lukmanaj commited on
Commit
deda80d
1 Parent(s): da6f41d

Upload tokenizer

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 ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
added_tokens.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__ace_Latn__": 256002,
3
+ "__ace__": 256001,
4
+ "__acm__": 256003,
5
+ "__acq__": 256004,
6
+ "__aeb__": 256005,
7
+ "__afr__": 256006,
8
+ "__ajp__": 256007,
9
+ "__aka__": 256008,
10
+ "__als__": 256162,
11
+ "__amh__": 256009,
12
+ "__apc__": 256010,
13
+ "__arb__": 256011,
14
+ "__ars__": 256012,
15
+ "__ary__": 256013,
16
+ "__arz__": 256014,
17
+ "__asm__": 256015,
18
+ "__ast__": 256016,
19
+ "__awa__": 256017,
20
+ "__ayr__": 256018,
21
+ "__azb__": 256019,
22
+ "__azj__": 256020,
23
+ "__bak__": 256021,
24
+ "__bam__": 256022,
25
+ "__ban__": 256023,
26
+ "__bel__": 256024,
27
+ "__bem__": 256025,
28
+ "__ben__": 256026,
29
+ "__bho__": 256027,
30
+ "__bjn_Latn__": 256029,
31
+ "__bjn__": 256028,
32
+ "__bod__": 256030,
33
+ "__bos__": 256031,
34
+ "__bug__": 256032,
35
+ "__bul__": 256033,
36
+ "__cat__": 256034,
37
+ "__ceb__": 256035,
38
+ "__ces__": 256036,
39
+ "__cjk__": 256037,
40
+ "__ckb__": 256038,
41
+ "__cmn_Hant__": 256201,
42
+ "__cmn__": 256200,
43
+ "__crh__": 256039,
44
+ "__cym__": 256040,
45
+ "__dan__": 256041,
46
+ "__deu__": 256042,
47
+ "__dik__": 256043,
48
+ "__dyu__": 256044,
49
+ "__dzo__": 256045,
50
+ "__ell__": 256046,
51
+ "__eng__": 256047,
52
+ "__epo__": 256048,
53
+ "__est__": 256049,
54
+ "__eus__": 256050,
55
+ "__ewe__": 256051,
56
+ "__fao__": 256052,
57
+ "__fij__": 256054,
58
+ "__fin__": 256055,
59
+ "__fon__": 256056,
60
+ "__fra__": 256057,
61
+ "__fur__": 256058,
62
+ "__fuv__": 256059,
63
+ "__gaz__": 256135,
64
+ "__gla__": 256060,
65
+ "__gle__": 256061,
66
+ "__glg__": 256062,
67
+ "__grn__": 256063,
68
+ "__guj__": 256064,
69
+ "__hat__": 256065,
70
+ "__hau__": 256066,
71
+ "__heb__": 256067,
72
+ "__hin__": 256068,
73
+ "__hne__": 256069,
74
+ "__hrv__": 256070,
75
+ "__hun__": 256071,
76
+ "__hye__": 256072,
77
+ "__ibo__": 256073,
78
+ "__ilo__": 256074,
79
+ "__ind__": 256075,
80
+ "__isl__": 256076,
81
+ "__ita__": 256077,
82
+ "__jav__": 256078,
83
+ "__jpn__": 256079,
84
+ "__kab__": 256080,
85
+ "__kac__": 256081,
86
+ "__kam__": 256082,
87
+ "__kan__": 256083,
88
+ "__kas_Deva__": 256085,
89
+ "__kas__": 256084,
90
+ "__kat__": 256086,
91
+ "__kaz__": 256089,
92
+ "__kbp__": 256090,
93
+ "__kea__": 256091,
94
+ "__khk__": 256122,
95
+ "__khm__": 256092,
96
+ "__kik__": 256093,
97
+ "__kin__": 256094,
98
+ "__kir__": 256095,
99
+ "__kmb__": 256096,
100
+ "__kmr__": 256099,
101
+ "__knc_Latn__": 256088,
102
+ "__knc__": 256087,
103
+ "__kon__": 256097,
104
+ "__kor__": 256098,
105
+ "__lao__": 256100,
106
+ "__lij__": 256102,
107
+ "__lim__": 256103,
108
+ "__lin__": 256104,
109
+ "__lit__": 256105,
110
+ "__lmo__": 256106,
111
+ "__ltg__": 256107,
112
+ "__ltz__": 256108,
113
+ "__lua__": 256109,
114
+ "__lug__": 256110,
115
+ "__luo__": 256111,
116
+ "__lus__": 256112,
117
+ "__lvs__": 256101,
118
+ "__mag__": 256113,
119
+ "__mai__": 256114,
120
+ "__mal__": 256115,
121
+ "__mar__": 256116,
122
+ "__min__": 256117,
123
+ "__mkd__": 256118,
124
+ "__mlt__": 256120,
125
+ "__mni__": 256121,
126
+ "__mos__": 256123,
127
+ "__mri__": 256124,
128
+ "__mya__": 256126,
129
+ "__nld__": 256127,
130
+ "__nno__": 256128,
131
+ "__nob__": 256129,
132
+ "__npi__": 256130,
133
+ "__nso__": 256131,
134
+ "__nus__": 256132,
135
+ "__nya__": 256133,
136
+ "__oci__": 256134,
137
+ "__ory__": 256136,
138
+ "__pag__": 256137,
139
+ "__pan__": 256138,
140
+ "__pap__": 256139,
141
+ "__pbt__": 256143,
142
+ "__pes__": 256053,
143
+ "__plt__": 256119,
144
+ "__pol__": 256140,
145
+ "__por__": 256141,
146
+ "__prs__": 256142,
147
+ "__quy__": 256144,
148
+ "__ron__": 256145,
149
+ "__run__": 256146,
150
+ "__rus__": 256147,
151
+ "__sag__": 256148,
152
+ "__san__": 256149,
153
+ "__sat__": 256150,
154
+ "__scn__": 256151,
155
+ "__shn__": 256152,
156
+ "__sin__": 256153,
157
+ "__slk__": 256154,
158
+ "__slv__": 256155,
159
+ "__smo__": 256156,
160
+ "__sna__": 256157,
161
+ "__snd__": 256158,
162
+ "__som__": 256159,
163
+ "__sot__": 256160,
164
+ "__spa__": 256161,
165
+ "__srd__": 256163,
166
+ "__srp__": 256164,
167
+ "__ssw__": 256165,
168
+ "__sun__": 256166,
169
+ "__swe__": 256167,
170
+ "__swh__": 256168,
171
+ "__szl__": 256169,
172
+ "__tam__": 256170,
173
+ "__taq_Tfng__": 256178,
174
+ "__taq__": 256177,
175
+ "__tat__": 256171,
176
+ "__tel__": 256172,
177
+ "__tgk__": 256173,
178
+ "__tgl__": 256174,
179
+ "__tha__": 256175,
180
+ "__tir__": 256176,
181
+ "__tpi__": 256179,
182
+ "__tsn__": 256180,
183
+ "__tso__": 256181,
184
+ "__tuk__": 256182,
185
+ "__tum__": 256183,
186
+ "__tur__": 256184,
187
+ "__twi__": 256185,
188
+ "__tzm__": 256186,
189
+ "__uig__": 256187,
190
+ "__ukr__": 256188,
191
+ "__umb__": 256189,
192
+ "__urd__": 256190,
193
+ "__uzn__": 256191,
194
+ "__vec__": 256192,
195
+ "__vie__": 256193,
196
+ "__war__": 256194,
197
+ "__wol__": 256195,
198
+ "__xho__": 256196,
199
+ "__ydd__": 256197,
200
+ "__yor__": 256198,
201
+ "__yue__": 256199,
202
+ "__zsm__": 256125,
203
+ "__zul__": 256202
204
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
special_tokens_map.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "<unk>",
5
+ "<s>",
6
+ "</s>",
7
+ "__ace__",
8
+ "__ace_Latn__",
9
+ "__acm__",
10
+ "__acq__",
11
+ "__aeb__",
12
+ "__afr__",
13
+ "__ajp__",
14
+ "__aka__",
15
+ "__amh__",
16
+ "__apc__",
17
+ "__arb__",
18
+ "__ars__",
19
+ "__ary__",
20
+ "__arz__",
21
+ "__asm__",
22
+ "__ast__",
23
+ "__awa__",
24
+ "__ayr__",
25
+ "__azb__",
26
+ "__azj__",
27
+ "__bak__",
28
+ "__bam__",
29
+ "__ban__",
30
+ "__bel__",
31
+ "__bem__",
32
+ "__ben__",
33
+ "__bho__",
34
+ "__bjn__",
35
+ "__bjn_Latn__",
36
+ "__bod__",
37
+ "__bos__",
38
+ "__bug__",
39
+ "__bul__",
40
+ "__cat__",
41
+ "__ceb__",
42
+ "__ces__",
43
+ "__cjk__",
44
+ "__ckb__",
45
+ "__crh__",
46
+ "__cym__",
47
+ "__dan__",
48
+ "__deu__",
49
+ "__dik__",
50
+ "__dyu__",
51
+ "__dzo__",
52
+ "__ell__",
53
+ "__eng__",
54
+ "__epo__",
55
+ "__est__",
56
+ "__eus__",
57
+ "__ewe__",
58
+ "__fao__",
59
+ "__pes__",
60
+ "__fij__",
61
+ "__fin__",
62
+ "__fon__",
63
+ "__fra__",
64
+ "__fur__",
65
+ "__fuv__",
66
+ "__gla__",
67
+ "__gle__",
68
+ "__glg__",
69
+ "__grn__",
70
+ "__guj__",
71
+ "__hat__",
72
+ "__hau__",
73
+ "__heb__",
74
+ "__hin__",
75
+ "__hne__",
76
+ "__hrv__",
77
+ "__hun__",
78
+ "__hye__",
79
+ "__ibo__",
80
+ "__ilo__",
81
+ "__ind__",
82
+ "__isl__",
83
+ "__ita__",
84
+ "__jav__",
85
+ "__jpn__",
86
+ "__kab__",
87
+ "__kac__",
88
+ "__kam__",
89
+ "__kan__",
90
+ "__kas__",
91
+ "__kas_Deva__",
92
+ "__kat__",
93
+ "__knc__",
94
+ "__knc_Latn__",
95
+ "__kaz__",
96
+ "__kbp__",
97
+ "__kea__",
98
+ "__khm__",
99
+ "__kik__",
100
+ "__kin__",
101
+ "__kir__",
102
+ "__kmb__",
103
+ "__kon__",
104
+ "__kor__",
105
+ "__kmr__",
106
+ "__lao__",
107
+ "__lvs__",
108
+ "__lij__",
109
+ "__lim__",
110
+ "__lin__",
111
+ "__lit__",
112
+ "__lmo__",
113
+ "__ltg__",
114
+ "__ltz__",
115
+ "__lua__",
116
+ "__lug__",
117
+ "__luo__",
118
+ "__lus__",
119
+ "__mag__",
120
+ "__mai__",
121
+ "__mal__",
122
+ "__mar__",
123
+ "__min__",
124
+ "__mkd__",
125
+ "__plt__",
126
+ "__mlt__",
127
+ "__mni__",
128
+ "__khk__",
129
+ "__mos__",
130
+ "__mri__",
131
+ "__zsm__",
132
+ "__mya__",
133
+ "__nld__",
134
+ "__nno__",
135
+ "__nob__",
136
+ "__npi__",
137
+ "__nso__",
138
+ "__nus__",
139
+ "__nya__",
140
+ "__oci__",
141
+ "__gaz__",
142
+ "__ory__",
143
+ "__pag__",
144
+ "__pan__",
145
+ "__pap__",
146
+ "__pol__",
147
+ "__por__",
148
+ "__prs__",
149
+ "__pbt__",
150
+ "__quy__",
151
+ "__ron__",
152
+ "__run__",
153
+ "__rus__",
154
+ "__sag__",
155
+ "__san__",
156
+ "__sat__",
157
+ "__scn__",
158
+ "__shn__",
159
+ "__sin__",
160
+ "__slk__",
161
+ "__slv__",
162
+ "__smo__",
163
+ "__sna__",
164
+ "__snd__",
165
+ "__som__",
166
+ "__sot__",
167
+ "__spa__",
168
+ "__als__",
169
+ "__srd__",
170
+ "__srp__",
171
+ "__ssw__",
172
+ "__sun__",
173
+ "__swe__",
174
+ "__swh__",
175
+ "__szl__",
176
+ "__tam__",
177
+ "__tat__",
178
+ "__tel__",
179
+ "__tgk__",
180
+ "__tgl__",
181
+ "__tha__",
182
+ "__tir__",
183
+ "__taq__",
184
+ "__taq_Tfng__",
185
+ "__tpi__",
186
+ "__tsn__",
187
+ "__tso__",
188
+ "__tuk__",
189
+ "__tum__",
190
+ "__tur__",
191
+ "__twi__",
192
+ "__tzm__",
193
+ "__uig__",
194
+ "__ukr__",
195
+ "__umb__",
196
+ "__urd__",
197
+ "__uzn__",
198
+ "__vec__",
199
+ "__vie__",
200
+ "__war__",
201
+ "__wol__",
202
+ "__xho__",
203
+ "__ydd__",
204
+ "__yor__",
205
+ "__yue__",
206
+ "__cmn__",
207
+ "__cmn_Hant__",
208
+ "__zul__"
209
+ ],
210
+ "bos_token": {
211
+ "content": "<s>",
212
+ "lstrip": false,
213
+ "normalized": false,
214
+ "rstrip": false,
215
+ "single_word": false
216
+ },
217
+ "cls_token": {
218
+ "content": "<s>",
219
+ "lstrip": false,
220
+ "normalized": false,
221
+ "rstrip": false,
222
+ "single_word": false
223
+ },
224
+ "eos_token": {
225
+ "content": "</s>",
226
+ "lstrip": false,
227
+ "normalized": false,
228
+ "rstrip": false,
229
+ "single_word": false
230
+ },
231
+ "pad_token": {
232
+ "content": "<pad>",
233
+ "lstrip": false,
234
+ "normalized": false,
235
+ "rstrip": false,
236
+ "single_word": false
237
+ },
238
+ "sep_token": {
239
+ "content": "</s>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false
244
+ },
245
+ "unk_token": {
246
+ "content": "<unk>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false
251
+ }
252
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78425cf90ead1727ae32918d37b6bca8ef9cc0c3c7360d8d7eb335fbdd6d6c2
3
+ size 17325817
tokenizer_config.json ADDED
@@ -0,0 +1,1881 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": 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": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "</s>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "256001": {
37
+ "content": "__ace__",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "256002": {
45
+ "content": "__ace_Latn__",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "256003": {
53
+ "content": "__acm__",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "256004": {
61
+ "content": "__acq__",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "256005": {
69
+ "content": "__aeb__",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "256006": {
77
+ "content": "__afr__",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "256007": {
85
+ "content": "__ajp__",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "256008": {
93
+ "content": "__aka__",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "256009": {
101
+ "content": "__amh__",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "256010": {
109
+ "content": "__apc__",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "256011": {
117
+ "content": "__arb__",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "256012": {
125
+ "content": "__ars__",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "256013": {
133
+ "content": "__ary__",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "256014": {
141
+ "content": "__arz__",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "256015": {
149
+ "content": "__asm__",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "256016": {
157
+ "content": "__ast__",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "256017": {
165
+ "content": "__awa__",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "256018": {
173
+ "content": "__ayr__",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "256019": {
181
+ "content": "__azb__",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "256020": {
189
+ "content": "__azj__",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "256021": {
197
+ "content": "__bak__",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "256022": {
205
+ "content": "__bam__",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "256023": {
213
+ "content": "__ban__",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "256024": {
221
+ "content": "__bel__",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "256025": {
229
+ "content": "__bem__",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "256026": {
237
+ "content": "__ben__",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "256027": {
245
+ "content": "__bho__",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "256028": {
253
+ "content": "__bjn__",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "256029": {
261
+ "content": "__bjn_Latn__",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "256030": {
269
+ "content": "__bod__",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "256031": {
277
+ "content": "__bos__",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "256032": {
285
+ "content": "__bug__",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "256033": {
293
+ "content": "__bul__",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "256034": {
301
+ "content": "__cat__",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "256035": {
309
+ "content": "__ceb__",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "256036": {
317
+ "content": "__ces__",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "256037": {
325
+ "content": "__cjk__",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "256038": {
333
+ "content": "__ckb__",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "256039": {
341
+ "content": "__crh__",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "256040": {
349
+ "content": "__cym__",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "256041": {
357
+ "content": "__dan__",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "256042": {
365
+ "content": "__deu__",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "256043": {
373
+ "content": "__dik__",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "256044": {
381
+ "content": "__dyu__",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "256045": {
389
+ "content": "__dzo__",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "256046": {
397
+ "content": "__ell__",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "256047": {
405
+ "content": "__eng__",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "256048": {
413
+ "content": "__epo__",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "256049": {
421
+ "content": "__est__",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "256050": {
429
+ "content": "__eus__",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "256051": {
437
+ "content": "__ewe__",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "256052": {
445
+ "content": "__fao__",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "256053": {
453
+ "content": "__pes__",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "256054": {
461
+ "content": "__fij__",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "256055": {
469
+ "content": "__fin__",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "256056": {
477
+ "content": "__fon__",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "256057": {
485
+ "content": "__fra__",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "256058": {
493
+ "content": "__fur__",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "256059": {
501
+ "content": "__fuv__",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "256060": {
509
+ "content": "__gla__",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "256061": {
517
+ "content": "__gle__",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "256062": {
525
+ "content": "__glg__",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "256063": {
533
+ "content": "__grn__",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "256064": {
541
+ "content": "__guj__",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "256065": {
549
+ "content": "__hat__",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "256066": {
557
+ "content": "__hau__",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "256067": {
565
+ "content": "__heb__",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "256068": {
573
+ "content": "__hin__",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "256069": {
581
+ "content": "__hne__",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "256070": {
589
+ "content": "__hrv__",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "256071": {
597
+ "content": "__hun__",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "256072": {
605
+ "content": "__hye__",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "256073": {
613
+ "content": "__ibo__",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "256074": {
621
+ "content": "__ilo__",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "256075": {
629
+ "content": "__ind__",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "256076": {
637
+ "content": "__isl__",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "256077": {
645
+ "content": "__ita__",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "256078": {
653
+ "content": "__jav__",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "256079": {
661
+ "content": "__jpn__",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "256080": {
669
+ "content": "__kab__",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "256081": {
677
+ "content": "__kac__",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "256082": {
685
+ "content": "__kam__",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "256083": {
693
+ "content": "__kan__",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "256084": {
701
+ "content": "__kas__",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "256085": {
709
+ "content": "__kas_Deva__",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "256086": {
717
+ "content": "__kat__",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "256087": {
725
+ "content": "__knc__",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "256088": {
733
+ "content": "__knc_Latn__",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "256089": {
741
+ "content": "__kaz__",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "256090": {
749
+ "content": "__kbp__",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "256091": {
757
+ "content": "__kea__",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "256092": {
765
+ "content": "__khm__",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "256093": {
773
+ "content": "__kik__",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "256094": {
781
+ "content": "__kin__",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "256095": {
789
+ "content": "__kir__",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "256096": {
797
+ "content": "__kmb__",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "256097": {
805
+ "content": "__kon__",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "256098": {
813
+ "content": "__kor__",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "256099": {
821
+ "content": "__kmr__",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "256100": {
829
+ "content": "__lao__",
830
+ "lstrip": true,
831
+ "normalized": false,
832
+ "rstrip": true,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "256101": {
837
+ "content": "__lvs__",
838
+ "lstrip": true,
839
+ "normalized": false,
840
+ "rstrip": true,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "256102": {
845
+ "content": "__lij__",
846
+ "lstrip": true,
847
+ "normalized": false,
848
+ "rstrip": true,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "256103": {
853
+ "content": "__lim__",
854
+ "lstrip": true,
855
+ "normalized": false,
856
+ "rstrip": true,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "256104": {
861
+ "content": "__lin__",
862
+ "lstrip": true,
863
+ "normalized": false,
864
+ "rstrip": true,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "256105": {
869
+ "content": "__lit__",
870
+ "lstrip": true,
871
+ "normalized": false,
872
+ "rstrip": true,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "256106": {
877
+ "content": "__lmo__",
878
+ "lstrip": true,
879
+ "normalized": false,
880
+ "rstrip": true,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "256107": {
885
+ "content": "__ltg__",
886
+ "lstrip": true,
887
+ "normalized": false,
888
+ "rstrip": true,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "256108": {
893
+ "content": "__ltz__",
894
+ "lstrip": true,
895
+ "normalized": false,
896
+ "rstrip": true,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "256109": {
901
+ "content": "__lua__",
902
+ "lstrip": true,
903
+ "normalized": false,
904
+ "rstrip": true,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "256110": {
909
+ "content": "__lug__",
910
+ "lstrip": true,
911
+ "normalized": false,
912
+ "rstrip": true,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "256111": {
917
+ "content": "__luo__",
918
+ "lstrip": true,
919
+ "normalized": false,
920
+ "rstrip": true,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "256112": {
925
+ "content": "__lus__",
926
+ "lstrip": true,
927
+ "normalized": false,
928
+ "rstrip": true,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "256113": {
933
+ "content": "__mag__",
934
+ "lstrip": true,
935
+ "normalized": false,
936
+ "rstrip": true,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "256114": {
941
+ "content": "__mai__",
942
+ "lstrip": true,
943
+ "normalized": false,
944
+ "rstrip": true,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "256115": {
949
+ "content": "__mal__",
950
+ "lstrip": true,
951
+ "normalized": false,
952
+ "rstrip": true,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "256116": {
957
+ "content": "__mar__",
958
+ "lstrip": true,
959
+ "normalized": false,
960
+ "rstrip": true,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "256117": {
965
+ "content": "__min__",
966
+ "lstrip": true,
967
+ "normalized": false,
968
+ "rstrip": true,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "256118": {
973
+ "content": "__mkd__",
974
+ "lstrip": true,
975
+ "normalized": false,
976
+ "rstrip": true,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "256119": {
981
+ "content": "__plt__",
982
+ "lstrip": true,
983
+ "normalized": false,
984
+ "rstrip": true,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "256120": {
989
+ "content": "__mlt__",
990
+ "lstrip": true,
991
+ "normalized": false,
992
+ "rstrip": true,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "256121": {
997
+ "content": "__mni__",
998
+ "lstrip": true,
999
+ "normalized": false,
1000
+ "rstrip": true,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "256122": {
1005
+ "content": "__khk__",
1006
+ "lstrip": true,
1007
+ "normalized": false,
1008
+ "rstrip": true,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "256123": {
1013
+ "content": "__mos__",
1014
+ "lstrip": true,
1015
+ "normalized": false,
1016
+ "rstrip": true,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "256124": {
1021
+ "content": "__mri__",
1022
+ "lstrip": true,
1023
+ "normalized": false,
1024
+ "rstrip": true,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "256125": {
1029
+ "content": "__zsm__",
1030
+ "lstrip": true,
1031
+ "normalized": false,
1032
+ "rstrip": true,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "256126": {
1037
+ "content": "__mya__",
1038
+ "lstrip": true,
1039
+ "normalized": false,
1040
+ "rstrip": true,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "256127": {
1045
+ "content": "__nld__",
1046
+ "lstrip": true,
1047
+ "normalized": false,
1048
+ "rstrip": true,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "256128": {
1053
+ "content": "__nno__",
1054
+ "lstrip": true,
1055
+ "normalized": false,
1056
+ "rstrip": true,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "256129": {
1061
+ "content": "__nob__",
1062
+ "lstrip": true,
1063
+ "normalized": false,
1064
+ "rstrip": true,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "256130": {
1069
+ "content": "__npi__",
1070
+ "lstrip": true,
1071
+ "normalized": false,
1072
+ "rstrip": true,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "256131": {
1077
+ "content": "__nso__",
1078
+ "lstrip": true,
1079
+ "normalized": false,
1080
+ "rstrip": true,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "256132": {
1085
+ "content": "__nus__",
1086
+ "lstrip": true,
1087
+ "normalized": false,
1088
+ "rstrip": true,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "256133": {
1093
+ "content": "__nya__",
1094
+ "lstrip": true,
1095
+ "normalized": false,
1096
+ "rstrip": true,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "256134": {
1101
+ "content": "__oci__",
1102
+ "lstrip": true,
1103
+ "normalized": false,
1104
+ "rstrip": true,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "256135": {
1109
+ "content": "__gaz__",
1110
+ "lstrip": true,
1111
+ "normalized": false,
1112
+ "rstrip": true,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "256136": {
1117
+ "content": "__ory__",
1118
+ "lstrip": true,
1119
+ "normalized": false,
1120
+ "rstrip": true,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "256137": {
1125
+ "content": "__pag__",
1126
+ "lstrip": true,
1127
+ "normalized": false,
1128
+ "rstrip": true,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "256138": {
1133
+ "content": "__pan__",
1134
+ "lstrip": true,
1135
+ "normalized": false,
1136
+ "rstrip": true,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "256139": {
1141
+ "content": "__pap__",
1142
+ "lstrip": true,
1143
+ "normalized": false,
1144
+ "rstrip": true,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "256140": {
1149
+ "content": "__pol__",
1150
+ "lstrip": true,
1151
+ "normalized": false,
1152
+ "rstrip": true,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "256141": {
1157
+ "content": "__por__",
1158
+ "lstrip": true,
1159
+ "normalized": false,
1160
+ "rstrip": true,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "256142": {
1165
+ "content": "__prs__",
1166
+ "lstrip": true,
1167
+ "normalized": false,
1168
+ "rstrip": true,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "256143": {
1173
+ "content": "__pbt__",
1174
+ "lstrip": true,
1175
+ "normalized": false,
1176
+ "rstrip": true,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "256144": {
1181
+ "content": "__quy__",
1182
+ "lstrip": true,
1183
+ "normalized": false,
1184
+ "rstrip": true,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "256145": {
1189
+ "content": "__ron__",
1190
+ "lstrip": true,
1191
+ "normalized": false,
1192
+ "rstrip": true,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "256146": {
1197
+ "content": "__run__",
1198
+ "lstrip": true,
1199
+ "normalized": false,
1200
+ "rstrip": true,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "256147": {
1205
+ "content": "__rus__",
1206
+ "lstrip": true,
1207
+ "normalized": false,
1208
+ "rstrip": true,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "256148": {
1213
+ "content": "__sag__",
1214
+ "lstrip": true,
1215
+ "normalized": false,
1216
+ "rstrip": true,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "256149": {
1221
+ "content": "__san__",
1222
+ "lstrip": true,
1223
+ "normalized": false,
1224
+ "rstrip": true,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "256150": {
1229
+ "content": "__sat__",
1230
+ "lstrip": true,
1231
+ "normalized": false,
1232
+ "rstrip": true,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "256151": {
1237
+ "content": "__scn__",
1238
+ "lstrip": true,
1239
+ "normalized": false,
1240
+ "rstrip": true,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "256152": {
1245
+ "content": "__shn__",
1246
+ "lstrip": true,
1247
+ "normalized": false,
1248
+ "rstrip": true,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "256153": {
1253
+ "content": "__sin__",
1254
+ "lstrip": true,
1255
+ "normalized": false,
1256
+ "rstrip": true,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "256154": {
1261
+ "content": "__slk__",
1262
+ "lstrip": true,
1263
+ "normalized": false,
1264
+ "rstrip": true,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "256155": {
1269
+ "content": "__slv__",
1270
+ "lstrip": true,
1271
+ "normalized": false,
1272
+ "rstrip": true,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "256156": {
1277
+ "content": "__smo__",
1278
+ "lstrip": true,
1279
+ "normalized": false,
1280
+ "rstrip": true,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "256157": {
1285
+ "content": "__sna__",
1286
+ "lstrip": true,
1287
+ "normalized": false,
1288
+ "rstrip": true,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "256158": {
1293
+ "content": "__snd__",
1294
+ "lstrip": true,
1295
+ "normalized": false,
1296
+ "rstrip": true,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "256159": {
1301
+ "content": "__som__",
1302
+ "lstrip": true,
1303
+ "normalized": false,
1304
+ "rstrip": true,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "256160": {
1309
+ "content": "__sot__",
1310
+ "lstrip": true,
1311
+ "normalized": false,
1312
+ "rstrip": true,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "256161": {
1317
+ "content": "__spa__",
1318
+ "lstrip": true,
1319
+ "normalized": false,
1320
+ "rstrip": true,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "256162": {
1325
+ "content": "__als__",
1326
+ "lstrip": true,
1327
+ "normalized": false,
1328
+ "rstrip": true,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "256163": {
1333
+ "content": "__srd__",
1334
+ "lstrip": true,
1335
+ "normalized": false,
1336
+ "rstrip": true,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "256164": {
1341
+ "content": "__srp__",
1342
+ "lstrip": true,
1343
+ "normalized": false,
1344
+ "rstrip": true,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "256165": {
1349
+ "content": "__ssw__",
1350
+ "lstrip": true,
1351
+ "normalized": false,
1352
+ "rstrip": true,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "256166": {
1357
+ "content": "__sun__",
1358
+ "lstrip": true,
1359
+ "normalized": false,
1360
+ "rstrip": true,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "256167": {
1365
+ "content": "__swe__",
1366
+ "lstrip": true,
1367
+ "normalized": false,
1368
+ "rstrip": true,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "256168": {
1373
+ "content": "__swh__",
1374
+ "lstrip": true,
1375
+ "normalized": false,
1376
+ "rstrip": true,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "256169": {
1381
+ "content": "__szl__",
1382
+ "lstrip": true,
1383
+ "normalized": false,
1384
+ "rstrip": true,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "256170": {
1389
+ "content": "__tam__",
1390
+ "lstrip": true,
1391
+ "normalized": false,
1392
+ "rstrip": true,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "256171": {
1397
+ "content": "__tat__",
1398
+ "lstrip": true,
1399
+ "normalized": false,
1400
+ "rstrip": true,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "256172": {
1405
+ "content": "__tel__",
1406
+ "lstrip": true,
1407
+ "normalized": false,
1408
+ "rstrip": true,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "256173": {
1413
+ "content": "__tgk__",
1414
+ "lstrip": true,
1415
+ "normalized": false,
1416
+ "rstrip": true,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "256174": {
1421
+ "content": "__tgl__",
1422
+ "lstrip": true,
1423
+ "normalized": false,
1424
+ "rstrip": true,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "256175": {
1429
+ "content": "__tha__",
1430
+ "lstrip": true,
1431
+ "normalized": false,
1432
+ "rstrip": true,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "256176": {
1437
+ "content": "__tir__",
1438
+ "lstrip": true,
1439
+ "normalized": false,
1440
+ "rstrip": true,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "256177": {
1445
+ "content": "__taq__",
1446
+ "lstrip": true,
1447
+ "normalized": false,
1448
+ "rstrip": true,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "256178": {
1453
+ "content": "__taq_Tfng__",
1454
+ "lstrip": true,
1455
+ "normalized": false,
1456
+ "rstrip": true,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "256179": {
1461
+ "content": "__tpi__",
1462
+ "lstrip": true,
1463
+ "normalized": false,
1464
+ "rstrip": true,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "256180": {
1469
+ "content": "__tsn__",
1470
+ "lstrip": true,
1471
+ "normalized": false,
1472
+ "rstrip": true,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "256181": {
1477
+ "content": "__tso__",
1478
+ "lstrip": true,
1479
+ "normalized": false,
1480
+ "rstrip": true,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "256182": {
1485
+ "content": "__tuk__",
1486
+ "lstrip": true,
1487
+ "normalized": false,
1488
+ "rstrip": true,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "256183": {
1493
+ "content": "__tum__",
1494
+ "lstrip": true,
1495
+ "normalized": false,
1496
+ "rstrip": true,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "256184": {
1501
+ "content": "__tur__",
1502
+ "lstrip": true,
1503
+ "normalized": false,
1504
+ "rstrip": true,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "256185": {
1509
+ "content": "__twi__",
1510
+ "lstrip": true,
1511
+ "normalized": false,
1512
+ "rstrip": true,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "256186": {
1517
+ "content": "__tzm__",
1518
+ "lstrip": true,
1519
+ "normalized": false,
1520
+ "rstrip": true,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "256187": {
1525
+ "content": "__uig__",
1526
+ "lstrip": true,
1527
+ "normalized": false,
1528
+ "rstrip": true,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "256188": {
1533
+ "content": "__ukr__",
1534
+ "lstrip": true,
1535
+ "normalized": false,
1536
+ "rstrip": true,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "256189": {
1541
+ "content": "__umb__",
1542
+ "lstrip": true,
1543
+ "normalized": false,
1544
+ "rstrip": true,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "256190": {
1549
+ "content": "__urd__",
1550
+ "lstrip": true,
1551
+ "normalized": false,
1552
+ "rstrip": true,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "256191": {
1557
+ "content": "__uzn__",
1558
+ "lstrip": true,
1559
+ "normalized": false,
1560
+ "rstrip": true,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "256192": {
1565
+ "content": "__vec__",
1566
+ "lstrip": true,
1567
+ "normalized": false,
1568
+ "rstrip": true,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "256193": {
1573
+ "content": "__vie__",
1574
+ "lstrip": true,
1575
+ "normalized": false,
1576
+ "rstrip": true,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "256194": {
1581
+ "content": "__war__",
1582
+ "lstrip": true,
1583
+ "normalized": false,
1584
+ "rstrip": true,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "256195": {
1589
+ "content": "__wol__",
1590
+ "lstrip": true,
1591
+ "normalized": false,
1592
+ "rstrip": true,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "256196": {
1597
+ "content": "__xho__",
1598
+ "lstrip": true,
1599
+ "normalized": false,
1600
+ "rstrip": true,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "256197": {
1605
+ "content": "__ydd__",
1606
+ "lstrip": true,
1607
+ "normalized": false,
1608
+ "rstrip": true,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "256198": {
1613
+ "content": "__yor__",
1614
+ "lstrip": true,
1615
+ "normalized": false,
1616
+ "rstrip": true,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "256199": {
1621
+ "content": "__yue__",
1622
+ "lstrip": true,
1623
+ "normalized": false,
1624
+ "rstrip": true,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "256200": {
1629
+ "content": "__cmn__",
1630
+ "lstrip": true,
1631
+ "normalized": false,
1632
+ "rstrip": true,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "256201": {
1637
+ "content": "__cmn_Hant__",
1638
+ "lstrip": true,
1639
+ "normalized": false,
1640
+ "rstrip": true,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "256202": {
1645
+ "content": "__zul__",
1646
+ "lstrip": true,
1647
+ "normalized": false,
1648
+ "rstrip": true,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ }
1652
+ },
1653
+ "additional_special_tokens": [
1654
+ "<pad>",
1655
+ "<unk>",
1656
+ "<s>",
1657
+ "</s>",
1658
+ "__ace__",
1659
+ "__ace_Latn__",
1660
+ "__acm__",
1661
+ "__acq__",
1662
+ "__aeb__",
1663
+ "__afr__",
1664
+ "__ajp__",
1665
+ "__aka__",
1666
+ "__amh__",
1667
+ "__apc__",
1668
+ "__arb__",
1669
+ "__ars__",
1670
+ "__ary__",
1671
+ "__arz__",
1672
+ "__asm__",
1673
+ "__ast__",
1674
+ "__awa__",
1675
+ "__ayr__",
1676
+ "__azb__",
1677
+ "__azj__",
1678
+ "__bak__",
1679
+ "__bam__",
1680
+ "__ban__",
1681
+ "__bel__",
1682
+ "__bem__",
1683
+ "__ben__",
1684
+ "__bho__",
1685
+ "__bjn__",
1686
+ "__bjn_Latn__",
1687
+ "__bod__",
1688
+ "__bos__",
1689
+ "__bug__",
1690
+ "__bul__",
1691
+ "__cat__",
1692
+ "__ceb__",
1693
+ "__ces__",
1694
+ "__cjk__",
1695
+ "__ckb__",
1696
+ "__crh__",
1697
+ "__cym__",
1698
+ "__dan__",
1699
+ "__deu__",
1700
+ "__dik__",
1701
+ "__dyu__",
1702
+ "__dzo__",
1703
+ "__ell__",
1704
+ "__eng__",
1705
+ "__epo__",
1706
+ "__est__",
1707
+ "__eus__",
1708
+ "__ewe__",
1709
+ "__fao__",
1710
+ "__pes__",
1711
+ "__fij__",
1712
+ "__fin__",
1713
+ "__fon__",
1714
+ "__fra__",
1715
+ "__fur__",
1716
+ "__fuv__",
1717
+ "__gla__",
1718
+ "__gle__",
1719
+ "__glg__",
1720
+ "__grn__",
1721
+ "__guj__",
1722
+ "__hat__",
1723
+ "__hau__",
1724
+ "__heb__",
1725
+ "__hin__",
1726
+ "__hne__",
1727
+ "__hrv__",
1728
+ "__hun__",
1729
+ "__hye__",
1730
+ "__ibo__",
1731
+ "__ilo__",
1732
+ "__ind__",
1733
+ "__isl__",
1734
+ "__ita__",
1735
+ "__jav__",
1736
+ "__jpn__",
1737
+ "__kab__",
1738
+ "__kac__",
1739
+ "__kam__",
1740
+ "__kan__",
1741
+ "__kas__",
1742
+ "__kas_Deva__",
1743
+ "__kat__",
1744
+ "__knc__",
1745
+ "__knc_Latn__",
1746
+ "__kaz__",
1747
+ "__kbp__",
1748
+ "__kea__",
1749
+ "__khm__",
1750
+ "__kik__",
1751
+ "__kin__",
1752
+ "__kir__",
1753
+ "__kmb__",
1754
+ "__kon__",
1755
+ "__kor__",
1756
+ "__kmr__",
1757
+ "__lao__",
1758
+ "__lvs__",
1759
+ "__lij__",
1760
+ "__lim__",
1761
+ "__lin__",
1762
+ "__lit__",
1763
+ "__lmo__",
1764
+ "__ltg__",
1765
+ "__ltz__",
1766
+ "__lua__",
1767
+ "__lug__",
1768
+ "__luo__",
1769
+ "__lus__",
1770
+ "__mag__",
1771
+ "__mai__",
1772
+ "__mal__",
1773
+ "__mar__",
1774
+ "__min__",
1775
+ "__mkd__",
1776
+ "__plt__",
1777
+ "__mlt__",
1778
+ "__mni__",
1779
+ "__khk__",
1780
+ "__mos__",
1781
+ "__mri__",
1782
+ "__zsm__",
1783
+ "__mya__",
1784
+ "__nld__",
1785
+ "__nno__",
1786
+ "__nob__",
1787
+ "__npi__",
1788
+ "__nso__",
1789
+ "__nus__",
1790
+ "__nya__",
1791
+ "__oci__",
1792
+ "__gaz__",
1793
+ "__ory__",
1794
+ "__pag__",
1795
+ "__pan__",
1796
+ "__pap__",
1797
+ "__pol__",
1798
+ "__por__",
1799
+ "__prs__",
1800
+ "__pbt__",
1801
+ "__quy__",
1802
+ "__ron__",
1803
+ "__run__",
1804
+ "__rus__",
1805
+ "__sag__",
1806
+ "__san__",
1807
+ "__sat__",
1808
+ "__scn__",
1809
+ "__shn__",
1810
+ "__sin__",
1811
+ "__slk__",
1812
+ "__slv__",
1813
+ "__smo__",
1814
+ "__sna__",
1815
+ "__snd__",
1816
+ "__som__",
1817
+ "__sot__",
1818
+ "__spa__",
1819
+ "__als__",
1820
+ "__srd__",
1821
+ "__srp__",
1822
+ "__ssw__",
1823
+ "__sun__",
1824
+ "__swe__",
1825
+ "__swh__",
1826
+ "__szl__",
1827
+ "__tam__",
1828
+ "__tat__",
1829
+ "__tel__",
1830
+ "__tgk__",
1831
+ "__tgl__",
1832
+ "__tha__",
1833
+ "__tir__",
1834
+ "__taq__",
1835
+ "__taq_Tfng__",
1836
+ "__tpi__",
1837
+ "__tsn__",
1838
+ "__tso__",
1839
+ "__tuk__",
1840
+ "__tum__",
1841
+ "__tur__",
1842
+ "__twi__",
1843
+ "__tzm__",
1844
+ "__uig__",
1845
+ "__ukr__",
1846
+ "__umb__",
1847
+ "__urd__",
1848
+ "__uzn__",
1849
+ "__vec__",
1850
+ "__vie__",
1851
+ "__war__",
1852
+ "__wol__",
1853
+ "__xho__",
1854
+ "__ydd__",
1855
+ "__yor__",
1856
+ "__yue__",
1857
+ "__cmn__",
1858
+ "__cmn_Hant__",
1859
+ "__zul__"
1860
+ ],
1861
+ "bos_token": "<s>",
1862
+ "clean_up_tokenization_spaces": true,
1863
+ "cls_token": "<s>",
1864
+ "eos_token": "</s>",
1865
+ "max_length": 128,
1866
+ "model_max_length": 1000000000000000019884624838656,
1867
+ "pad_to_multiple_of": 2,
1868
+ "pad_token": "<pad>",
1869
+ "pad_token_type_id": 0,
1870
+ "padding_side": "right",
1871
+ "processor_class": "SeamlessM4TProcessor",
1872
+ "sep_token": "</s>",
1873
+ "sp_model_kwargs": {},
1874
+ "src_lang": "__eng__",
1875
+ "stride": 0,
1876
+ "tgt_lang": "__fra__",
1877
+ "tokenizer_class": "SeamlessM4TTokenizer",
1878
+ "truncation_side": "right",
1879
+ "truncation_strategy": "longest_first",
1880
+ "unk_token": "<unk>"
1881
+ }