|
[INFO|configuration_utils.py:675] 2024-10-14 08:50:23,832 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/config.json |
|
|
|
[INFO|configuration_utils.py:742] 2024-10-14 08:50:23,836 >> Model config PaliGemmaConfig { |
|
"_name_or_path": "google/paligemma-3b-pt-448", |
|
"_vocab_size": 257216, |
|
"architectures": [ |
|
"PaliGemmaForConditionalGeneration" |
|
], |
|
"bos_token_id": 2, |
|
"eos_token_id": 1, |
|
"hidden_size": 2048, |
|
"image_token_index": 257152, |
|
"model_type": "paligemma", |
|
"pad_token_id": 0, |
|
"projection_dim": 2048, |
|
"text_config": { |
|
"hidden_size": 2048, |
|
"intermediate_size": 16384, |
|
"model_type": "gemma", |
|
"num_attention_heads": 8, |
|
"num_hidden_layers": 18, |
|
"num_image_tokens": 1024, |
|
"num_key_value_heads": 1, |
|
"torch_dtype": "float32", |
|
"vocab_size": 257216 |
|
}, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.45.2", |
|
"vision_config": { |
|
"hidden_size": 1152, |
|
"image_size": 448, |
|
"intermediate_size": 4304, |
|
"model_type": "siglip_vision_model", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 27, |
|
"num_image_tokens": 1024, |
|
"patch_size": 14, |
|
"projection_dim": 2048, |
|
"projector_hidden_act": "gelu_fast", |
|
"vision_use_head": false |
|
} |
|
} |
|
|
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:27,516 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/tokenizer.model |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:27,516 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/tokenizer.json |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:27,516 >> loading file added_tokens.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/added_tokens.json |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:27,516 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/special_tokens_map.json |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:27,516 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/tokenizer_config.json |
|
|
|
[INFO|image_processing_base.py:375] 2024-10-14 08:50:29,553 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/preprocessor_config.json |
|
|
|
[INFO|image_processing_base.py:375] 2024-10-14 08:50:29,792 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/preprocessor_config.json |
|
|
|
[INFO|image_processing_base.py:429] 2024-10-14 08:50:29,793 >> Image processor SiglipImageProcessor { |
|
"do_convert_rgb": null, |
|
"do_normalize": true, |
|
"do_rescale": true, |
|
"do_resize": true, |
|
"image_mean": [ |
|
0.5, |
|
0.5, |
|
0.5 |
|
], |
|
"image_processor_type": "SiglipImageProcessor", |
|
"image_seq_length": 1024, |
|
"image_std": [ |
|
0.5, |
|
0.5, |
|
0.5 |
|
], |
|
"processor_class": "PaliGemmaProcessor", |
|
"resample": 3, |
|
"rescale_factor": 0.00392156862745098, |
|
"size": { |
|
"height": 448, |
|
"width": 448 |
|
} |
|
} |
|
|
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:30,051 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/tokenizer.model |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:30,051 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/tokenizer.json |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:30,051 >> loading file added_tokens.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/added_tokens.json |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:30,051 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/special_tokens_map.json |
|
|
|
[INFO|tokenization_utils_base.py:2206] 2024-10-14 08:50:30,051 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/tokenizer_config.json |
|
|
|
[INFO|processing_utils.py:744] 2024-10-14 08:50:33,590 >> Processor PaliGemmaProcessor: |
|
- image_processor: SiglipImageProcessor { |
|
"do_convert_rgb": null, |
|
"do_normalize": true, |
|
"do_rescale": true, |
|
"do_resize": true, |
|
"image_mean": [ |
|
0.5, |
|
0.5, |
|
0.5 |
|
], |
|
"image_processor_type": "SiglipImageProcessor", |
|
"image_seq_length": 1024, |
|
"image_std": [ |
|
0.5, |
|
0.5, |
|
0.5 |
|
], |
|
"processor_class": "PaliGemmaProcessor", |
|
"resample": 3, |
|
"rescale_factor": 0.00392156862745098, |
|
"size": { |
|
"height": 448, |
|
"width": 448 |
|
} |
|
} |
|
|
|
- tokenizer: GemmaTokenizerFast(name_or_path='google/paligemma-3b-pt-448', vocab_size=257152, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'bos_token': '<bos>', 'eos_token': '<eos>', 'unk_token': '<unk>', 'pad_token': '<pad>', 'additional_special_tokens': ['<image>']}, clean_up_tokenization_spaces=False), added_tokens_decoder={ |
|
0: AddedToken("<pad>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), |
|
1: AddedToken("<eos>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), |
|
2: AddedToken("<bos>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), |
|
3: AddedToken("<unk>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), |
|
4: AddedToken("<mask>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
5: AddedToken("<2mass>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
6: AddedToken("[@BOS@]", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
7: AddedToken("<unused0>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
8: AddedToken("<unused1>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
9: AddedToken("<unused2>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
10: AddedToken("<unused3>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
11: AddedToken("<unused4>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
12: AddedToken("<unused5>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
13: AddedToken("<unused6>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
14: AddedToken("<unused7>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
15: AddedToken("<unused8>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
16: AddedToken("<unused9>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
17: AddedToken("<unused10>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
18: AddedToken("<unused11>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
19: AddedToken("<unused12>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
20: AddedToken("<unused13>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
21: AddedToken("<unused14>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
22: AddedToken("<unused15>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
23: AddedToken("<unused16>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
24: AddedToken("<unused17>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
25: AddedToken("<unused18>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
26: AddedToken("<unused19>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
27: AddedToken("<unused20>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
28: AddedToken("<unused21>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
29: AddedToken("<unused22>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
30: AddedToken("<unused23>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
31: AddedToken("<unused24>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
32: AddedToken("<unused25>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
33: AddedToken("<unused26>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
34: AddedToken("<unused27>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
35: AddedToken("<unused28>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
36: AddedToken("<unused29>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
37: AddedToken("<unused30>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
38: AddedToken("<unused31>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
39: AddedToken("<unused32>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
40: AddedToken("<unused33>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
41: AddedToken("<unused34>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
42: AddedToken("<unused35>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
43: AddedToken("<unused36>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
44: AddedToken("<unused37>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
45: AddedToken("<unused38>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
46: AddedToken("<unused39>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
47: AddedToken("<unused40>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
48: AddedToken("<unused41>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
49: AddedToken("<unused42>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
50: AddedToken("<unused43>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
51: AddedToken("<unused44>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
52: AddedToken("<unused45>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
53: AddedToken("<unused46>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
54: AddedToken("<unused47>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
55: AddedToken("<unused48>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
56: AddedToken("<unused49>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
57: AddedToken("<unused50>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
58: AddedToken("<unused51>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
59: AddedToken("<unused52>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
60: AddedToken("<unused53>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
61: AddedToken("<unused54>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
62: AddedToken("<unused55>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
63: AddedToken("<unused56>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
64: AddedToken("<unused57>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
65: AddedToken("<unused58>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
66: AddedToken("<unused59>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
67: AddedToken("<unused60>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
68: AddedToken("<unused61>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
69: AddedToken("<unused62>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
70: AddedToken("<unused63>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
71: AddedToken("<unused64>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
72: AddedToken("<unused65>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
73: AddedToken("<unused66>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
74: AddedToken("<unused67>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
75: AddedToken("<unused68>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
76: AddedToken("<unused69>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
77: AddedToken("<unused70>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
78: AddedToken("<unused71>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
79: AddedToken("<unused72>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
80: AddedToken("<unused73>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
81: AddedToken("<unused74>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
82: AddedToken("<unused75>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
83: AddedToken("<unused76>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
84: AddedToken("<unused77>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
85: AddedToken("<unused78>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
86: AddedToken("<unused79>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
87: AddedToken("<unused80>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
88: AddedToken("<unused81>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
89: AddedToken("<unused82>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
90: AddedToken("<unused83>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
91: AddedToken("<unused84>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
92: AddedToken("<unused85>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
93: AddedToken("<unused86>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
94: AddedToken("<unused87>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
95: AddedToken("<unused88>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
96: AddedToken("<unused89>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
97: AddedToken("<unused90>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
98: AddedToken("<unused91>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
99: AddedToken("<unused92>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
100: AddedToken("<unused93>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
101: AddedToken("<unused94>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
102: AddedToken("<unused95>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
103: AddedToken("<unused96>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
104: AddedToken("<unused97>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
105: AddedToken("<unused98>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
106: AddedToken("<start_of_turn>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
107: AddedToken("<end_of_turn>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
108: AddedToken(" |
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
109: AddedToken(" |
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
110: AddedToken(" |
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
111: AddedToken(" |
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
112: AddedToken(" |
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
113: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
114: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
115: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
116: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
117: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
118: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
119: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
120: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
121: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
122: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
123: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
124: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
125: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
126: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
127: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
128: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
129: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
130: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
131: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
132: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
133: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
134: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
135: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
136: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
137: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
138: AddedToken(" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
139: AddedToken("▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
140: AddedToken("▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
141: AddedToken("▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
142: AddedToken("▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
143: AddedToken("▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
144: AddedToken("▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
145: AddedToken("▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
146: AddedToken("▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
147: AddedToken("▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
148: AddedToken("▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
149: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
150: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
151: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
152: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
153: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
154: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
155: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
156: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
157: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
158: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
159: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
160: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
161: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
162: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
163: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
164: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
165: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
166: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
167: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
168: AddedToken("▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
169: AddedToken("<table>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
170: AddedToken("<caption>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
171: AddedToken("<thead>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
172: AddedToken("<tbody>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
173: AddedToken("<tfoot>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
174: AddedToken("<tr>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
175: AddedToken("<th>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
176: AddedToken("<td>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
177: AddedToken("</table>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
178: AddedToken("</caption>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
179: AddedToken("</thead>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
180: AddedToken("</tbody>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
181: AddedToken("</tfoot>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
182: AddedToken("</tr>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
183: AddedToken("</th>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
184: AddedToken("</td>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
185: AddedToken("<h1>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
186: AddedToken("<h2>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
187: AddedToken("<h3>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
188: AddedToken("<h4>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
189: AddedToken("<h5>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
190: AddedToken("<h6>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
191: AddedToken("<blockquote>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
192: AddedToken("</h1>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
193: AddedToken("</h2>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
194: AddedToken("</h3>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
195: AddedToken("</h4>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
196: AddedToken("</h5>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
197: AddedToken("</h6>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
198: AddedToken("</blockquote>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
199: AddedToken("<strong>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
200: AddedToken("<em>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
201: AddedToken("<b>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
202: AddedToken("<i>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
203: AddedToken("<u>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
204: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
205: AddedToken("<sub>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
206: AddedToken("<sup>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
207: AddedToken("<code>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
208: AddedToken("</strong>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
209: AddedToken("</em>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
210: AddedToken("</b>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
211: AddedToken("</i>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
212: AddedToken("</u>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
213: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
214: AddedToken("</sub>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
215: AddedToken("</sup>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
216: AddedToken("</code>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256000: AddedToken("<loc0000>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256001: AddedToken("<loc0001>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256002: AddedToken("<loc0002>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256003: AddedToken("<loc0003>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256004: AddedToken("<loc0004>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256005: AddedToken("<loc0005>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256006: AddedToken("<loc0006>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256007: AddedToken("<loc0007>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256008: AddedToken("<loc0008>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256009: AddedToken("<loc0009>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256010: AddedToken("<loc0010>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256011: AddedToken("<loc0011>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256012: AddedToken("<loc0012>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256013: AddedToken("<loc0013>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256014: AddedToken("<loc0014>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256015: AddedToken("<loc0015>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256016: AddedToken("<loc0016>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256017: AddedToken("<loc0017>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256018: AddedToken("<loc0018>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256019: AddedToken("<loc0019>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256020: AddedToken("<loc0020>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256021: AddedToken("<loc0021>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256022: AddedToken("<loc0022>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256023: AddedToken("<loc0023>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256024: AddedToken("<loc0024>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256025: AddedToken("<loc0025>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256026: AddedToken("<loc0026>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256027: AddedToken("<loc0027>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256028: AddedToken("<loc0028>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256029: AddedToken("<loc0029>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256030: AddedToken("<loc0030>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256031: AddedToken("<loc0031>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256032: AddedToken("<loc0032>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256033: AddedToken("<loc0033>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256034: AddedToken("<loc0034>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256035: AddedToken("<loc0035>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256036: AddedToken("<loc0036>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256037: AddedToken("<loc0037>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256038: AddedToken("<loc0038>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256039: AddedToken("<loc0039>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256040: AddedToken("<loc0040>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256041: AddedToken("<loc0041>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256042: AddedToken("<loc0042>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256043: AddedToken("<loc0043>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256044: AddedToken("<loc0044>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256045: AddedToken("<loc0045>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256046: AddedToken("<loc0046>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256047: AddedToken("<loc0047>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256048: AddedToken("<loc0048>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256049: AddedToken("<loc0049>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256050: AddedToken("<loc0050>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256051: AddedToken("<loc0051>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256052: AddedToken("<loc0052>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256053: AddedToken("<loc0053>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256054: AddedToken("<loc0054>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256055: AddedToken("<loc0055>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256056: AddedToken("<loc0056>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256057: AddedToken("<loc0057>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256058: AddedToken("<loc0058>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256059: AddedToken("<loc0059>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256060: AddedToken("<loc0060>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256061: AddedToken("<loc0061>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256062: AddedToken("<loc0062>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256063: AddedToken("<loc0063>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256064: AddedToken("<loc0064>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256065: AddedToken("<loc0065>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256066: AddedToken("<loc0066>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256067: AddedToken("<loc0067>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256068: AddedToken("<loc0068>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256069: AddedToken("<loc0069>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256070: AddedToken("<loc0070>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256071: AddedToken("<loc0071>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256072: AddedToken("<loc0072>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256073: AddedToken("<loc0073>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256074: AddedToken("<loc0074>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256075: AddedToken("<loc0075>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256076: AddedToken("<loc0076>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256077: AddedToken("<loc0077>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256078: AddedToken("<loc0078>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256079: AddedToken("<loc0079>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256080: AddedToken("<loc0080>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256081: AddedToken("<loc0081>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256082: AddedToken("<loc0082>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256083: AddedToken("<loc0083>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256084: AddedToken("<loc0084>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256085: AddedToken("<loc0085>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256086: AddedToken("<loc0086>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256087: AddedToken("<loc0087>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256088: AddedToken("<loc0088>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256089: AddedToken("<loc0089>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256090: AddedToken("<loc0090>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256091: AddedToken("<loc0091>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256092: AddedToken("<loc0092>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256093: AddedToken("<loc0093>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256094: AddedToken("<loc0094>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256095: AddedToken("<loc0095>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256096: AddedToken("<loc0096>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256097: AddedToken("<loc0097>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256098: AddedToken("<loc0098>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256099: AddedToken("<loc0099>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256100: AddedToken("<loc0100>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256101: AddedToken("<loc0101>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256102: AddedToken("<loc0102>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256103: AddedToken("<loc0103>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256104: AddedToken("<loc0104>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256105: AddedToken("<loc0105>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256106: AddedToken("<loc0106>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256107: AddedToken("<loc0107>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256108: AddedToken("<loc0108>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256109: AddedToken("<loc0109>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256110: AddedToken("<loc0110>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256111: AddedToken("<loc0111>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256112: AddedToken("<loc0112>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256113: AddedToken("<loc0113>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256114: AddedToken("<loc0114>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256115: AddedToken("<loc0115>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256116: AddedToken("<loc0116>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256117: AddedToken("<loc0117>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256118: AddedToken("<loc0118>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256119: AddedToken("<loc0119>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256120: AddedToken("<loc0120>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256121: AddedToken("<loc0121>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256122: AddedToken("<loc0122>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256123: AddedToken("<loc0123>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256124: AddedToken("<loc0124>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256125: AddedToken("<loc0125>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256126: AddedToken("<loc0126>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256127: AddedToken("<loc0127>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256128: AddedToken("<loc0128>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256129: AddedToken("<loc0129>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256130: AddedToken("<loc0130>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256131: AddedToken("<loc0131>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256132: AddedToken("<loc0132>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256133: AddedToken("<loc0133>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256134: AddedToken("<loc0134>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256135: AddedToken("<loc0135>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256136: AddedToken("<loc0136>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256137: AddedToken("<loc0137>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256138: AddedToken("<loc0138>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256139: AddedToken("<loc0139>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256140: AddedToken("<loc0140>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256141: AddedToken("<loc0141>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256142: AddedToken("<loc0142>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256143: AddedToken("<loc0143>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256144: AddedToken("<loc0144>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256145: AddedToken("<loc0145>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256146: AddedToken("<loc0146>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256147: AddedToken("<loc0147>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256148: AddedToken("<loc0148>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256149: AddedToken("<loc0149>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256150: AddedToken("<loc0150>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256151: AddedToken("<loc0151>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256152: AddedToken("<loc0152>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256153: AddedToken("<loc0153>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256154: AddedToken("<loc0154>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256155: AddedToken("<loc0155>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256156: AddedToken("<loc0156>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256157: AddedToken("<loc0157>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256158: AddedToken("<loc0158>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256159: AddedToken("<loc0159>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256160: AddedToken("<loc0160>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256161: AddedToken("<loc0161>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256162: AddedToken("<loc0162>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256163: AddedToken("<loc0163>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256164: AddedToken("<loc0164>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256165: AddedToken("<loc0165>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256166: AddedToken("<loc0166>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256167: AddedToken("<loc0167>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256168: AddedToken("<loc0168>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256169: AddedToken("<loc0169>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256170: AddedToken("<loc0170>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256171: AddedToken("<loc0171>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256172: AddedToken("<loc0172>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256173: AddedToken("<loc0173>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256174: AddedToken("<loc0174>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256175: AddedToken("<loc0175>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256176: AddedToken("<loc0176>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256177: AddedToken("<loc0177>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256178: AddedToken("<loc0178>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256179: AddedToken("<loc0179>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256180: AddedToken("<loc0180>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256181: AddedToken("<loc0181>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256182: AddedToken("<loc0182>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256183: AddedToken("<loc0183>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256184: AddedToken("<loc0184>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256185: AddedToken("<loc0185>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256186: AddedToken("<loc0186>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256187: AddedToken("<loc0187>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256188: AddedToken("<loc0188>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256189: AddedToken("<loc0189>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256190: AddedToken("<loc0190>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256191: AddedToken("<loc0191>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256192: AddedToken("<loc0192>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256193: AddedToken("<loc0193>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256194: AddedToken("<loc0194>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256195: AddedToken("<loc0195>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256196: AddedToken("<loc0196>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256197: AddedToken("<loc0197>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256198: AddedToken("<loc0198>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256199: AddedToken("<loc0199>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256200: AddedToken("<loc0200>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256201: AddedToken("<loc0201>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256202: AddedToken("<loc0202>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256203: AddedToken("<loc0203>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256204: AddedToken("<loc0204>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256205: AddedToken("<loc0205>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256206: AddedToken("<loc0206>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256207: AddedToken("<loc0207>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256208: AddedToken("<loc0208>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256209: AddedToken("<loc0209>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256210: AddedToken("<loc0210>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256211: AddedToken("<loc0211>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256212: AddedToken("<loc0212>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256213: AddedToken("<loc0213>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256214: AddedToken("<loc0214>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256215: AddedToken("<loc0215>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256216: AddedToken("<loc0216>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256217: AddedToken("<loc0217>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256218: AddedToken("<loc0218>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256219: AddedToken("<loc0219>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256220: AddedToken("<loc0220>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256221: AddedToken("<loc0221>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256222: AddedToken("<loc0222>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256223: AddedToken("<loc0223>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256224: AddedToken("<loc0224>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256225: AddedToken("<loc0225>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256226: AddedToken("<loc0226>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256227: AddedToken("<loc0227>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256228: AddedToken("<loc0228>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256229: AddedToken("<loc0229>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256230: AddedToken("<loc0230>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256231: AddedToken("<loc0231>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256232: AddedToken("<loc0232>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256233: AddedToken("<loc0233>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256234: AddedToken("<loc0234>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256235: AddedToken("<loc0235>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256236: AddedToken("<loc0236>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256237: AddedToken("<loc0237>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256238: AddedToken("<loc0238>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256239: AddedToken("<loc0239>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256240: AddedToken("<loc0240>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256241: AddedToken("<loc0241>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256242: AddedToken("<loc0242>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256243: AddedToken("<loc0243>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256244: AddedToken("<loc0244>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256245: AddedToken("<loc0245>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256246: AddedToken("<loc0246>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256247: AddedToken("<loc0247>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256248: AddedToken("<loc0248>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256249: AddedToken("<loc0249>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256250: AddedToken("<loc0250>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256251: AddedToken("<loc0251>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256252: AddedToken("<loc0252>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256253: AddedToken("<loc0253>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256254: AddedToken("<loc0254>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256255: AddedToken("<loc0255>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256256: AddedToken("<loc0256>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256257: AddedToken("<loc0257>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256258: AddedToken("<loc0258>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256259: AddedToken("<loc0259>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256260: AddedToken("<loc0260>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256261: AddedToken("<loc0261>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256262: AddedToken("<loc0262>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256263: AddedToken("<loc0263>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256264: AddedToken("<loc0264>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256265: AddedToken("<loc0265>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256266: AddedToken("<loc0266>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256267: AddedToken("<loc0267>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256268: AddedToken("<loc0268>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256269: AddedToken("<loc0269>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256270: AddedToken("<loc0270>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256271: AddedToken("<loc0271>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256272: AddedToken("<loc0272>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256273: AddedToken("<loc0273>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256274: AddedToken("<loc0274>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256275: AddedToken("<loc0275>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256276: AddedToken("<loc0276>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256277: AddedToken("<loc0277>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256278: AddedToken("<loc0278>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256279: AddedToken("<loc0279>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256280: AddedToken("<loc0280>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256281: AddedToken("<loc0281>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256282: AddedToken("<loc0282>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256283: AddedToken("<loc0283>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256284: AddedToken("<loc0284>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256285: AddedToken("<loc0285>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256286: AddedToken("<loc0286>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256287: AddedToken("<loc0287>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256288: AddedToken("<loc0288>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256289: AddedToken("<loc0289>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256290: AddedToken("<loc0290>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256291: AddedToken("<loc0291>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256292: AddedToken("<loc0292>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256293: AddedToken("<loc0293>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256294: AddedToken("<loc0294>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256295: AddedToken("<loc0295>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256296: AddedToken("<loc0296>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256297: AddedToken("<loc0297>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256298: AddedToken("<loc0298>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256299: AddedToken("<loc0299>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256300: AddedToken("<loc0300>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256301: AddedToken("<loc0301>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256302: AddedToken("<loc0302>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256303: AddedToken("<loc0303>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256304: AddedToken("<loc0304>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256305: AddedToken("<loc0305>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256306: AddedToken("<loc0306>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256307: AddedToken("<loc0307>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256308: AddedToken("<loc0308>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256309: AddedToken("<loc0309>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256310: AddedToken("<loc0310>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256311: AddedToken("<loc0311>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256312: AddedToken("<loc0312>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256313: AddedToken("<loc0313>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256314: AddedToken("<loc0314>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256315: AddedToken("<loc0315>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256316: AddedToken("<loc0316>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256317: AddedToken("<loc0317>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256318: AddedToken("<loc0318>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256319: AddedToken("<loc0319>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256320: AddedToken("<loc0320>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256321: AddedToken("<loc0321>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256322: AddedToken("<loc0322>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256323: AddedToken("<loc0323>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256324: AddedToken("<loc0324>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256325: AddedToken("<loc0325>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256326: AddedToken("<loc0326>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256327: AddedToken("<loc0327>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256328: AddedToken("<loc0328>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256329: AddedToken("<loc0329>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256330: AddedToken("<loc0330>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256331: AddedToken("<loc0331>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256332: AddedToken("<loc0332>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256333: AddedToken("<loc0333>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256334: AddedToken("<loc0334>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256335: AddedToken("<loc0335>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256336: AddedToken("<loc0336>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256337: AddedToken("<loc0337>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256338: AddedToken("<loc0338>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256339: AddedToken("<loc0339>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256340: AddedToken("<loc0340>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256341: AddedToken("<loc0341>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256342: AddedToken("<loc0342>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256343: AddedToken("<loc0343>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256344: AddedToken("<loc0344>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256345: AddedToken("<loc0345>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256346: AddedToken("<loc0346>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256347: AddedToken("<loc0347>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256348: AddedToken("<loc0348>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256349: AddedToken("<loc0349>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256350: AddedToken("<loc0350>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256351: AddedToken("<loc0351>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256352: AddedToken("<loc0352>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256353: AddedToken("<loc0353>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256354: AddedToken("<loc0354>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256355: AddedToken("<loc0355>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256356: AddedToken("<loc0356>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256357: AddedToken("<loc0357>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256358: AddedToken("<loc0358>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256359: AddedToken("<loc0359>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256360: AddedToken("<loc0360>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256361: AddedToken("<loc0361>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256362: AddedToken("<loc0362>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256363: AddedToken("<loc0363>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256364: AddedToken("<loc0364>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256365: AddedToken("<loc0365>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256366: AddedToken("<loc0366>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256367: AddedToken("<loc0367>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256368: AddedToken("<loc0368>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256369: AddedToken("<loc0369>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256370: AddedToken("<loc0370>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256371: AddedToken("<loc0371>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256372: AddedToken("<loc0372>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256373: AddedToken("<loc0373>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256374: AddedToken("<loc0374>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256375: AddedToken("<loc0375>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256376: AddedToken("<loc0376>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256377: AddedToken("<loc0377>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256378: AddedToken("<loc0378>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256379: AddedToken("<loc0379>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256380: AddedToken("<loc0380>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256381: AddedToken("<loc0381>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256382: AddedToken("<loc0382>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256383: AddedToken("<loc0383>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256384: AddedToken("<loc0384>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256385: AddedToken("<loc0385>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256386: AddedToken("<loc0386>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256387: AddedToken("<loc0387>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256388: AddedToken("<loc0388>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256389: AddedToken("<loc0389>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256390: AddedToken("<loc0390>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256391: AddedToken("<loc0391>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256392: AddedToken("<loc0392>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256393: AddedToken("<loc0393>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256394: AddedToken("<loc0394>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256395: AddedToken("<loc0395>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256396: AddedToken("<loc0396>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256397: AddedToken("<loc0397>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256398: AddedToken("<loc0398>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256399: AddedToken("<loc0399>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256400: AddedToken("<loc0400>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256401: AddedToken("<loc0401>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256402: AddedToken("<loc0402>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256403: AddedToken("<loc0403>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256404: AddedToken("<loc0404>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256405: AddedToken("<loc0405>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256406: AddedToken("<loc0406>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256407: AddedToken("<loc0407>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256408: AddedToken("<loc0408>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256409: AddedToken("<loc0409>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256410: AddedToken("<loc0410>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256411: AddedToken("<loc0411>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256412: AddedToken("<loc0412>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256413: AddedToken("<loc0413>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256414: AddedToken("<loc0414>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256415: AddedToken("<loc0415>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256416: AddedToken("<loc0416>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256417: AddedToken("<loc0417>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256418: AddedToken("<loc0418>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256419: AddedToken("<loc0419>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256420: AddedToken("<loc0420>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256421: AddedToken("<loc0421>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256422: AddedToken("<loc0422>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256423: AddedToken("<loc0423>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256424: AddedToken("<loc0424>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256425: AddedToken("<loc0425>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256426: AddedToken("<loc0426>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256427: AddedToken("<loc0427>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256428: AddedToken("<loc0428>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256429: AddedToken("<loc0429>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256430: AddedToken("<loc0430>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256431: AddedToken("<loc0431>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256432: AddedToken("<loc0432>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256433: AddedToken("<loc0433>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256434: AddedToken("<loc0434>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256435: AddedToken("<loc0435>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256436: AddedToken("<loc0436>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256437: AddedToken("<loc0437>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256438: AddedToken("<loc0438>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256439: AddedToken("<loc0439>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256440: AddedToken("<loc0440>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256441: AddedToken("<loc0441>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256442: AddedToken("<loc0442>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256443: AddedToken("<loc0443>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256444: AddedToken("<loc0444>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256445: AddedToken("<loc0445>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256446: AddedToken("<loc0446>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256447: AddedToken("<loc0447>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256448: AddedToken("<loc0448>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256449: AddedToken("<loc0449>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256450: AddedToken("<loc0450>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256451: AddedToken("<loc0451>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256452: AddedToken("<loc0452>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256453: AddedToken("<loc0453>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256454: AddedToken("<loc0454>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256455: AddedToken("<loc0455>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256456: AddedToken("<loc0456>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256457: AddedToken("<loc0457>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256458: AddedToken("<loc0458>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256459: AddedToken("<loc0459>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256460: AddedToken("<loc0460>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256461: AddedToken("<loc0461>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256462: AddedToken("<loc0462>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256463: AddedToken("<loc0463>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256464: AddedToken("<loc0464>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256465: AddedToken("<loc0465>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256466: AddedToken("<loc0466>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256467: AddedToken("<loc0467>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256468: AddedToken("<loc0468>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256469: AddedToken("<loc0469>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256470: AddedToken("<loc0470>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256471: AddedToken("<loc0471>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256472: AddedToken("<loc0472>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256473: AddedToken("<loc0473>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256474: AddedToken("<loc0474>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256475: AddedToken("<loc0475>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256476: AddedToken("<loc0476>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256477: AddedToken("<loc0477>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256478: AddedToken("<loc0478>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256479: AddedToken("<loc0479>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256480: AddedToken("<loc0480>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256481: AddedToken("<loc0481>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256482: AddedToken("<loc0482>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256483: AddedToken("<loc0483>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256484: AddedToken("<loc0484>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256485: AddedToken("<loc0485>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256486: AddedToken("<loc0486>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256487: AddedToken("<loc0487>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256488: AddedToken("<loc0488>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256489: AddedToken("<loc0489>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256490: AddedToken("<loc0490>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256491: AddedToken("<loc0491>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256492: AddedToken("<loc0492>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256493: AddedToken("<loc0493>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256494: AddedToken("<loc0494>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256495: AddedToken("<loc0495>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256496: AddedToken("<loc0496>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256497: AddedToken("<loc0497>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256498: AddedToken("<loc0498>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256499: AddedToken("<loc0499>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256500: AddedToken("<loc0500>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256501: AddedToken("<loc0501>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256502: AddedToken("<loc0502>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256503: AddedToken("<loc0503>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256504: AddedToken("<loc0504>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256505: AddedToken("<loc0505>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256506: AddedToken("<loc0506>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256507: AddedToken("<loc0507>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256508: AddedToken("<loc0508>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256509: AddedToken("<loc0509>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256510: AddedToken("<loc0510>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256511: AddedToken("<loc0511>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256512: AddedToken("<loc0512>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256513: AddedToken("<loc0513>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256514: AddedToken("<loc0514>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256515: AddedToken("<loc0515>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256516: AddedToken("<loc0516>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256517: AddedToken("<loc0517>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256518: AddedToken("<loc0518>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256519: AddedToken("<loc0519>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256520: AddedToken("<loc0520>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256521: AddedToken("<loc0521>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256522: AddedToken("<loc0522>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256523: AddedToken("<loc0523>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256524: AddedToken("<loc0524>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256525: AddedToken("<loc0525>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256526: AddedToken("<loc0526>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256527: AddedToken("<loc0527>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256528: AddedToken("<loc0528>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256529: AddedToken("<loc0529>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256530: AddedToken("<loc0530>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256531: AddedToken("<loc0531>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256532: AddedToken("<loc0532>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256533: AddedToken("<loc0533>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256534: AddedToken("<loc0534>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256535: AddedToken("<loc0535>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256536: AddedToken("<loc0536>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256537: AddedToken("<loc0537>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256538: AddedToken("<loc0538>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256539: AddedToken("<loc0539>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256540: AddedToken("<loc0540>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256541: AddedToken("<loc0541>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256542: AddedToken("<loc0542>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256543: AddedToken("<loc0543>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256544: AddedToken("<loc0544>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256545: AddedToken("<loc0545>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256546: AddedToken("<loc0546>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256547: AddedToken("<loc0547>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256548: AddedToken("<loc0548>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256549: AddedToken("<loc0549>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256550: AddedToken("<loc0550>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256551: AddedToken("<loc0551>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256552: AddedToken("<loc0552>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256553: AddedToken("<loc0553>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256554: AddedToken("<loc0554>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256555: AddedToken("<loc0555>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256556: AddedToken("<loc0556>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256557: AddedToken("<loc0557>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256558: AddedToken("<loc0558>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256559: AddedToken("<loc0559>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256560: AddedToken("<loc0560>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256561: AddedToken("<loc0561>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256562: AddedToken("<loc0562>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256563: AddedToken("<loc0563>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256564: AddedToken("<loc0564>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256565: AddedToken("<loc0565>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256566: AddedToken("<loc0566>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256567: AddedToken("<loc0567>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256568: AddedToken("<loc0568>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256569: AddedToken("<loc0569>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256570: AddedToken("<loc0570>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256571: AddedToken("<loc0571>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256572: AddedToken("<loc0572>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256573: AddedToken("<loc0573>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256574: AddedToken("<loc0574>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256575: AddedToken("<loc0575>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256576: AddedToken("<loc0576>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256577: AddedToken("<loc0577>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256578: AddedToken("<loc0578>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256579: AddedToken("<loc0579>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256580: AddedToken("<loc0580>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256581: AddedToken("<loc0581>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256582: AddedToken("<loc0582>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256583: AddedToken("<loc0583>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256584: AddedToken("<loc0584>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256585: AddedToken("<loc0585>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256586: AddedToken("<loc0586>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256587: AddedToken("<loc0587>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256588: AddedToken("<loc0588>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256589: AddedToken("<loc0589>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256590: AddedToken("<loc0590>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256591: AddedToken("<loc0591>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256592: AddedToken("<loc0592>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256593: AddedToken("<loc0593>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256594: AddedToken("<loc0594>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256595: AddedToken("<loc0595>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256596: AddedToken("<loc0596>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256597: AddedToken("<loc0597>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256598: AddedToken("<loc0598>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256599: AddedToken("<loc0599>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256600: AddedToken("<loc0600>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256601: AddedToken("<loc0601>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256602: AddedToken("<loc0602>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256603: AddedToken("<loc0603>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256604: AddedToken("<loc0604>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256605: AddedToken("<loc0605>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256606: AddedToken("<loc0606>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256607: AddedToken("<loc0607>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256608: AddedToken("<loc0608>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256609: AddedToken("<loc0609>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256610: AddedToken("<loc0610>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256611: AddedToken("<loc0611>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256612: AddedToken("<loc0612>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256613: AddedToken("<loc0613>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256614: AddedToken("<loc0614>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256615: AddedToken("<loc0615>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256616: AddedToken("<loc0616>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256617: AddedToken("<loc0617>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256618: AddedToken("<loc0618>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256619: AddedToken("<loc0619>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256620: AddedToken("<loc0620>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256621: AddedToken("<loc0621>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256622: AddedToken("<loc0622>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256623: AddedToken("<loc0623>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256624: AddedToken("<loc0624>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256625: AddedToken("<loc0625>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256626: AddedToken("<loc0626>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256627: AddedToken("<loc0627>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256628: AddedToken("<loc0628>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256629: AddedToken("<loc0629>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256630: AddedToken("<loc0630>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256631: AddedToken("<loc0631>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256632: AddedToken("<loc0632>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256633: AddedToken("<loc0633>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256634: AddedToken("<loc0634>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256635: AddedToken("<loc0635>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256636: AddedToken("<loc0636>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256637: AddedToken("<loc0637>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256638: AddedToken("<loc0638>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256639: AddedToken("<loc0639>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256640: AddedToken("<loc0640>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256641: AddedToken("<loc0641>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256642: AddedToken("<loc0642>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256643: AddedToken("<loc0643>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256644: AddedToken("<loc0644>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256645: AddedToken("<loc0645>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256646: AddedToken("<loc0646>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256647: AddedToken("<loc0647>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256648: AddedToken("<loc0648>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256649: AddedToken("<loc0649>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256650: AddedToken("<loc0650>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256651: AddedToken("<loc0651>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256652: AddedToken("<loc0652>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256653: AddedToken("<loc0653>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256654: AddedToken("<loc0654>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256655: AddedToken("<loc0655>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256656: AddedToken("<loc0656>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256657: AddedToken("<loc0657>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256658: AddedToken("<loc0658>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256659: AddedToken("<loc0659>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256660: AddedToken("<loc0660>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256661: AddedToken("<loc0661>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256662: AddedToken("<loc0662>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256663: AddedToken("<loc0663>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256664: AddedToken("<loc0664>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256665: AddedToken("<loc0665>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256666: AddedToken("<loc0666>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256667: AddedToken("<loc0667>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256668: AddedToken("<loc0668>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256669: AddedToken("<loc0669>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256670: AddedToken("<loc0670>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256671: AddedToken("<loc0671>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256672: AddedToken("<loc0672>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256673: AddedToken("<loc0673>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256674: AddedToken("<loc0674>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256675: AddedToken("<loc0675>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256676: AddedToken("<loc0676>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256677: AddedToken("<loc0677>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256678: AddedToken("<loc0678>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256679: AddedToken("<loc0679>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256680: AddedToken("<loc0680>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256681: AddedToken("<loc0681>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256682: AddedToken("<loc0682>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256683: AddedToken("<loc0683>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256684: AddedToken("<loc0684>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256685: AddedToken("<loc0685>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256686: AddedToken("<loc0686>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256687: AddedToken("<loc0687>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256688: AddedToken("<loc0688>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256689: AddedToken("<loc0689>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256690: AddedToken("<loc0690>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256691: AddedToken("<loc0691>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256692: AddedToken("<loc0692>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256693: AddedToken("<loc0693>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256694: AddedToken("<loc0694>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256695: AddedToken("<loc0695>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256696: AddedToken("<loc0696>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256697: AddedToken("<loc0697>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256698: AddedToken("<loc0698>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256699: AddedToken("<loc0699>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256700: AddedToken("<loc0700>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256701: AddedToken("<loc0701>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256702: AddedToken("<loc0702>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256703: AddedToken("<loc0703>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256704: AddedToken("<loc0704>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256705: AddedToken("<loc0705>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256706: AddedToken("<loc0706>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256707: AddedToken("<loc0707>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256708: AddedToken("<loc0708>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256709: AddedToken("<loc0709>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256710: AddedToken("<loc0710>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256711: AddedToken("<loc0711>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256712: AddedToken("<loc0712>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256713: AddedToken("<loc0713>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256714: AddedToken("<loc0714>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256715: AddedToken("<loc0715>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256716: AddedToken("<loc0716>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256717: AddedToken("<loc0717>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256718: AddedToken("<loc0718>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256719: AddedToken("<loc0719>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256720: AddedToken("<loc0720>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256721: AddedToken("<loc0721>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256722: AddedToken("<loc0722>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256723: AddedToken("<loc0723>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256724: AddedToken("<loc0724>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256725: AddedToken("<loc0725>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256726: AddedToken("<loc0726>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256727: AddedToken("<loc0727>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256728: AddedToken("<loc0728>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256729: AddedToken("<loc0729>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256730: AddedToken("<loc0730>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256731: AddedToken("<loc0731>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256732: AddedToken("<loc0732>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256733: AddedToken("<loc0733>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256734: AddedToken("<loc0734>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256735: AddedToken("<loc0735>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256736: AddedToken("<loc0736>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256737: AddedToken("<loc0737>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256738: AddedToken("<loc0738>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256739: AddedToken("<loc0739>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256740: AddedToken("<loc0740>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256741: AddedToken("<loc0741>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256742: AddedToken("<loc0742>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256743: AddedToken("<loc0743>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256744: AddedToken("<loc0744>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256745: AddedToken("<loc0745>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256746: AddedToken("<loc0746>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256747: AddedToken("<loc0747>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256748: AddedToken("<loc0748>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256749: AddedToken("<loc0749>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256750: AddedToken("<loc0750>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256751: AddedToken("<loc0751>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256752: AddedToken("<loc0752>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256753: AddedToken("<loc0753>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256754: AddedToken("<loc0754>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256755: AddedToken("<loc0755>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256756: AddedToken("<loc0756>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256757: AddedToken("<loc0757>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256758: AddedToken("<loc0758>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256759: AddedToken("<loc0759>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256760: AddedToken("<loc0760>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256761: AddedToken("<loc0761>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256762: AddedToken("<loc0762>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256763: AddedToken("<loc0763>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256764: AddedToken("<loc0764>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256765: AddedToken("<loc0765>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256766: AddedToken("<loc0766>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256767: AddedToken("<loc0767>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256768: AddedToken("<loc0768>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256769: AddedToken("<loc0769>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256770: AddedToken("<loc0770>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256771: AddedToken("<loc0771>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256772: AddedToken("<loc0772>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256773: AddedToken("<loc0773>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256774: AddedToken("<loc0774>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256775: AddedToken("<loc0775>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256776: AddedToken("<loc0776>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256777: AddedToken("<loc0777>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256778: AddedToken("<loc0778>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256779: AddedToken("<loc0779>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256780: AddedToken("<loc0780>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256781: AddedToken("<loc0781>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256782: AddedToken("<loc0782>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256783: AddedToken("<loc0783>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256784: AddedToken("<loc0784>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256785: AddedToken("<loc0785>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256786: AddedToken("<loc0786>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256787: AddedToken("<loc0787>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256788: AddedToken("<loc0788>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256789: AddedToken("<loc0789>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256790: AddedToken("<loc0790>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256791: AddedToken("<loc0791>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256792: AddedToken("<loc0792>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256793: AddedToken("<loc0793>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256794: AddedToken("<loc0794>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256795: AddedToken("<loc0795>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256796: AddedToken("<loc0796>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256797: AddedToken("<loc0797>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256798: AddedToken("<loc0798>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256799: AddedToken("<loc0799>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256800: AddedToken("<loc0800>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256801: AddedToken("<loc0801>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256802: AddedToken("<loc0802>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256803: AddedToken("<loc0803>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256804: AddedToken("<loc0804>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256805: AddedToken("<loc0805>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256806: AddedToken("<loc0806>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256807: AddedToken("<loc0807>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256808: AddedToken("<loc0808>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256809: AddedToken("<loc0809>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256810: AddedToken("<loc0810>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256811: AddedToken("<loc0811>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256812: AddedToken("<loc0812>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256813: AddedToken("<loc0813>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256814: AddedToken("<loc0814>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256815: AddedToken("<loc0815>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256816: AddedToken("<loc0816>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256817: AddedToken("<loc0817>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256818: AddedToken("<loc0818>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256819: AddedToken("<loc0819>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256820: AddedToken("<loc0820>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256821: AddedToken("<loc0821>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256822: AddedToken("<loc0822>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256823: AddedToken("<loc0823>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256824: AddedToken("<loc0824>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256825: AddedToken("<loc0825>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256826: AddedToken("<loc0826>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256827: AddedToken("<loc0827>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256828: AddedToken("<loc0828>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256829: AddedToken("<loc0829>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256830: AddedToken("<loc0830>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256831: AddedToken("<loc0831>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256832: AddedToken("<loc0832>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256833: AddedToken("<loc0833>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256834: AddedToken("<loc0834>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256835: AddedToken("<loc0835>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256836: AddedToken("<loc0836>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256837: AddedToken("<loc0837>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256838: AddedToken("<loc0838>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256839: AddedToken("<loc0839>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256840: AddedToken("<loc0840>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256841: AddedToken("<loc0841>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256842: AddedToken("<loc0842>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256843: AddedToken("<loc0843>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256844: AddedToken("<loc0844>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256845: AddedToken("<loc0845>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256846: AddedToken("<loc0846>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256847: AddedToken("<loc0847>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256848: AddedToken("<loc0848>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256849: AddedToken("<loc0849>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256850: AddedToken("<loc0850>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256851: AddedToken("<loc0851>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256852: AddedToken("<loc0852>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256853: AddedToken("<loc0853>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256854: AddedToken("<loc0854>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256855: AddedToken("<loc0855>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256856: AddedToken("<loc0856>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256857: AddedToken("<loc0857>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256858: AddedToken("<loc0858>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256859: AddedToken("<loc0859>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256860: AddedToken("<loc0860>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256861: AddedToken("<loc0861>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256862: AddedToken("<loc0862>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256863: AddedToken("<loc0863>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256864: AddedToken("<loc0864>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256865: AddedToken("<loc0865>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256866: AddedToken("<loc0866>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256867: AddedToken("<loc0867>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256868: AddedToken("<loc0868>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256869: AddedToken("<loc0869>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256870: AddedToken("<loc0870>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256871: AddedToken("<loc0871>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256872: AddedToken("<loc0872>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256873: AddedToken("<loc0873>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256874: AddedToken("<loc0874>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256875: AddedToken("<loc0875>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256876: AddedToken("<loc0876>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256877: AddedToken("<loc0877>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256878: AddedToken("<loc0878>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256879: AddedToken("<loc0879>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256880: AddedToken("<loc0880>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256881: AddedToken("<loc0881>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256882: AddedToken("<loc0882>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256883: AddedToken("<loc0883>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256884: AddedToken("<loc0884>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256885: AddedToken("<loc0885>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256886: AddedToken("<loc0886>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256887: AddedToken("<loc0887>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256888: AddedToken("<loc0888>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256889: AddedToken("<loc0889>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256890: AddedToken("<loc0890>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256891: AddedToken("<loc0891>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256892: AddedToken("<loc0892>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256893: AddedToken("<loc0893>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256894: AddedToken("<loc0894>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256895: AddedToken("<loc0895>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256896: AddedToken("<loc0896>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256897: AddedToken("<loc0897>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256898: AddedToken("<loc0898>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256899: AddedToken("<loc0899>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256900: AddedToken("<loc0900>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256901: AddedToken("<loc0901>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256902: AddedToken("<loc0902>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256903: AddedToken("<loc0903>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256904: AddedToken("<loc0904>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256905: AddedToken("<loc0905>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256906: AddedToken("<loc0906>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256907: AddedToken("<loc0907>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256908: AddedToken("<loc0908>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256909: AddedToken("<loc0909>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256910: AddedToken("<loc0910>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256911: AddedToken("<loc0911>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256912: AddedToken("<loc0912>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256913: AddedToken("<loc0913>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256914: AddedToken("<loc0914>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256915: AddedToken("<loc0915>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256916: AddedToken("<loc0916>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256917: AddedToken("<loc0917>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256918: AddedToken("<loc0918>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256919: AddedToken("<loc0919>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256920: AddedToken("<loc0920>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256921: AddedToken("<loc0921>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256922: AddedToken("<loc0922>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256923: AddedToken("<loc0923>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256924: AddedToken("<loc0924>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256925: AddedToken("<loc0925>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256926: AddedToken("<loc0926>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256927: AddedToken("<loc0927>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256928: AddedToken("<loc0928>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256929: AddedToken("<loc0929>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256930: AddedToken("<loc0930>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256931: AddedToken("<loc0931>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256932: AddedToken("<loc0932>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256933: AddedToken("<loc0933>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256934: AddedToken("<loc0934>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256935: AddedToken("<loc0935>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256936: AddedToken("<loc0936>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256937: AddedToken("<loc0937>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256938: AddedToken("<loc0938>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256939: AddedToken("<loc0939>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256940: AddedToken("<loc0940>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256941: AddedToken("<loc0941>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256942: AddedToken("<loc0942>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256943: AddedToken("<loc0943>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256944: AddedToken("<loc0944>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256945: AddedToken("<loc0945>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256946: AddedToken("<loc0946>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256947: AddedToken("<loc0947>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256948: AddedToken("<loc0948>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256949: AddedToken("<loc0949>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256950: AddedToken("<loc0950>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256951: AddedToken("<loc0951>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256952: AddedToken("<loc0952>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256953: AddedToken("<loc0953>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256954: AddedToken("<loc0954>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256955: AddedToken("<loc0955>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256956: AddedToken("<loc0956>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256957: AddedToken("<loc0957>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256958: AddedToken("<loc0958>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256959: AddedToken("<loc0959>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256960: AddedToken("<loc0960>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256961: AddedToken("<loc0961>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256962: AddedToken("<loc0962>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256963: AddedToken("<loc0963>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256964: AddedToken("<loc0964>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256965: AddedToken("<loc0965>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256966: AddedToken("<loc0966>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256967: AddedToken("<loc0967>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256968: AddedToken("<loc0968>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256969: AddedToken("<loc0969>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256970: AddedToken("<loc0970>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256971: AddedToken("<loc0971>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256972: AddedToken("<loc0972>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256973: AddedToken("<loc0973>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256974: AddedToken("<loc0974>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256975: AddedToken("<loc0975>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256976: AddedToken("<loc0976>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256977: AddedToken("<loc0977>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256978: AddedToken("<loc0978>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256979: AddedToken("<loc0979>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256980: AddedToken("<loc0980>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256981: AddedToken("<loc0981>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256982: AddedToken("<loc0982>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256983: AddedToken("<loc0983>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256984: AddedToken("<loc0984>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256985: AddedToken("<loc0985>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256986: AddedToken("<loc0986>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256987: AddedToken("<loc0987>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256988: AddedToken("<loc0988>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256989: AddedToken("<loc0989>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256990: AddedToken("<loc0990>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256991: AddedToken("<loc0991>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256992: AddedToken("<loc0992>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256993: AddedToken("<loc0993>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256994: AddedToken("<loc0994>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256995: AddedToken("<loc0995>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256996: AddedToken("<loc0996>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256997: AddedToken("<loc0997>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256998: AddedToken("<loc0998>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
256999: AddedToken("<loc0999>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257000: AddedToken("<loc1000>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257001: AddedToken("<loc1001>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257002: AddedToken("<loc1002>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257003: AddedToken("<loc1003>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257004: AddedToken("<loc1004>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257005: AddedToken("<loc1005>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257006: AddedToken("<loc1006>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257007: AddedToken("<loc1007>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257008: AddedToken("<loc1008>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257009: AddedToken("<loc1009>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257010: AddedToken("<loc1010>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257011: AddedToken("<loc1011>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257012: AddedToken("<loc1012>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257013: AddedToken("<loc1013>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257014: AddedToken("<loc1014>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257015: AddedToken("<loc1015>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257016: AddedToken("<loc1016>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257017: AddedToken("<loc1017>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257018: AddedToken("<loc1018>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257019: AddedToken("<loc1019>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257020: AddedToken("<loc1020>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257021: AddedToken("<loc1021>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257022: AddedToken("<loc1022>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257023: AddedToken("<loc1023>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257024: AddedToken("<seg000>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257025: AddedToken("<seg001>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257026: AddedToken("<seg002>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257027: AddedToken("<seg003>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257028: AddedToken("<seg004>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257029: AddedToken("<seg005>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257030: AddedToken("<seg006>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257031: AddedToken("<seg007>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257032: AddedToken("<seg008>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257033: AddedToken("<seg009>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257034: AddedToken("<seg010>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257035: AddedToken("<seg011>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257036: AddedToken("<seg012>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257037: AddedToken("<seg013>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257038: AddedToken("<seg014>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257039: AddedToken("<seg015>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257040: AddedToken("<seg016>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257041: AddedToken("<seg017>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257042: AddedToken("<seg018>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257043: AddedToken("<seg019>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257044: AddedToken("<seg020>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257045: AddedToken("<seg021>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257046: AddedToken("<seg022>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257047: AddedToken("<seg023>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257048: AddedToken("<seg024>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257049: AddedToken("<seg025>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257050: AddedToken("<seg026>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257051: AddedToken("<seg027>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257052: AddedToken("<seg028>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257053: AddedToken("<seg029>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257054: AddedToken("<seg030>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257055: AddedToken("<seg031>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257056: AddedToken("<seg032>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257057: AddedToken("<seg033>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257058: AddedToken("<seg034>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257059: AddedToken("<seg035>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257060: AddedToken("<seg036>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257061: AddedToken("<seg037>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257062: AddedToken("<seg038>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257063: AddedToken("<seg039>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257064: AddedToken("<seg040>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257065: AddedToken("<seg041>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257066: AddedToken("<seg042>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257067: AddedToken("<seg043>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257068: AddedToken("<seg044>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257069: AddedToken("<seg045>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257070: AddedToken("<seg046>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257071: AddedToken("<seg047>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257072: AddedToken("<seg048>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257073: AddedToken("<seg049>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257074: AddedToken("<seg050>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257075: AddedToken("<seg051>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257076: AddedToken("<seg052>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257077: AddedToken("<seg053>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257078: AddedToken("<seg054>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257079: AddedToken("<seg055>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257080: AddedToken("<seg056>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257081: AddedToken("<seg057>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257082: AddedToken("<seg058>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257083: AddedToken("<seg059>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257084: AddedToken("<seg060>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257085: AddedToken("<seg061>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257086: AddedToken("<seg062>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257087: AddedToken("<seg063>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257088: AddedToken("<seg064>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257089: AddedToken("<seg065>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257090: AddedToken("<seg066>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257091: AddedToken("<seg067>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257092: AddedToken("<seg068>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257093: AddedToken("<seg069>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257094: AddedToken("<seg070>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257095: AddedToken("<seg071>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257096: AddedToken("<seg072>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257097: AddedToken("<seg073>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257098: AddedToken("<seg074>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257099: AddedToken("<seg075>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257100: AddedToken("<seg076>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257101: AddedToken("<seg077>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257102: AddedToken("<seg078>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257103: AddedToken("<seg079>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257104: AddedToken("<seg080>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257105: AddedToken("<seg081>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257106: AddedToken("<seg082>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257107: AddedToken("<seg083>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257108: AddedToken("<seg084>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257109: AddedToken("<seg085>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257110: AddedToken("<seg086>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257111: AddedToken("<seg087>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257112: AddedToken("<seg088>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257113: AddedToken("<seg089>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257114: AddedToken("<seg090>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257115: AddedToken("<seg091>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257116: AddedToken("<seg092>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257117: AddedToken("<seg093>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257118: AddedToken("<seg094>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257119: AddedToken("<seg095>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257120: AddedToken("<seg096>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257121: AddedToken("<seg097>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257122: AddedToken("<seg098>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257123: AddedToken("<seg099>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257124: AddedToken("<seg100>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257125: AddedToken("<seg101>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257126: AddedToken("<seg102>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257127: AddedToken("<seg103>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257128: AddedToken("<seg104>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257129: AddedToken("<seg105>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257130: AddedToken("<seg106>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257131: AddedToken("<seg107>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257132: AddedToken("<seg108>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257133: AddedToken("<seg109>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257134: AddedToken("<seg110>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257135: AddedToken("<seg111>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257136: AddedToken("<seg112>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257137: AddedToken("<seg113>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257138: AddedToken("<seg114>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257139: AddedToken("<seg115>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257140: AddedToken("<seg116>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257141: AddedToken("<seg117>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257142: AddedToken("<seg118>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257143: AddedToken("<seg119>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257144: AddedToken("<seg120>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257145: AddedToken("<seg121>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257146: AddedToken("<seg122>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257147: AddedToken("<seg123>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257148: AddedToken("<seg124>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257149: AddedToken("<seg125>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257150: AddedToken("<seg126>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257151: AddedToken("<seg127>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), |
|
257152: AddedToken("<image>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), |
|
} |
|
|
|
{ |
|
"processor_class": "PaliGemmaProcessor" |
|
} |
|
|
|
|
|
[INFO|configuration_utils.py:675] 2024-10-14 08:50:47,291 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/config.json |
|
|
|
[INFO|configuration_utils.py:742] 2024-10-14 08:50:47,294 >> Model config PaliGemmaConfig { |
|
"_name_or_path": "google/paligemma-3b-pt-448", |
|
"_vocab_size": 257216, |
|
"architectures": [ |
|
"PaliGemmaForConditionalGeneration" |
|
], |
|
"bos_token_id": 2, |
|
"eos_token_id": 1, |
|
"hidden_size": 2048, |
|
"image_token_index": 257152, |
|
"model_type": "paligemma", |
|
"pad_token_id": 0, |
|
"projection_dim": 2048, |
|
"text_config": { |
|
"hidden_size": 2048, |
|
"intermediate_size": 16384, |
|
"model_type": "gemma", |
|
"num_attention_heads": 8, |
|
"num_hidden_layers": 18, |
|
"num_image_tokens": 1024, |
|
"num_key_value_heads": 1, |
|
"torch_dtype": "float32", |
|
"vocab_size": 257216 |
|
}, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.45.2", |
|
"vision_config": { |
|
"hidden_size": 1152, |
|
"image_size": 448, |
|
"intermediate_size": 4304, |
|
"model_type": "siglip_vision_model", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 27, |
|
"num_image_tokens": 1024, |
|
"patch_size": 14, |
|
"projection_dim": 2048, |
|
"projector_hidden_act": "gelu_fast", |
|
"vision_use_head": false |
|
} |
|
} |
|
|
|
|
|
[INFO|modeling_utils.py:3732] 2024-10-14 08:50:48,260 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/model.safetensors.index.json |
|
|
|
[INFO|modeling_utils.py:1622] 2024-10-14 08:59:29,919 >> Instantiating PaliGemmaForConditionalGeneration model under default dtype torch.bfloat16. |
|
|
|
[INFO|configuration_utils.py:1099] 2024-10-14 08:59:29,921 >> Generate config GenerationConfig { |
|
"bos_token_id": 2, |
|
"eos_token_id": 1, |
|
"pad_token_id": 0 |
|
} |
|
|
|
|
|
[INFO|configuration_utils.py:1099] 2024-10-14 08:59:30,085 >> Generate config GenerationConfig { |
|
"bos_token_id": 2, |
|
"eos_token_id": 1, |
|
"pad_token_id": 0 |
|
} |
|
|
|
|
|
[WARNING|logging.py:328] 2024-10-14 08:59:30,114 >> `config.hidden_act` is ignored, you should use `config.hidden_activation` instead. |
|
Gemma's activation function will be set to `gelu_pytorch_tanh`. Please, use |
|
`config.hidden_activation` if you want to override this behaviour. |
|
See https://github.com/huggingface/transformers/pull/29402 for more details. |
|
|
|
[INFO|modeling_utils.py:4574] 2024-10-14 08:59:33,998 >> All model checkpoint weights were used when initializing PaliGemmaForConditionalGeneration. |
|
|
|
|
|
[INFO|modeling_utils.py:4582] 2024-10-14 08:59:33,999 >> All the weights of PaliGemmaForConditionalGeneration were initialized from the model checkpoint at google/paligemma-3b-pt-448. |
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use PaliGemmaForConditionalGeneration for predictions without further training. |
|
|
|
[INFO|configuration_utils.py:1054] 2024-10-14 08:59:34,505 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--google--paligemma-3b-pt-448/snapshots/b714490ff582c78fb13d35175505831497970a75/generation_config.json |
|
|
|
[INFO|configuration_utils.py:1099] 2024-10-14 08:59:34,506 >> Generate config GenerationConfig { |
|
"bos_token_id": 2, |
|
"eos_token_id": 1, |
|
"pad_token_id": 0 |
|
} |
|
|
|
|
|
[INFO|trainer.py:667] 2024-10-14 08:59:35,140 >> Using auto half precision backend |
|
|
|
[INFO|trainer.py:2243] 2024-10-14 08:59:35,720 >> ***** Running training ***** |
|
|
|
[INFO|trainer.py:2244] 2024-10-14 08:59:35,721 >> Num examples = 1,000 |
|
|
|
[INFO|trainer.py:2245] 2024-10-14 08:59:35,721 >> Num Epochs = 2 |
|
|
|
[INFO|trainer.py:2246] 2024-10-14 08:59:35,721 >> Instantaneous batch size per device = 2 |
|
|
|
[INFO|trainer.py:2249] 2024-10-14 08:59:35,721 >> Total train batch size (w. parallel, distributed & accumulation) = 16 |
|
|
|
[INFO|trainer.py:2250] 2024-10-14 08:59:35,721 >> Gradient Accumulation steps = 8 |
|
|
|
[INFO|trainer.py:2251] 2024-10-14 08:59:35,721 >> Total optimization steps = 124 |
|
|
|
[INFO|trainer.py:2252] 2024-10-14 08:59:35,725 >> Number of trainable parameters = 9,805,824 |
|
|
|
[WARNING|logging.py:328] 2024-10-14 08:59:37,223 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
|
[WARNING|logging.py:328] 2024-10-14 08:59:37,558 >> Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
|
[INFO|trainer.py:3705] 2024-10-14 09:19:27,447 >> Saving model checkpoint to saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-100 |
|
|
|
[INFO|tokenization_utils_base.py:2641] 2024-10-14 09:19:27,821 >> tokenizer config file saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-100/tokenizer_config.json |
|
|
|
[INFO|tokenization_utils_base.py:2650] 2024-10-14 09:19:27,822 >> Special tokens file saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-100/special_tokens_map.json |
|
|
|
[INFO|image_processing_base.py:258] 2024-10-14 09:19:28,460 >> Image processor saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-100/preprocessor_config.json |
|
|
|
[INFO|trainer.py:3705] 2024-10-14 09:24:13,727 >> Saving model checkpoint to saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-124 |
|
|
|
[INFO|tokenization_utils_base.py:2641] 2024-10-14 09:24:14,101 >> tokenizer config file saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-124/tokenizer_config.json |
|
|
|
[INFO|tokenization_utils_base.py:2650] 2024-10-14 09:24:14,101 >> Special tokens file saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-124/special_tokens_map.json |
|
|
|
[INFO|image_processing_base.py:258] 2024-10-14 09:24:14,707 >> Image processor saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/checkpoint-124/preprocessor_config.json |
|
|
|
[INFO|trainer.py:2505] 2024-10-14 09:24:14,707 >> |
|
|
|
Training completed. Do not forget to share your model on huggingface.co/models =) |
|
|
|
|
|
|
|
[INFO|image_processing_base.py:258] 2024-10-14 09:24:14,709 >> Image processor saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/preprocessor_config.json |
|
|
|
[INFO|trainer.py:3705] 2024-10-14 09:24:14,710 >> Saving model checkpoint to saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57 |
|
|
|
[INFO|tokenization_utils_base.py:2641] 2024-10-14 09:24:15,086 >> tokenizer config file saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/tokenizer_config.json |
|
|
|
[INFO|tokenization_utils_base.py:2650] 2024-10-14 09:24:15,087 >> Special tokens file saved in saves/PaliGemma-3B-pt-448-Chat/lora/train_2024-10-14-08-49-57/special_tokens_map.json |
|
|
|
[INFO|modelcard.py:449] 2024-10-14 09:24:15,719 >> Dropping the following result as it does not have all the necessary fields: |
|
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} |
|
|
|
|