deryaerman commited on
Commit
0e344f5
ยท
1 Parent(s): 4c057cb

Add FLERT model files and update README with FLERT inference code

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,296 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ language:
4
+ - ar
5
+ - it
6
+ - de
7
+ - en
8
+ - hi
9
+ - fi
10
+ - fr
11
+ - tr
12
+ - es
13
+ - pt
14
+ - pl
15
+ base_model:
16
+ - jhu-clsp/mmBERT-base
17
+ pipeline_tag: token-classification
18
+ tags:
19
+ - ner
20
+ - pii
21
+ - de-identification
22
+ - multilingual
23
+ - modernbert
24
+ - crf
25
+ - flert
26
  ---
27
+
28
+ # Multilingual DialogPII NER
29
+
30
+ A fine-tuned [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) model with a CRF layer for **Personally Identifiable Information (PII) detection** in multilingual dialogues across 11 languages.
31
+
32
+ ## Model Description
33
+
34
+ This model performs token-level Named Entity Recognition (NER) to identify and classify PII entities in dialogue text. It was trained on synthetic multilingual de-identification of conversational data.
35
+
36
+ - **Architecture:** mmBERT-base (ModernBERT) + CRF head with FLERT context windowing
37
+ - **Training:** Fine-tuned on all 11 languages jointly (multilingual training) using FLERT-style document context
38
+ - **Loss:** Cross-Entropy
39
+ - **Hyperparameters:** lr=2e-05, batch_size=32, max_length=2048, dropout=0.1, epochs=10
40
+ - **Context window:** 2 sentences left + 2 sentences right, separated by `[SEP]` markers
41
+ - **Decoding:** Viterbi decoding via CRF layer
42
+
43
+ ## Supported Languages
44
+
45
+ | Code | Language |
46
+ |------|----------|
47
+ | AR | Arabic |
48
+ | DE | German |
49
+ | EN | English |
50
+ | FI | Finnish |
51
+ | FR | French |
52
+ | HI | Hindi |
53
+ | IT | Italian |
54
+ | PL | Polish |
55
+ | PT | Portuguese |
56
+ | SP | Spanish |
57
+ | TR | Turkish |
58
+
59
+ ## Entity Types
60
+
61
+ The model recognizes 19 PII entity types using BIO tagging:
62
+
63
+ | Entity | Description |
64
+ |--------|-------------|
65
+ | `PERSON` | Person names |
66
+ | `PERSON_EMAIL` | Email addresses |
67
+ | `PERSON_SOCIAL_RELATION` | Social relations (e.g., "my wife") |
68
+ | `ORG` | Organizations |
69
+ | `LOC_CITY` | Cities |
70
+ | `LOC_COUNTRY` | Countries |
71
+ | `LOC_STREET` | Street names |
72
+ | `LOC_ZIP` | ZIP/postal codes |
73
+ | `LOC_HOUSENUMBER` | House numbers |
74
+ | `LOC_OTHER` | Other locations |
75
+ | `DATETIME` | Dates and times |
76
+ | `DATETIME_AGE` | Ages |
77
+ | `CODE` | ID numbers, reference codes |
78
+ | `CODE_PHONE` | Phone numbers |
79
+ | `CODE_URL` | URLs |
80
+ | `PROFESSION` | Professions |
81
+ | `PRODUCT` | Product names |
82
+ | `QUANTITY` | Quantities |
83
+ | `MISC` | Miscellaneous PII |
84
+
85
+ ## Performance
86
+
87
+ Evaluated on held-out test sets per language (type-aware micro scores):
88
+
89
+ | Language | Lenient F1 | Lenient F2 | Exact F1 | Exact F2 |
90
+ |----------|-----------|-----------|---------|---------|
91
+ | AR | 80.76 | 76.66 | 76.99 | 73.08 |
92
+ | DE | 91.66 | 90.71 | 90.54 | 89.60 |
93
+ | EN | 93.68 | 92.70 | 91.66 | 90.70 |
94
+ | FI | 87.70 | 86.77 | 85.65 | 84.73 |
95
+ | FR | 87.26 | 85.89 | 83.68 | 82.36 |
96
+ | HI | 84.94 | 82.91 | 81.26 | 79.31 |
97
+ | IT | 90.03 | 88.19 | 87.14 | 85.35 |
98
+ | PL | 89.33 | 89.45 | 86.17 | 86.29 |
99
+ | PT | 90.30 | 89.15 | 88.81 | 87.68 |
100
+ | SP | 91.39 | 90.76 | 89.62 | 89.00 |
101
+ | TR | 85.53 | 84.72 | 82.06 | 81.27 |
102
+ | **AVG** | **88.42** | **87.08** | **85.78** | **84.49** |
103
+
104
+ ## Usage
105
+
106
+ This model uses a custom CRF architecture with FLERT-style context windowing and cannot be loaded directly with `AutoModelForTokenClassification`. You need to use the custom `ModernBertCRF` class.
107
+
108
+ ### Setup
109
+
110
+ ```python
111
+ import torch
112
+ import json
113
+ import re
114
+ import torch.nn as nn
115
+ import spacy
116
+ from transformers import AutoModel, AutoTokenizer
117
+ from torchcrf import CRF
118
+ from huggingface_hub import snapshot_download
119
+
120
+ class ModernBertCRF(nn.Module):
121
+ def __init__(self, base_model_name, num_labels, id2label, label2id):
122
+ super().__init__()
123
+ self.num_labels = num_labels
124
+ self.id2label = id2label
125
+ self.label2id = label2id
126
+ self.transformer = AutoModel.from_pretrained(base_model_name)
127
+ hidden_size = self.transformer.config.hidden_size
128
+ self.classifier = nn.Linear(hidden_size, num_labels)
129
+ self.dropout = nn.Dropout(0.1)
130
+ self.crf = CRF(num_labels, batch_first=True)
131
+
132
+ def forward(self, input_ids, attention_mask, labels=None, **kwargs):
133
+ kwargs.pop("token_type_ids", None)
134
+ outputs = self.transformer(input_ids=input_ids, attention_mask=attention_mask)
135
+ sequence_output = self.dropout(outputs.last_hidden_state)
136
+ emissions = self.classifier(sequence_output)
137
+ return {"logits": emissions}
138
+
139
+ def decode(self, emissions, mask):
140
+ return self.crf.decode(emissions, mask=mask)
141
+
142
+ # Load model
143
+ model_dir = snapshot_download("DFKI-SLT/multilingual_DialogPII_NER")
144
+
145
+ with open(f"{model_dir}/crf_config.json") as f:
146
+ config = json.load(f)
147
+
148
+ with open(f"{model_dir}/flert_config.json") as f:
149
+ flert_config = json.load(f)
150
+
151
+ model = ModernBertCRF(
152
+ base_model_name=config["base_model_name"],
153
+ num_labels=config["num_labels"],
154
+ id2label=config["id2label"],
155
+ label2id=config["label2id"],
156
+ )
157
+ model.load_state_dict(torch.load(f"{model_dir}/pytorch_model.bin", map_location="cpu"))
158
+ model.eval()
159
+
160
+ tokenizer = AutoTokenizer.from_pretrained(model_dir)
161
+ id2label = {int(k): v for k, v in config["id2label"].items()}
162
+
163
+ context_window = flert_config["context_window"] # 2
164
+ use_sep_marker = flert_config["context_sep_marker"] # True
165
+ ```
166
+
167
+ ### Preprocessing: Sentence Splitting
168
+
169
+ The model was trained using FLERT-style context windowing over **sentence-level** input. Each sentence is predicted with surrounding context sentences. For best results, split your input into sentences using [spaCy](https://spacy.io/) before inference.
170
+
171
+ ```python
172
+ nlp = spacy.blank("en") # use "de" for German, "xx" for multilingual
173
+ nlp.add_pipe("sentencizer")
174
+
175
+ def split_dialogue(text, nlp):
176
+ sentences = []
177
+ for line in text.strip().splitlines():
178
+ m = re.match(r"^(SPEAKER_\d+)\s*:\s*(.*)", line.strip())
179
+ if m:
180
+ speaker, rest = m.group(1), m.group(2)
181
+ sentences.append([speaker, ":"])
182
+ line = rest
183
+ if not line:
184
+ continue
185
+ doc = nlp(line)
186
+ for sent in doc.sents:
187
+ tokens = [tok.text for tok in sent if not tok.is_space]
188
+ if tokens:
189
+ sentences.append(tokens)
190
+ return sentences
191
+
192
+ # Example
193
+ raw = """SPEAKER_00: Hello, my name is Peter.
194
+ SPEAKER_01: Hello, my name is Peter as well. Okay, and where do you come from? I come from Chicago."""
195
+
196
+ sentences = split_dialogue(raw, nlp)
197
+ ```
198
+
199
+ ### Inference with FLERT Context Windowing
200
+
201
+ The key difference from standard token classification: each sentence is predicted within a window of surrounding context sentences, joined by `[SEP]` tokens. Only labels for the target sentence are extracted.
202
+
203
+ ```python
204
+ def predict_dialogue(sentences, model, tokenizer, id2label,
205
+ context_window=2, use_sep_marker=True, device="cpu"):
206
+ sep = tokenizer.sep_token
207
+ all_labels = []
208
+ for i, target_tokens in enumerate(sentences):
209
+ left = sentences[max(0, i - context_window):i]
210
+ right = sentences[i + 1:i + 1 + context_window]
211
+
212
+ flat_tokens = []
213
+ for s in left:
214
+ flat_tokens.extend(s)
215
+ if use_sep_marker and left:
216
+ flat_tokens.append(sep)
217
+
218
+ tgt_start = len(flat_tokens)
219
+ flat_tokens.extend(target_tokens)
220
+ tgt_end = len(flat_tokens)
221
+
222
+ if use_sep_marker and right:
223
+ flat_tokens.append(sep)
224
+ for s in right:
225
+ flat_tokens.extend(s)
226
+
227
+ enc = tokenizer(flat_tokens, is_split_into_words=True,
228
+ return_tensors="pt", truncation=False).to(device)
229
+ word_ids = enc.word_ids(batch_index=0)
230
+
231
+ with torch.no_grad():
232
+ emissions = model(**enc)["logits"]
233
+ mask = enc["attention_mask"].bool()
234
+ preds = model.decode(emissions, mask)[0]
235
+
236
+ word_labels = ["O"] * len(target_tokens)
237
+ seen = set()
238
+ for idx, wid in enumerate(word_ids):
239
+ if wid is None or wid in seen:
240
+ continue
241
+ seen.add(wid)
242
+ if tgt_start <= wid < tgt_end:
243
+ word_labels[wid - tgt_start] = id2label[preds[idx]]
244
+
245
+ all_labels.append(word_labels)
246
+ return all_labels
247
+
248
+
249
+ # Run prediction
250
+ results = predict_dialogue(sentences, model, tokenizer, id2label,
251
+ context_window=context_window,
252
+ use_sep_marker=use_sep_marker)
253
+
254
+ for sent_tokens, sent_labels in zip(sentences, results):
255
+ for token, label in zip(sent_tokens, sent_labels):
256
+ if label != "O":
257
+ print(f"{token:20s} -> {label}")
258
+ ```
259
+
260
+ ### Single-sentence inference
261
+
262
+ For isolated sentences without dialogue context, pass them with `context_window=0`:
263
+
264
+ ```python
265
+ tokens = ["My", "name", "is", "John", "Smith", "and", "I", "live", "in", "Berlin", "."]
266
+
267
+ results = predict_dialogue([tokens], model, tokenizer, id2label,
268
+ context_window=0, use_sep_marker=False)
269
+
270
+ for token, label in zip(tokens, results[0]):
271
+ if label != "O":
272
+ print(f"{token:20s} -> {label}")
273
+ ```
274
+
275
+ ## Training Data
276
+
277
+ The model was trained on synthetic multilingual dialogue data covering various domains (medical anamnesis, customer support, police reports, therapy sessions, etc.). The data was generated and annotated as part of a thesis project on multilingual PII de-identification.
278
+
279
+ ## Limitations
280
+
281
+ - Trained on synthetic dialogue data; performance on real-world data may vary
282
+ - Optimized for dialogue/conversational text; may underperform on formal documents
283
+ - Arabic and Hindi show lower performance compared to European languages
284
+ - Requires `pytorch-crf` package for inference
285
+
286
+ ## Citation
287
+
288
+ If you use this model, please cite:
289
+
290
+ ```
291
+ @mastersthesis{erman2026multilingual,
292
+ title={Multilingual De-Identification of Dialogue Data using Transformer-based NER},
293
+ author={Erman, Derya},
294
+ year={2026}
295
+ }
296
+ ```
crf_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name": "jhu-clsp/mmBERT-base",
3
+ "num_labels": 48,
4
+ "id2label": {
5
+ "0": "O",
6
+ "1": "B-CITY",
7
+ "2": "B-CODE",
8
+ "3": "B-CODE_PHONE",
9
+ "4": "B-CODE_URL",
10
+ "5": "B-DATETIME",
11
+ "6": "B-DATETIME_AGE",
12
+ "7": "B-DISEASE",
13
+ "8": "B-LOC_CITY",
14
+ "9": "B-LOC_COUNTRY",
15
+ "10": "B-LOC_DISTRICT",
16
+ "11": "B-LOC_HOUSENUMBER",
17
+ "12": "B-LOC_NAME",
18
+ "13": "B-LOC_OTHER",
19
+ "14": "B-LOC_STREET",
20
+ "15": "B-LOC_ZIP",
21
+ "16": "B-MISC",
22
+ "17": "B-NAME",
23
+ "18": "B-ORG",
24
+ "19": "B-PERSON",
25
+ "20": "B-PERSON_EMAIL",
26
+ "21": "B-PERSON_SOCIAL_RELATION",
27
+ "22": "B-PRODUCT",
28
+ "23": "B-PROFESSION",
29
+ "24": "B-QUANTITY",
30
+ "25": "I-CITY",
31
+ "26": "I-CODE",
32
+ "27": "I-CODE_PHONE",
33
+ "28": "I-DATETIME",
34
+ "29": "I-DATETIME_AGE",
35
+ "30": "I-DISEASE",
36
+ "31": "I-LOC_CITY",
37
+ "32": "I-LOC_COUNTRY",
38
+ "33": "I-LOC_DISTRICT",
39
+ "34": "I-LOC_HOUSENUMBER",
40
+ "35": "I-LOC_NAME",
41
+ "36": "I-LOC_OTHER",
42
+ "37": "I-LOC_STREET",
43
+ "38": "I-LOC_ZIP",
44
+ "39": "I-MISC",
45
+ "40": "I-NAME",
46
+ "41": "I-ORG",
47
+ "42": "I-PERSON",
48
+ "43": "I-PERSON_EMAIL",
49
+ "44": "I-PERSON_SOCIAL_RELATION",
50
+ "45": "I-PRODUCT",
51
+ "46": "I-PROFESSION",
52
+ "47": "I-QUANTITY"
53
+ },
54
+ "label2id": {
55
+ "O": 0,
56
+ "B-CITY": 1,
57
+ "B-CODE": 2,
58
+ "B-CODE_PHONE": 3,
59
+ "B-CODE_URL": 4,
60
+ "B-DATETIME": 5,
61
+ "B-DATETIME_AGE": 6,
62
+ "B-DISEASE": 7,
63
+ "B-LOC_CITY": 8,
64
+ "B-LOC_COUNTRY": 9,
65
+ "B-LOC_DISTRICT": 10,
66
+ "B-LOC_HOUSENUMBER": 11,
67
+ "B-LOC_NAME": 12,
68
+ "B-LOC_OTHER": 13,
69
+ "B-LOC_STREET": 14,
70
+ "B-LOC_ZIP": 15,
71
+ "B-MISC": 16,
72
+ "B-NAME": 17,
73
+ "B-ORG": 18,
74
+ "B-PERSON": 19,
75
+ "B-PERSON_EMAIL": 20,
76
+ "B-PERSON_SOCIAL_RELATION": 21,
77
+ "B-PRODUCT": 22,
78
+ "B-PROFESSION": 23,
79
+ "B-QUANTITY": 24,
80
+ "I-CITY": 25,
81
+ "I-CODE": 26,
82
+ "I-CODE_PHONE": 27,
83
+ "I-DATETIME": 28,
84
+ "I-DATETIME_AGE": 29,
85
+ "I-DISEASE": 30,
86
+ "I-LOC_CITY": 31,
87
+ "I-LOC_COUNTRY": 32,
88
+ "I-LOC_DISTRICT": 33,
89
+ "I-LOC_HOUSENUMBER": 34,
90
+ "I-LOC_NAME": 35,
91
+ "I-LOC_OTHER": 36,
92
+ "I-LOC_STREET": 37,
93
+ "I-LOC_ZIP": 38,
94
+ "I-MISC": 39,
95
+ "I-NAME": 40,
96
+ "I-ORG": 41,
97
+ "I-PERSON": 42,
98
+ "I-PERSON_EMAIL": 43,
99
+ "I-PERSON_SOCIAL_RELATION": 44,
100
+ "I-PRODUCT": 45,
101
+ "I-PROFESSION": 46,
102
+ "I-QUANTITY": 47
103
+ },
104
+ "use_crf": true
105
+ }
flert_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "use_flert": true,
3
+ "context_window": 2,
4
+ "context_sep_marker": true,
5
+ "context_left_only": false
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c238f753c9d909276486ce10b7f6f190734197092ad75ad0fc7c5aa944b10c6
3
+ size 1227978319
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<bos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "<eos>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "<eos>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f
3
+ size 34363188
tokenizer_config.json ADDED
@@ -0,0 +1,2018 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<eos>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<bos>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<2mass>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "6": {
53
+ "content": "[@BOS@]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "7": {
61
+ "content": "<unused0>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "8": {
69
+ "content": "<unused1>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "9": {
77
+ "content": "<unused2>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "10": {
85
+ "content": "<unused3>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "11": {
93
+ "content": "<unused4>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "12": {
101
+ "content": "<unused5>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "13": {
109
+ "content": "<unused6>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "14": {
117
+ "content": "<unused7>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "15": {
125
+ "content": "<unused8>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "16": {
133
+ "content": "<unused9>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "17": {
141
+ "content": "<unused10>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "18": {
149
+ "content": "<unused11>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "19": {
157
+ "content": "<unused12>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "20": {
165
+ "content": "<unused13>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "21": {
173
+ "content": "<unused14>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "22": {
181
+ "content": "<unused15>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "23": {
189
+ "content": "<unused16>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "24": {
197
+ "content": "<unused17>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "25": {
205
+ "content": "<unused18>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "26": {
213
+ "content": "<unused19>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "27": {
221
+ "content": "<unused20>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "28": {
229
+ "content": "<unused21>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "29": {
237
+ "content": "<unused22>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "30": {
245
+ "content": "<unused23>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "31": {
253
+ "content": "<unused24>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "32": {
261
+ "content": "<unused25>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "33": {
269
+ "content": "<unused26>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "34": {
277
+ "content": "<unused27>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "35": {
285
+ "content": "<unused28>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "36": {
293
+ "content": "<unused29>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "37": {
301
+ "content": "<unused30>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "38": {
309
+ "content": "<unused31>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "39": {
317
+ "content": "<unused32>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "40": {
325
+ "content": "<unused33>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "41": {
333
+ "content": "<unused34>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "42": {
341
+ "content": "<unused35>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "43": {
349
+ "content": "<unused36>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "44": {
357
+ "content": "<unused37>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "45": {
365
+ "content": "<unused38>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "46": {
373
+ "content": "<unused39>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "47": {
381
+ "content": "<unused40>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "48": {
389
+ "content": "<unused41>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "49": {
397
+ "content": "<unused42>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "50": {
405
+ "content": "<unused43>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "51": {
413
+ "content": "<unused44>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "52": {
421
+ "content": "<unused45>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "53": {
429
+ "content": "<unused46>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "54": {
437
+ "content": "<unused47>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "55": {
445
+ "content": "<unused48>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "56": {
453
+ "content": "<unused49>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "57": {
461
+ "content": "<unused50>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "58": {
469
+ "content": "<unused51>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "59": {
477
+ "content": "<unused52>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "60": {
485
+ "content": "<unused53>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "61": {
493
+ "content": "<unused54>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "62": {
501
+ "content": "<unused55>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "63": {
509
+ "content": "<unused56>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "64": {
517
+ "content": "<unused57>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "65": {
525
+ "content": "<unused58>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "66": {
533
+ "content": "<unused59>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "67": {
541
+ "content": "<unused60>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "68": {
549
+ "content": "<unused61>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "69": {
557
+ "content": "<unused62>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "70": {
565
+ "content": "<unused63>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "71": {
573
+ "content": "<unused64>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "72": {
581
+ "content": "<unused65>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "73": {
589
+ "content": "<unused66>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "74": {
597
+ "content": "<unused67>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "75": {
605
+ "content": "<unused68>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "76": {
613
+ "content": "<unused69>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "77": {
621
+ "content": "<unused70>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "78": {
629
+ "content": "<unused71>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "79": {
637
+ "content": "<unused72>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "80": {
645
+ "content": "<unused73>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "81": {
653
+ "content": "<unused74>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "82": {
661
+ "content": "<unused75>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "83": {
669
+ "content": "<unused76>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "84": {
677
+ "content": "<unused77>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "85": {
685
+ "content": "<unused78>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "86": {
693
+ "content": "<unused79>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "87": {
701
+ "content": "<unused80>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "88": {
709
+ "content": "<unused81>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "89": {
717
+ "content": "<unused82>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "90": {
725
+ "content": "<unused83>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "91": {
733
+ "content": "<unused84>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "92": {
741
+ "content": "<unused85>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "93": {
749
+ "content": "<unused86>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "94": {
757
+ "content": "<unused87>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "95": {
765
+ "content": "<unused88>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "96": {
773
+ "content": "<unused89>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "97": {
781
+ "content": "<unused90>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "98": {
789
+ "content": "<unused91>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "99": {
797
+ "content": "<unused92>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "100": {
805
+ "content": "<unused93>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "101": {
813
+ "content": "<unused94>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "102": {
821
+ "content": "<unused95>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ },
828
+ "103": {
829
+ "content": "<unused96>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "104": {
837
+ "content": "<unused97>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "105": {
845
+ "content": "<unused98>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ },
852
+ "106": {
853
+ "content": "<start_of_turn>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "107": {
861
+ "content": "<end_of_turn>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "108": {
869
+ "content": "\n",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": false
875
+ },
876
+ "109": {
877
+ "content": "\n\n",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": false
883
+ },
884
+ "110": {
885
+ "content": "\n\n\n",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": false
891
+ },
892
+ "111": {
893
+ "content": "\n\n\n\n",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": false
899
+ },
900
+ "112": {
901
+ "content": "\n\n\n\n\n",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": false
907
+ },
908
+ "113": {
909
+ "content": "\n\n\n\n\n\n",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": false
915
+ },
916
+ "114": {
917
+ "content": "\n\n\n\n\n\n\n",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": false
923
+ },
924
+ "115": {
925
+ "content": "\n\n\n\n\n\n\n\n",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": false
931
+ },
932
+ "116": {
933
+ "content": "\n\n\n\n\n\n\n\n\n",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": false
939
+ },
940
+ "117": {
941
+ "content": "\n\n\n\n\n\n\n\n\n\n",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": false
947
+ },
948
+ "118": {
949
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": false
955
+ },
956
+ "119": {
957
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": false
963
+ },
964
+ "120": {
965
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": false
971
+ },
972
+ "121": {
973
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": false
979
+ },
980
+ "122": {
981
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": false
987
+ },
988
+ "123": {
989
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": false
995
+ },
996
+ "124": {
997
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": false
1003
+ },
1004
+ "125": {
1005
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": false
1011
+ },
1012
+ "126": {
1013
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": false
1019
+ },
1020
+ "127": {
1021
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": false
1027
+ },
1028
+ "128": {
1029
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": false
1035
+ },
1036
+ "129": {
1037
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": false
1043
+ },
1044
+ "130": {
1045
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": false
1051
+ },
1052
+ "131": {
1053
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": false
1059
+ },
1060
+ "132": {
1061
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": false
1067
+ },
1068
+ "133": {
1069
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": false
1075
+ },
1076
+ "134": {
1077
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": false
1083
+ },
1084
+ "135": {
1085
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": false
1091
+ },
1092
+ "136": {
1093
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": false
1099
+ },
1100
+ "137": {
1101
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": false
1107
+ },
1108
+ "138": {
1109
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": false
1115
+ },
1116
+ "139": {
1117
+ "content": "โ–โ–",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": false
1123
+ },
1124
+ "140": {
1125
+ "content": "โ–โ–โ–",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": false
1131
+ },
1132
+ "141": {
1133
+ "content": "โ–โ–โ–โ–",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": false
1139
+ },
1140
+ "142": {
1141
+ "content": "โ–โ–โ–โ–โ–",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": false
1147
+ },
1148
+ "143": {
1149
+ "content": "โ–โ–โ–โ–โ–โ–",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": false
1155
+ },
1156
+ "144": {
1157
+ "content": "โ–โ–โ–โ–โ–โ–โ–",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": false
1163
+ },
1164
+ "145": {
1165
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": false
1171
+ },
1172
+ "146": {
1173
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": false
1179
+ },
1180
+ "147": {
1181
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": false
1187
+ },
1188
+ "148": {
1189
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": false
1195
+ },
1196
+ "149": {
1197
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": false
1203
+ },
1204
+ "150": {
1205
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": false
1211
+ },
1212
+ "151": {
1213
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": false
1219
+ },
1220
+ "152": {
1221
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": false
1227
+ },
1228
+ "153": {
1229
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": false
1235
+ },
1236
+ "154": {
1237
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": false
1243
+ },
1244
+ "155": {
1245
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": false
1251
+ },
1252
+ "156": {
1253
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": false
1259
+ },
1260
+ "157": {
1261
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": false
1267
+ },
1268
+ "158": {
1269
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": false
1275
+ },
1276
+ "159": {
1277
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": false
1283
+ },
1284
+ "160": {
1285
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": false
1291
+ },
1292
+ "161": {
1293
+ "content": "โ–โ–โ–๏ฟฝ๏ฟฝ๏ฟฝโ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": false
1299
+ },
1300
+ "162": {
1301
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": false
1307
+ },
1308
+ "163": {
1309
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": false
1315
+ },
1316
+ "164": {
1317
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": false
1323
+ },
1324
+ "165": {
1325
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": false
1331
+ },
1332
+ "166": {
1333
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": false
1339
+ },
1340
+ "167": {
1341
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": false
1347
+ },
1348
+ "168": {
1349
+ "content": "โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–โ–",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": false
1355
+ },
1356
+ "169": {
1357
+ "content": "<table>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": false
1363
+ },
1364
+ "170": {
1365
+ "content": "<caption>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": false
1371
+ },
1372
+ "171": {
1373
+ "content": "<thead>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": false
1379
+ },
1380
+ "172": {
1381
+ "content": "<tbody>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": false
1387
+ },
1388
+ "173": {
1389
+ "content": "<tfoot>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": false
1395
+ },
1396
+ "174": {
1397
+ "content": "<tr>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": false
1403
+ },
1404
+ "175": {
1405
+ "content": "<th>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": false
1411
+ },
1412
+ "176": {
1413
+ "content": "<td>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": false
1419
+ },
1420
+ "177": {
1421
+ "content": "</table>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": false
1427
+ },
1428
+ "178": {
1429
+ "content": "</caption>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": false
1435
+ },
1436
+ "179": {
1437
+ "content": "</thead>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": false
1443
+ },
1444
+ "180": {
1445
+ "content": "</tbody>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": false
1451
+ },
1452
+ "181": {
1453
+ "content": "</tfoot>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": false
1459
+ },
1460
+ "182": {
1461
+ "content": "</tr>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": false
1467
+ },
1468
+ "183": {
1469
+ "content": "</th>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": false
1475
+ },
1476
+ "184": {
1477
+ "content": "</td>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": false
1483
+ },
1484
+ "185": {
1485
+ "content": "<h1>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": false
1491
+ },
1492
+ "186": {
1493
+ "content": "<h2>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": false
1499
+ },
1500
+ "187": {
1501
+ "content": "<h3>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": false
1507
+ },
1508
+ "188": {
1509
+ "content": "<h4>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": false
1515
+ },
1516
+ "189": {
1517
+ "content": "<h5>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": false
1523
+ },
1524
+ "190": {
1525
+ "content": "<h6>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": false
1531
+ },
1532
+ "191": {
1533
+ "content": "<blockquote>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": false
1539
+ },
1540
+ "192": {
1541
+ "content": "</h1>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": false
1547
+ },
1548
+ "193": {
1549
+ "content": "</h2>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": false
1555
+ },
1556
+ "194": {
1557
+ "content": "</h3>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": false
1563
+ },
1564
+ "195": {
1565
+ "content": "</h4>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": false
1571
+ },
1572
+ "196": {
1573
+ "content": "</h5>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": false
1579
+ },
1580
+ "197": {
1581
+ "content": "</h6>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": false
1587
+ },
1588
+ "198": {
1589
+ "content": "</blockquote>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": false
1595
+ },
1596
+ "199": {
1597
+ "content": "<strong>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": false
1603
+ },
1604
+ "200": {
1605
+ "content": "<em>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": false
1611
+ },
1612
+ "201": {
1613
+ "content": "<b>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": false
1619
+ },
1620
+ "202": {
1621
+ "content": "<i>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": false
1627
+ },
1628
+ "203": {
1629
+ "content": "<u>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": false
1635
+ },
1636
+ "204": {
1637
+ "content": "<s>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": false
1643
+ },
1644
+ "205": {
1645
+ "content": "<sub>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": false
1651
+ },
1652
+ "206": {
1653
+ "content": "<sup>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": false
1659
+ },
1660
+ "207": {
1661
+ "content": "<code>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": false
1667
+ },
1668
+ "208": {
1669
+ "content": "</strong>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": false
1675
+ },
1676
+ "209": {
1677
+ "content": "</em>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": false
1683
+ },
1684
+ "210": {
1685
+ "content": "</b>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": false
1691
+ },
1692
+ "211": {
1693
+ "content": "</i>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": false
1699
+ },
1700
+ "212": {
1701
+ "content": "</u>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": false
1707
+ },
1708
+ "213": {
1709
+ "content": "</s>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": false
1715
+ },
1716
+ "214": {
1717
+ "content": "</sub>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": false
1723
+ },
1724
+ "215": {
1725
+ "content": "</sup>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": false
1731
+ },
1732
+ "216": {
1733
+ "content": "</code>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": false
1739
+ },
1740
+ "255968": {
1741
+ "content": "[toxicity=0]",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": false
1747
+ },
1748
+ "255969": {
1749
+ "content": "\t\t",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": false
1755
+ },
1756
+ "255970": {
1757
+ "content": "\t\t\t",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": false
1763
+ },
1764
+ "255971": {
1765
+ "content": "\t\t\t\t",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": false
1771
+ },
1772
+ "255972": {
1773
+ "content": "\t\t\t\t\t",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": false
1779
+ },
1780
+ "255973": {
1781
+ "content": "\t\t\t\t\t\t",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": false
1787
+ },
1788
+ "255974": {
1789
+ "content": "\t\t\t\t\t\t\t",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": false
1795
+ },
1796
+ "255975": {
1797
+ "content": "\t\t\t\t\t\t\t\t",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": false
1803
+ },
1804
+ "255976": {
1805
+ "content": "\t\t\t\t\t\t\t\t\t",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": false
1811
+ },
1812
+ "255977": {
1813
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": false
1819
+ },
1820
+ "255978": {
1821
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": false
1827
+ },
1828
+ "255979": {
1829
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": false
1835
+ },
1836
+ "255980": {
1837
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": false
1843
+ },
1844
+ "255981": {
1845
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": false
1851
+ },
1852
+ "255982": {
1853
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": false
1859
+ },
1860
+ "255983": {
1861
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": false
1867
+ },
1868
+ "255984": {
1869
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": false
1875
+ },
1876
+ "255985": {
1877
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": false
1883
+ },
1884
+ "255986": {
1885
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": false
1891
+ },
1892
+ "255987": {
1893
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": false
1899
+ },
1900
+ "255988": {
1901
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": false
1907
+ },
1908
+ "255989": {
1909
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": false
1915
+ },
1916
+ "255990": {
1917
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": false
1923
+ },
1924
+ "255991": {
1925
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": false
1931
+ },
1932
+ "255992": {
1933
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": false
1939
+ },
1940
+ "255993": {
1941
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": false
1947
+ },
1948
+ "255994": {
1949
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": false
1955
+ },
1956
+ "255995": {
1957
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": false
1963
+ },
1964
+ "255996": {
1965
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": false
1971
+ },
1972
+ "255997": {
1973
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": false
1979
+ },
1980
+ "255998": {
1981
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": false
1987
+ },
1988
+ "255999": {
1989
+ "content": "<unused99>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": false
1995
+ }
1996
+ },
1997
+ "additional_special_tokens": [
1998
+ "<start_of_turn>",
1999
+ "<end_of_turn>"
2000
+ ],
2001
+ "bos_token": "<bos>",
2002
+ "clean_up_tokenization_spaces": false,
2003
+ "cls_token": "<bos>",
2004
+ "eos_token": "<eos>",
2005
+ "extra_special_tokens": {},
2006
+ "mask_token": "<mask>",
2007
+ "model_input_names": [
2008
+ "input_ids",
2009
+ "attention_mask"
2010
+ ],
2011
+ "model_max_length": 8192,
2012
+ "pad_token": "<pad>",
2013
+ "padding_side": "right",
2014
+ "sep_token": "<eos>",
2015
+ "spaces_between_special_tokens": false,
2016
+ "tokenizer_class": "PreTrainedTokenizerFast",
2017
+ "unk_token": "<unk>"
2018
+ }