },
1147
+ "642": {
1148
+ "content": "<|extra_139|>",
1149
+ "single_word": false,
1150
+ "lstrip": false,
1151
+ "rstrip": false,
1152
+ "normalized": true,
1153
+ "special": false
1154
+ },
1155
+ "643": {
1156
+ "content": "<|extra_140|>",
1157
+ "single_word": false,
1158
+ "lstrip": false,
1159
+ "rstrip": false,
1160
+ "normalized": true,
1161
+ "special": false
1162
+ },
1163
+ "644": {
1164
+ "content": "<|extra_141|>",
1165
+ "single_word": false,
1166
+ "lstrip": false,
1167
+ "rstrip": false,
1168
+ "normalized": true,
1169
+ "special": false
1170
+ },
1171
+ "645": {
1172
+ "content": "<|extra_142|>",
1173
+ "single_word": false,
1174
+ "lstrip": false,
1175
+ "rstrip": false,
1176
+ "normalized": true,
1177
+ "special": false
1178
+ },
1179
+ "646": {
1180
+ "content": "<|extra_143|>",
1181
+ "single_word": false,
1182
+ "lstrip": false,
1183
+ "rstrip": false,
1184
+ "normalized": true,
1185
+ "special": false
1186
+ },
1187
+ "647": {
1188
+ "content": "<|extra_144|>",
1189
+ "single_word": false,
1190
+ "lstrip": false,
1191
+ "rstrip": false,
1192
+ "normalized": true,
1193
+ "special": false
1194
+ },
1195
+ "648": {
1196
+ "content": "<|extra_145|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": true,
1201
+ "special": false
1202
+ },
1203
+ "649": {
1204
+ "content": "<|extra_146|>",
1205
+ "single_word": false,
1206
+ "lstrip": false,
1207
+ "rstrip": false,
1208
+ "normalized": true,
1209
+ "special": false
1210
+ },
1211
+ "650": {
1212
+ "content": "<|extra_147|>",
1213
+ "single_word": false,
1214
+ "lstrip": false,
1215
+ "rstrip": false,
1216
+ "normalized": true,
1217
+ "special": false
1218
+ },
1219
+ "651": {
1220
+ "content": "<|extra_148|>",
1221
+ "single_word": false,
1222
+ "lstrip": false,
1223
+ "rstrip": false,
1224
+ "normalized": true,
1225
+ "special": false
1226
+ },
1227
+ "652": {
1228
+ "content": "<|extra_149|>",
1229
+ "single_word": false,
1230
+ "lstrip": false,
1231
+ "rstrip": false,
1232
+ "normalized": true,
1233
+ "special": false
1234
+ },
1235
+ "653": {
1236
+ "content": "<|extra_150|>",
1237
+ "single_word": false,
1238
+ "lstrip": false,
1239
+ "rstrip": false,
1240
+ "normalized": true,
1241
+ "special": false
1242
+ },
1243
+ "654": {
1244
+ "content": "<|extra_151|>",
1245
+ "single_word": false,
1246
+ "lstrip": false,
1247
+ "rstrip": false,
1248
+ "normalized": true,
1249
+ "special": false
1250
+ },
1251
+ "655": {
1252
+ "content": "<|extra_152|>",
1253
+ "single_word": false,
1254
+ "lstrip": false,
1255
+ "rstrip": false,
1256
+ "normalized": true,
1257
+ "special": false
1258
+ },
1259
+ "656": {
1260
+ "content": "<|extra_153|>",
1261
+ "single_word": false,
1262
+ "lstrip": false,
1263
+ "rstrip": false,
1264
+ "normalized": true,
1265
+ "special": false
1266
+ },
1267
+ "657": {
1268
+ "content": "<|extra_154|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": true,
1273
+ "special": false
1274
+ },
1275
+ "658": {
1276
+ "content": "<|extra_155|>",
1277
+ "single_word": false,
1278
+ "lstrip": false,
1279
+ "rstrip": false,
1280
+ "normalized": true,
1281
+ "special": false
1282
+ },
1283
+ "659": {
1284
+ "content": "<|extra_156|>",
1285
+ "single_word": false,
1286
+ "lstrip": false,
1287
+ "rstrip": false,
1288
+ "normalized": true,
1289
+ "special": false
1290
+ },
1291
+ "660": {
1292
+ "content": "<|extra_157|>",
1293
+ "single_word": false,
1294
+ "lstrip": false,
1295
+ "rstrip": false,
1296
+ "normalized": true,
1297
+ "special": false
1298
+ },
1299
+ "661": {
1300
+ "content": "<|extra_158|>",
1301
+ "single_word": false,
1302
+ "lstrip": false,
1303
+ "rstrip": false,
1304
+ "normalized": true,
1305
+ "special": false
1306
+ },
1307
+ "662": {
1308
+ "content": "<|extra_159|>",
1309
+ "single_word": false,
1310
+ "lstrip": false,
1311
+ "rstrip": false,
1312
+ "normalized": true,
1313
+ "special": false
1314
+ },
1315
+ "663": {
1316
+ "content": "<|extra_160|>",
1317
+ "single_word": false,
1318
+ "lstrip": false,
1319
+ "rstrip": false,
1320
+ "normalized": true,
1321
+ "special": false
1322
+ },
1323
+ "664": {
1324
+ "content": "<|extra_161|>",
1325
+ "single_word": false,
1326
+ "lstrip": false,
1327
+ "rstrip": false,
1328
+ "normalized": true,
1329
+ "special": false
1330
+ },
1331
+ "665": {
1332
+ "content": "<|extra_162|>",
1333
+ "single_word": false,
1334
+ "lstrip": false,
1335
+ "rstrip": false,
1336
+ "normalized": true,
1337
+ "special": false
1338
+ },
1339
+ "666": {
1340
+ "content": "<|extra_163|>",
1341
+ "single_word": false,
1342
+ "lstrip": false,
1343
+ "rstrip": false,
1344
+ "normalized": true,
1345
+ "special": false
1346
+ },
1347
+ "667": {
1348
+ "content": "<|extra_164|>",
1349
+ "single_word": false,
1350
+ "lstrip": false,
1351
+ "rstrip": false,
1352
+ "normalized": true,
1353
+ "special": false
1354
+ },
1355
+ "668": {
1356
+ "content": "<|extra_165|>",
1357
+ "single_word": false,
1358
+ "lstrip": false,
1359
+ "rstrip": false,
1360
+ "normalized": true,
1361
+ "special": false
1362
+ },
1363
+ "669": {
1364
+ "content": "<|extra_166|>",
1365
+ "single_word": false,
1366
+ "lstrip": false,
1367
+ "rstrip": false,
1368
+ "normalized": true,
1369
+ "special": false
1370
+ },
1371
+ "670": {
1372
+ "content": "<|extra_167|>",
1373
+ "single_word": false,
1374
+ "lstrip": false,
1375
+ "rstrip": false,
1376
+ "normalized": true,
1377
+ "special": false
1378
+ },
1379
+ "671": {
1380
+ "content": "<|extra_168|>",
1381
+ "single_word": false,
1382
+ "lstrip": false,
1383
+ "rstrip": false,
1384
+ "normalized": true,
1385
+ "special": false
1386
+ },
1387
+ "672": {
1388
+ "content": "<|extra_169|>",
1389
+ "single_word": false,
1390
+ "lstrip": false,
1391
+ "rstrip": false,
1392
+ "normalized": true,
1393
+ "special": false
1394
+ },
1395
+ "673": {
1396
+ "content": "<|extra_170|>",
1397
+ "single_word": false,
1398
+ "lstrip": false,
1399
+ "rstrip": false,
1400
+ "normalized": true,
1401
+ "special": false
1402
+ },
1403
+ "674": {
1404
+ "content": "<|extra_171|>",
1405
+ "single_word": false,
1406
+ "lstrip": false,
1407
+ "rstrip": false,
1408
+ "normalized": true,
1409
+ "special": false
1410
+ },
1411
+ "675": {
1412
+ "content": "<|extra_172|>",
1413
+ "single_word": false,
1414
+ "lstrip": false,
1415
+ "rstrip": false,
1416
+ "normalized": true,
1417
+ "special": false
1418
+ },
1419
+ "676": {
1420
+ "content": "<|extra_173|>",
1421
+ "single_word": false,
1422
+ "lstrip": false,
1423
+ "rstrip": false,
1424
+ "normalized": true,
1425
+ "special": false
1426
+ },
1427
+ "677": {
1428
+ "content": "<|extra_174|>",
1429
+ "single_word": false,
1430
+ "lstrip": false,
1431
+ "rstrip": false,
1432
+ "normalized": true,
1433
+ "special": false
1434
+ },
1435
+ "678": {
1436
+ "content": "<|extra_175|>",
1437
+ "single_word": false,
1438
+ "lstrip": false,
1439
+ "rstrip": false,
1440
+ "normalized": true,
1441
+ "special": false
1442
+ },
1443
+ "679": {
1444
+ "content": "<|extra_176|>",
1445
+ "single_word": false,
1446
+ "lstrip": false,
1447
+ "rstrip": false,
1448
+ "normalized": true,
1449
+ "special": false
1450
+ },
1451
+ "680": {
1452
+ "content": "<|extra_177|>",
1453
+ "single_word": false,
1454
+ "lstrip": false,
1455
+ "rstrip": false,
1456
+ "normalized": true,
1457
+ "special": false
1458
+ },
1459
+ "681": {
1460
+ "content": "<|extra_178|>",
1461
+ "single_word": false,
1462
+ "lstrip": false,
1463
+ "rstrip": false,
1464
+ "normalized": true,
1465
+ "special": false
1466
+ },
1467
+ "682": {
1468
+ "content": "<|extra_179|>",
1469
+ "single_word": false,
1470
+ "lstrip": false,
1471
+ "rstrip": false,
1472
+ "normalized": true,
1473
+ "special": false
1474
+ },
1475
+ "683": {
1476
+ "content": "<|extra_180|>",
1477
+ "single_word": false,
1478
+ "lstrip": false,
1479
+ "rstrip": false,
1480
+ "normalized": true,
1481
+ "special": false
1482
+ },
1483
+ "684": {
1484
+ "content": "<|extra_181|>",
1485
+ "single_word": false,
1486
+ "lstrip": false,
1487
+ "rstrip": false,
1488
+ "normalized": true,
1489
+ "special": false
1490
+ },
1491
+ "685": {
1492
+ "content": "<|extra_182|>",
1493
+ "single_word": false,
1494
+ "lstrip": false,
1495
+ "rstrip": false,
1496
+ "normalized": true,
1497
+ "special": false
1498
+ },
1499
+ "686": {
1500
+ "content": "<|extra_183|>",
1501
+ "single_word": false,
1502
+ "lstrip": false,
1503
+ "rstrip": false,
1504
+ "normalized": true,
1505
+ "special": false
1506
+ },
1507
+ "687": {
1508
+ "content": "<|extra_184|>",
1509
+ "single_word": false,
1510
+ "lstrip": false,
1511
+ "rstrip": false,
1512
+ "normalized": true,
1513
+ "special": false
1514
+ },
1515
+ "688": {
1516
+ "content": "<|extra_185|>",
1517
+ "single_word": false,
1518
+ "lstrip": false,
1519
+ "rstrip": false,
1520
+ "normalized": true,
1521
+ "special": false
1522
+ },
1523
+ "689": {
1524
+ "content": "<|extra_186|>",
1525
+ "single_word": false,
1526
+ "lstrip": false,
1527
+ "rstrip": false,
1528
+ "normalized": true,
1529
+ "special": false
1530
+ },
1531
+ "690": {
1532
+ "content": "<|extra_187|>",
1533
+ "single_word": false,
1534
+ "lstrip": false,
1535
+ "rstrip": false,
1536
+ "normalized": true,
1537
+ "special": false
1538
+ },
1539
+ "691": {
1540
+ "content": "<|extra_188|>",
1541
+ "single_word": false,
1542
+ "lstrip": false,
1543
+ "rstrip": false,
1544
+ "normalized": true,
1545
+ "special": false
1546
+ },
1547
+ "692": {
1548
+ "content": "<|extra_189|>",
1549
+ "single_word": false,
1550
+ "lstrip": false,
1551
+ "rstrip": false,
1552
+ "normalized": true,
1553
+ "special": false
1554
+ },
1555
+ "693": {
1556
+ "content": "<|extra_190|>",
1557
+ "single_word": false,
1558
+ "lstrip": false,
1559
+ "rstrip": false,
1560
+ "normalized": true,
1561
+ "special": false
1562
+ },
1563
+ "694": {
1564
+ "content": "<|extra_191|>",
1565
+ "single_word": false,
1566
+ "lstrip": false,
1567
+ "rstrip": false,
1568
+ "normalized": true,
1569
+ "special": false
1570
+ },
1571
+ "695": {
1572
+ "content": "<|extra_192|>",
1573
+ "single_word": false,
1574
+ "lstrip": false,
1575
+ "rstrip": false,
1576
+ "normalized": true,
1577
+ "special": false
1578
+ },
1579
+ "696": {
1580
+ "content": "<|extra_193|>",
1581
+ "single_word": false,
1582
+ "lstrip": false,
1583
+ "rstrip": false,
1584
+ "normalized": true,
1585
+ "special": false
1586
+ },
1587
+ "697": {
1588
+ "content": "<|extra_194|>",
1589
+ "single_word": false,
1590
+ "lstrip": false,
1591
+ "rstrip": false,
1592
+ "normalized": true,
1593
+ "special": false
1594
+ },
1595
+ "698": {
1596
+ "content": "<|extra_195|>",
1597
+ "single_word": false,
1598
+ "lstrip": false,
1599
+ "rstrip": false,
1600
+ "normalized": true,
1601
+ "special": false
1602
+ },
1603
+ "699": {
1604
+ "content": "<|extra_196|>",
1605
+ "single_word": false,
1606
+ "lstrip": false,
1607
+ "rstrip": false,
1608
+ "normalized": true,
1609
+ "special": false
1610
+ },
1611
+ "700": {
1612
+ "content": "<|extra_197|>",
1613
+ "single_word": false,
1614
+ "lstrip": false,
1615
+ "rstrip": false,
1616
+ "normalized": true,
1617
+ "special": false
1618
+ },
1619
+ "701": {
1620
+ "content": "<|extra_198|>",
1621
+ "single_word": false,
1622
+ "lstrip": false,
1623
+ "rstrip": false,
1624
+ "normalized": true,
1625
+ "special": false
1626
+ },
1627
+ "702": {
1628
+ "content": "<|extra_199|>",
1629
+ "single_word": false,
1630
+ "lstrip": false,
1631
+ "rstrip": false,
1632
+ "normalized": true,
1633
+ "special": false
1634
+ },
1635
+ "703": {
1636
+ "content": "<|extra_200|>",
1637
+ "single_word": false,
1638
+ "lstrip": false,
1639
+ "rstrip": false,
1640
+ "normalized": true,
1641
+ "special": false
1642
+ },
1643
+ "704": {
1644
+ "content": "<|extra_201|>",
1645
+ "single_word": false,
1646
+ "lstrip": false,
1647
+ "rstrip": false,
1648
+ "normalized": true,
1649
+ "special": false
1650
+ },
1651
+ "705": {
1652
+ "content": "<|extra_202|>",
1653
+ "single_word": false,
1654
+ "lstrip": false,
1655
+ "rstrip": false,
1656
+ "normalized": true,
1657
+ "special": false
1658
+ },
1659
+ "706": {
1660
+ "content": "<|extra_203|>",
1661
+ "single_word": false,
1662
+ "lstrip": false,
1663
+ "rstrip": false,
1664
+ "normalized": true,
1665
+ "special": false
1666
+ },
1667
+ "707": {
1668
+ "content": "<|extra_204|>",
1669
+ "single_word": false,
1670
+ "lstrip": false,
1671
+ "rstrip": false,
1672
+ "normalized": true,
1673
+ "special": false
1674
+ },
1675
+ "708": {
1676
+ "content": "<ref>",
1677
+ "single_word": false,
1678
+ "lstrip": false,
1679
+ "rstrip": false,
1680
+ "normalized": false,
1681
+ "special": true
1682
+ },
1683
+ "709": {
1684
+ "content": "</ref>",
1685
+ "single_word": false,
1686
+ "lstrip": false,
1687
+ "rstrip": false,
1688
+ "normalized": false,
1689
+ "special": true
1690
+ },
1691
+ "710": {
1692
+ "content": "<box>",
1693
+ "single_word": false,
1694
+ "lstrip": false,
1695
+ "rstrip": false,
1696
+ "normalized": false,
1697
+ "special": true
1698
+ },
1699
+ "711": {
1700
+ "content": "</box>",
1701
+ "single_word": false,
1702
+ "lstrip": false,
1703
+ "rstrip": false,
1704
+ "normalized": false,
1705
+ "special": true
1706
+ },
1707
+ "712": {
1708
+ "content": "<quad>",
1709
+ "single_word": false,
1710
+ "lstrip": false,
1711
+ "rstrip": false,
1712
+ "normalized": false,
1713
+ "special": true
1714
+ },
1715
+ "713": {
1716
+ "content": "</quad>",
1717
+ "single_word": false,
1718
+ "lstrip": false,
1719
+ "rstrip": false,
1720
+ "normalized": false,
1721
+ "special": true
1722
+ },
1723
+ "714": {
1724
+ "content": "<img>",
1725
+ "single_word": false,
1726
+ "lstrip": false,
1727
+ "rstrip": false,
1728
+ "normalized": false,
1729
+ "special": true
1730
+ },
1731
+ "715": {
1732
+ "content": "</img>",
1733
+ "single_word": false,
1734
+ "lstrip": false,
1735
+ "rstrip": false,
1736
+ "normalized": false,
1737
+ "special": true
1738
+ },
1739
+ "716": {
1740
+ "content": "<imgpad>",
1741
+ "single_word": false,
1742
+ "lstrip": false,
1743
+ "rstrip": false,
1744
+ "normalized": false,
1745
+ "special": true
1746
+ }
1747
+ }
1748
+ }