gajasankarraja commited on
Commit
a42ae1c
·
verified ·
1 Parent(s): e534e43

Training in progress, step 500

Browse files
added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__af__": 128004,
3
+ "__am__": 128005,
4
+ "__ar__": 128006,
5
+ "__ast__": 128007,
6
+ "__az__": 128008,
7
+ "__ba__": 128009,
8
+ "__be__": 128010,
9
+ "__bg__": 128011,
10
+ "__bn__": 128012,
11
+ "__br__": 128013,
12
+ "__bs__": 128014,
13
+ "__ca__": 128015,
14
+ "__ceb__": 128016,
15
+ "__cs__": 128017,
16
+ "__cy__": 128018,
17
+ "__da__": 128019,
18
+ "__de__": 128020,
19
+ "__el__": 128021,
20
+ "__en__": 128022,
21
+ "__es__": 128023,
22
+ "__et__": 128024,
23
+ "__fa__": 128025,
24
+ "__ff__": 128026,
25
+ "__fi__": 128027,
26
+ "__fr__": 128028,
27
+ "__fy__": 128029,
28
+ "__ga__": 128030,
29
+ "__gd__": 128031,
30
+ "__gl__": 128032,
31
+ "__gu__": 128033,
32
+ "__ha__": 128034,
33
+ "__he__": 128035,
34
+ "__hi__": 128036,
35
+ "__hr__": 128037,
36
+ "__ht__": 128038,
37
+ "__hu__": 128039,
38
+ "__hy__": 128040,
39
+ "__id__": 128041,
40
+ "__ig__": 128042,
41
+ "__ilo__": 128043,
42
+ "__is__": 128044,
43
+ "__it__": 128045,
44
+ "__ja__": 128046,
45
+ "__jv__": 128047,
46
+ "__ka__": 128048,
47
+ "__kk__": 128049,
48
+ "__km__": 128050,
49
+ "__kn__": 128051,
50
+ "__ko__": 128052,
51
+ "__lb__": 128053,
52
+ "__lg__": 128054,
53
+ "__ln__": 128055,
54
+ "__lo__": 128056,
55
+ "__lt__": 128057,
56
+ "__lv__": 128058,
57
+ "__mg__": 128059,
58
+ "__mk__": 128060,
59
+ "__ml__": 128061,
60
+ "__mn__": 128062,
61
+ "__mr__": 128063,
62
+ "__ms__": 128064,
63
+ "__my__": 128065,
64
+ "__ne__": 128066,
65
+ "__nl__": 128067,
66
+ "__no__": 128068,
67
+ "__ns__": 128069,
68
+ "__oc__": 128070,
69
+ "__or__": 128071,
70
+ "__pa__": 128072,
71
+ "__pl__": 128073,
72
+ "__ps__": 128074,
73
+ "__pt__": 128075,
74
+ "__ro__": 128076,
75
+ "__ru__": 128077,
76
+ "__sd__": 128078,
77
+ "__si__": 128079,
78
+ "__sk__": 128080,
79
+ "__sl__": 128081,
80
+ "__so__": 128082,
81
+ "__sq__": 128083,
82
+ "__sr__": 128084,
83
+ "__ss__": 128085,
84
+ "__su__": 128086,
85
+ "__sv__": 128087,
86
+ "__sw__": 128088,
87
+ "__ta__": 128089,
88
+ "__th__": 128090,
89
+ "__tl__": 128091,
90
+ "__tn__": 128092,
91
+ "__tr__": 128093,
92
+ "__uk__": 128094,
93
+ "__ur__": 128095,
94
+ "__uz__": 128096,
95
+ "__vi__": 128097,
96
+ "__wo__": 128098,
97
+ "__xh__": 128099,
98
+ "__yi__": 128100,
99
+ "__yo__": 128101,
100
+ "__zh__": 128102,
101
+ "__zu__": 128103
102
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "M2M100ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder_attention_heads": 16,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0.05,
13
+ "decoder_layers": 12,
14
+ "decoder_start_token_id": 2,
15
+ "dropout": 0.1,
16
+ "dtype": "float32",
17
+ "early_stopping": null,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.05,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "gradient_checkpointing": false,
24
+ "init_std": 0.02,
25
+ "is_encoder_decoder": true,
26
+ "max_length": null,
27
+ "max_position_embeddings": 1024,
28
+ "model_type": "m2m_100",
29
+ "num_beams": null,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "scale_embedding": true,
33
+ "transformers_version": "4.57.1",
34
+ "use_cache": true,
35
+ "vocab_size": 128112
36
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": [
6
+ 2
7
+ ],
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.57.1"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b78fd7bd1f17dc15ccdfd7c8c404b764cc4818ac7f7c50e6f9dc86c4fe16200
3
+ size 1935681888
runs/Oct22_03-54-47_37fc4ddcecb9/events.out.tfevents.1761105386.37fc4ddcecb9.837.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce373748c2437f2b8a2c6996976f1b63acd7cee91f63eaeea205172733fe67a5
3
+ size 6059
runs/Oct22_04-03-40_37fc4ddcecb9/events.out.tfevents.1761105825.37fc4ddcecb9.837.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab49087ba1e59fe66c848f950a527bb374fbd7c308c8989c0fc15d8c0e70605
3
+ size 6905
runs/Oct22_04-19-12_37fc4ddcecb9/events.out.tfevents.1761106756.37fc4ddcecb9.837.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4aa15a427ce2988dcf2ee98a5978b69d7c0453e8b093e141ff9d6933b4395e7
3
+ size 5638
runs/Oct22_04-23-59_37fc4ddcecb9/events.out.tfevents.1761107042.37fc4ddcecb9.837.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8e6b0ceaf23f6da8396f3a443f03b86f4bf3e628c8ef18a8bce413a551ed7f
3
+ size 5638
runs/Oct22_04-26-36_37fc4ddcecb9/events.out.tfevents.1761107198.37fc4ddcecb9.837.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6137f0686ee76b0b432837c429f61a69419350c4a97e77dedfb2d5571244280
3
+ size 5426
runs/Oct22_04-28-14_37fc4ddcecb9/events.out.tfevents.1761107298.37fc4ddcecb9.837.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516d6ab313483ae223169da3d56f4f71f04923f2932644c6b202403ffd8889d4
3
+ size 5428
runs/Oct22_04-40-56_37fc4ddcecb9/events.out.tfevents.1761108059.37fc4ddcecb9.837.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5524f92f151f8255aef3f2fe7d0d070037817812167af3a02f3300b3c6d77be7
3
+ size 5426
runs/Oct22_04-45-07_37fc4ddcecb9/events.out.tfevents.1761108340.37fc4ddcecb9.837.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0820ee36e2010d3aba8e44eece2bbdd03e0694f412a1a5b3d962d46f1934bfb
3
+ size 5428
runs/Oct22_04-59-10_37fc4ddcecb9/events.out.tfevents.1761109155.37fc4ddcecb9.837.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd57a283443a0cedd8300b81ddbfef0b9672ec0ba9fee8a8e079d4a69cbf47c
3
+ size 6478
runs/Oct22_05-33-37_37fc4ddcecb9/events.out.tfevents.1761111221.37fc4ddcecb9.837.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ece11cbbbae6bcd6cd9ec35c82d0b64318944ca1c2653a8b6bc09c93cb68c7a
3
+ size 6799
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
special_tokens_map.json CHANGED
@@ -1,34 +1,109 @@
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
- "eos_token": {
14
- "content": "<eos>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "pad_token": {
21
- "content": "<pad>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
- "unk_token": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false
33
- }
34
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
  ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "</s>",
108
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
tokenizer_config.json CHANGED
@@ -1,9 +1,7 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
- "content": "<pad>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
@@ -11,7 +9,7 @@
11
  "special": true
12
  },
13
  "1": {
14
- "content": "<eos>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
@@ -19,7 +17,7 @@
19
  "special": true
20
  },
21
  "2": {
22
- "content": "<bos>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
@@ -34,1724 +32,921 @@
34
  "single_word": false,
35
  "special": true
36
  },
37
- "4": {
38
- "content": "<mask>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "5": {
46
- "content": "<2mass>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "6": {
54
- "content": "[@BOS@]",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "7": {
62
- "content": "<unused0>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "8": {
70
- "content": "<unused1>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": false
76
- },
77
- "9": {
78
- "content": "<unused2>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": false
84
- },
85
- "10": {
86
- "content": "<unused3>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": false
92
- },
93
- "11": {
94
- "content": "<unused4>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": false
100
- },
101
- "12": {
102
- "content": "<unused5>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": false
108
- },
109
- "13": {
110
- "content": "<unused6>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": false
116
- },
117
- "14": {
118
- "content": "<unused7>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "15": {
126
- "content": "<unused8>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "16": {
134
- "content": "<unused9>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "17": {
142
- "content": "<unused10>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "18": {
150
- "content": "<unused11>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "19": {
158
- "content": "<unused12>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "20": {
166
- "content": "<unused13>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "21": {
174
- "content": "<unused14>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "22": {
182
- "content": "<unused15>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "23": {
190
- "content": "<unused16>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "24": {
198
- "content": "<unused17>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "25": {
206
- "content": "<unused18>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- },
213
- "26": {
214
- "content": "<unused19>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": false
220
- },
221
- "27": {
222
- "content": "<unused20>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": false
228
- },
229
- "28": {
230
- "content": "<unused21>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": false
236
- },
237
- "29": {
238
- "content": "<unused22>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": false
244
- },
245
- "30": {
246
- "content": "<unused23>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": false
252
- },
253
- "31": {
254
- "content": "<unused24>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": false
260
- },
261
- "32": {
262
- "content": "<unused25>",
263
  "lstrip": false,
264
  "normalized": false,
265
  "rstrip": false,
266
  "single_word": false,
267
- "special": false
268
- },
269
- "33": {
270
- "content": "<unused26>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": false
276
- },
277
- "34": {
278
- "content": "<unused27>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": false
284
- },
285
- "35": {
286
- "content": "<unused28>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": false
292
  },
293
- "36": {
294
- "content": "<unused29>",
295
  "lstrip": false,
296
  "normalized": false,
297
  "rstrip": false,
298
  "single_word": false,
299
- "special": false
300
  },
301
- "37": {
302
- "content": "<unused30>",
303
  "lstrip": false,
304
  "normalized": false,
305
  "rstrip": false,
306
  "single_word": false,
307
- "special": false
308
  },
309
- "38": {
310
- "content": "<unused31>",
311
  "lstrip": false,
312
  "normalized": false,
313
  "rstrip": false,
314
  "single_word": false,
315
- "special": false
316
  },
317
- "39": {
318
- "content": "<unused32>",
319
  "lstrip": false,
320
  "normalized": false,
321
  "rstrip": false,
322
  "single_word": false,
323
- "special": false
324
  },
325
- "40": {
326
- "content": "<unused33>",
327
  "lstrip": false,
328
  "normalized": false,
329
  "rstrip": false,
330
  "single_word": false,
331
- "special": false
332
  },
333
- "41": {
334
- "content": "<unused34>",
335
  "lstrip": false,
336
  "normalized": false,
337
  "rstrip": false,
338
  "single_word": false,
339
- "special": false
340
  },
341
- "42": {
342
- "content": "<unused35>",
343
  "lstrip": false,
344
  "normalized": false,
345
  "rstrip": false,
346
  "single_word": false,
347
- "special": false
348
  },
349
- "43": {
350
- "content": "<unused36>",
351
  "lstrip": false,
352
  "normalized": false,
353
  "rstrip": false,
354
  "single_word": false,
355
- "special": false
356
  },
357
- "44": {
358
- "content": "<unused37>",
359
  "lstrip": false,
360
  "normalized": false,
361
  "rstrip": false,
362
  "single_word": false,
363
- "special": false
364
  },
365
- "45": {
366
- "content": "<unused38>",
367
  "lstrip": false,
368
  "normalized": false,
369
  "rstrip": false,
370
  "single_word": false,
371
- "special": false
372
  },
373
- "46": {
374
- "content": "<unused39>",
375
  "lstrip": false,
376
  "normalized": false,
377
  "rstrip": false,
378
  "single_word": false,
379
- "special": false
380
  },
381
- "47": {
382
- "content": "<unused40>",
383
  "lstrip": false,
384
  "normalized": false,
385
  "rstrip": false,
386
  "single_word": false,
387
- "special": false
388
  },
389
- "48": {
390
- "content": "<unused41>",
391
  "lstrip": false,
392
  "normalized": false,
393
  "rstrip": false,
394
  "single_word": false,
395
- "special": false
396
  },
397
- "49": {
398
- "content": "<unused42>",
399
  "lstrip": false,
400
  "normalized": false,
401
  "rstrip": false,
402
  "single_word": false,
403
- "special": false
404
  },
405
- "50": {
406
- "content": "<unused43>",
407
  "lstrip": false,
408
  "normalized": false,
409
  "rstrip": false,
410
  "single_word": false,
411
- "special": false
412
  },
413
- "51": {
414
- "content": "<unused44>",
415
  "lstrip": false,
416
  "normalized": false,
417
  "rstrip": false,
418
  "single_word": false,
419
- "special": false
420
  },
421
- "52": {
422
- "content": "<unused45>",
423
  "lstrip": false,
424
  "normalized": false,
425
  "rstrip": false,
426
  "single_word": false,
427
- "special": false
428
  },
429
- "53": {
430
- "content": "<unused46>",
431
  "lstrip": false,
432
  "normalized": false,
433
  "rstrip": false,
434
  "single_word": false,
435
- "special": false
436
  },
437
- "54": {
438
- "content": "<unused47>",
439
  "lstrip": false,
440
  "normalized": false,
441
  "rstrip": false,
442
  "single_word": false,
443
- "special": false
444
  },
445
- "55": {
446
- "content": "<unused48>",
447
  "lstrip": false,
448
  "normalized": false,
449
  "rstrip": false,
450
  "single_word": false,
451
- "special": false
452
  },
453
- "56": {
454
- "content": "<unused49>",
455
  "lstrip": false,
456
  "normalized": false,
457
  "rstrip": false,
458
  "single_word": false,
459
- "special": false
460
  },
461
- "57": {
462
- "content": "<unused50>",
463
  "lstrip": false,
464
  "normalized": false,
465
  "rstrip": false,
466
  "single_word": false,
467
- "special": false
468
  },
469
- "58": {
470
- "content": "<unused51>",
471
  "lstrip": false,
472
  "normalized": false,
473
  "rstrip": false,
474
  "single_word": false,
475
- "special": false
476
  },
477
- "59": {
478
- "content": "<unused52>",
479
  "lstrip": false,
480
  "normalized": false,
481
  "rstrip": false,
482
  "single_word": false,
483
- "special": false
484
  },
485
- "60": {
486
- "content": "<unused53>",
487
  "lstrip": false,
488
  "normalized": false,
489
  "rstrip": false,
490
  "single_word": false,
491
- "special": false
492
  },
493
- "61": {
494
- "content": "<unused54>",
495
  "lstrip": false,
496
  "normalized": false,
497
  "rstrip": false,
498
  "single_word": false,
499
- "special": false
500
  },
501
- "62": {
502
- "content": "<unused55>",
503
  "lstrip": false,
504
  "normalized": false,
505
  "rstrip": false,
506
  "single_word": false,
507
- "special": false
508
  },
509
- "63": {
510
- "content": "<unused56>",
511
  "lstrip": false,
512
  "normalized": false,
513
  "rstrip": false,
514
  "single_word": false,
515
- "special": false
516
  },
517
- "64": {
518
- "content": "<unused57>",
519
  "lstrip": false,
520
  "normalized": false,
521
  "rstrip": false,
522
  "single_word": false,
523
- "special": false
524
  },
525
- "65": {
526
- "content": "<unused58>",
527
  "lstrip": false,
528
  "normalized": false,
529
  "rstrip": false,
530
  "single_word": false,
531
- "special": false
532
  },
533
- "66": {
534
- "content": "<unused59>",
535
  "lstrip": false,
536
  "normalized": false,
537
  "rstrip": false,
538
  "single_word": false,
539
- "special": false
540
  },
541
- "67": {
542
- "content": "<unused60>",
543
  "lstrip": false,
544
  "normalized": false,
545
  "rstrip": false,
546
  "single_word": false,
547
- "special": false
548
  },
549
- "68": {
550
- "content": "<unused61>",
551
  "lstrip": false,
552
  "normalized": false,
553
  "rstrip": false,
554
  "single_word": false,
555
- "special": false
556
  },
557
- "69": {
558
- "content": "<unused62>",
559
  "lstrip": false,
560
  "normalized": false,
561
  "rstrip": false,
562
  "single_word": false,
563
- "special": false
564
  },
565
- "70": {
566
- "content": "<unused63>",
567
  "lstrip": false,
568
  "normalized": false,
569
  "rstrip": false,
570
  "single_word": false,
571
- "special": false
572
  },
573
- "71": {
574
- "content": "<unused64>",
575
  "lstrip": false,
576
  "normalized": false,
577
  "rstrip": false,
578
  "single_word": false,
579
- "special": false
580
  },
581
- "72": {
582
- "content": "<unused65>",
583
  "lstrip": false,
584
  "normalized": false,
585
  "rstrip": false,
586
  "single_word": false,
587
- "special": false
588
  },
589
- "73": {
590
- "content": "<unused66>",
591
  "lstrip": false,
592
  "normalized": false,
593
  "rstrip": false,
594
  "single_word": false,
595
- "special": false
596
  },
597
- "74": {
598
- "content": "<unused67>",
599
  "lstrip": false,
600
  "normalized": false,
601
  "rstrip": false,
602
  "single_word": false,
603
- "special": false
604
  },
605
- "75": {
606
- "content": "<unused68>",
607
  "lstrip": false,
608
  "normalized": false,
609
  "rstrip": false,
610
  "single_word": false,
611
- "special": false
612
  },
613
- "76": {
614
- "content": "<unused69>",
615
  "lstrip": false,
616
  "normalized": false,
617
  "rstrip": false,
618
  "single_word": false,
619
- "special": false
620
  },
621
- "77": {
622
- "content": "<unused70>",
623
  "lstrip": false,
624
  "normalized": false,
625
  "rstrip": false,
626
  "single_word": false,
627
- "special": false
628
  },
629
- "78": {
630
- "content": "<unused71>",
631
  "lstrip": false,
632
  "normalized": false,
633
  "rstrip": false,
634
  "single_word": false,
635
- "special": false
636
  },
637
- "79": {
638
- "content": "<unused72>",
639
  "lstrip": false,
640
  "normalized": false,
641
  "rstrip": false,
642
  "single_word": false,
643
- "special": false
644
  },
645
- "80": {
646
- "content": "<unused73>",
647
  "lstrip": false,
648
  "normalized": false,
649
  "rstrip": false,
650
  "single_word": false,
651
- "special": false
652
  },
653
- "81": {
654
- "content": "<unused74>",
655
  "lstrip": false,
656
  "normalized": false,
657
  "rstrip": false,
658
  "single_word": false,
659
- "special": false
660
  },
661
- "82": {
662
- "content": "<unused75>",
663
  "lstrip": false,
664
  "normalized": false,
665
  "rstrip": false,
666
  "single_word": false,
667
- "special": false
668
  },
669
- "83": {
670
- "content": "<unused76>",
671
  "lstrip": false,
672
  "normalized": false,
673
  "rstrip": false,
674
  "single_word": false,
675
- "special": false
676
  },
677
- "84": {
678
- "content": "<unused77>",
679
  "lstrip": false,
680
  "normalized": false,
681
  "rstrip": false,
682
  "single_word": false,
683
- "special": false
684
  },
685
- "85": {
686
- "content": "<unused78>",
687
  "lstrip": false,
688
  "normalized": false,
689
  "rstrip": false,
690
  "single_word": false,
691
- "special": false
692
  },
693
- "86": {
694
- "content": "<unused79>",
695
  "lstrip": false,
696
  "normalized": false,
697
  "rstrip": false,
698
  "single_word": false,
699
- "special": false
700
  },
701
- "87": {
702
- "content": "<unused80>",
703
  "lstrip": false,
704
  "normalized": false,
705
  "rstrip": false,
706
  "single_word": false,
707
- "special": false
708
  },
709
- "88": {
710
- "content": "<unused81>",
711
  "lstrip": false,
712
  "normalized": false,
713
  "rstrip": false,
714
  "single_word": false,
715
- "special": false
716
  },
717
- "89": {
718
- "content": "<unused82>",
719
  "lstrip": false,
720
  "normalized": false,
721
  "rstrip": false,
722
  "single_word": false,
723
- "special": false
724
  },
725
- "90": {
726
- "content": "<unused83>",
727
  "lstrip": false,
728
  "normalized": false,
729
  "rstrip": false,
730
  "single_word": false,
731
- "special": false
732
  },
733
- "91": {
734
- "content": "<unused84>",
735
  "lstrip": false,
736
  "normalized": false,
737
  "rstrip": false,
738
  "single_word": false,
739
- "special": false
740
  },
741
- "92": {
742
- "content": "<unused85>",
743
  "lstrip": false,
744
  "normalized": false,
745
  "rstrip": false,
746
  "single_word": false,
747
- "special": false
748
  },
749
- "93": {
750
- "content": "<unused86>",
751
  "lstrip": false,
752
  "normalized": false,
753
  "rstrip": false,
754
  "single_word": false,
755
- "special": false
756
  },
757
- "94": {
758
- "content": "<unused87>",
759
  "lstrip": false,
760
  "normalized": false,
761
  "rstrip": false,
762
  "single_word": false,
763
- "special": false
764
  },
765
- "95": {
766
- "content": "<unused88>",
767
  "lstrip": false,
768
  "normalized": false,
769
  "rstrip": false,
770
  "single_word": false,
771
- "special": false
772
  },
773
- "96": {
774
- "content": "<unused89>",
775
  "lstrip": false,
776
  "normalized": false,
777
  "rstrip": false,
778
  "single_word": false,
779
- "special": false
780
  },
781
- "97": {
782
- "content": "<unused90>",
783
  "lstrip": false,
784
  "normalized": false,
785
  "rstrip": false,
786
  "single_word": false,
787
- "special": false
788
  },
789
- "98": {
790
- "content": "<unused91>",
791
  "lstrip": false,
792
  "normalized": false,
793
  "rstrip": false,
794
  "single_word": false,
795
- "special": false
796
  },
797
- "99": {
798
- "content": "<unused92>",
799
  "lstrip": false,
800
  "normalized": false,
801
  "rstrip": false,
802
  "single_word": false,
803
- "special": false
804
  },
805
- "100": {
806
- "content": "<unused93>",
807
  "lstrip": false,
808
  "normalized": false,
809
  "rstrip": false,
810
  "single_word": false,
811
- "special": false
812
  },
813
- "101": {
814
- "content": "<unused94>",
815
  "lstrip": false,
816
  "normalized": false,
817
  "rstrip": false,
818
  "single_word": false,
819
- "special": false
820
  },
821
- "102": {
822
- "content": "<unused95>",
823
  "lstrip": false,
824
  "normalized": false,
825
  "rstrip": false,
826
  "single_word": false,
827
- "special": false
828
  },
829
- "103": {
830
- "content": "<unused96>",
831
  "lstrip": false,
832
  "normalized": false,
833
  "rstrip": false,
834
  "single_word": false,
835
- "special": false
836
  },
837
- "104": {
838
- "content": "<unused97>",
839
  "lstrip": false,
840
  "normalized": false,
841
  "rstrip": false,
842
  "single_word": false,
843
- "special": false
844
  },
845
- "105": {
846
- "content": "<unused98>",
847
  "lstrip": false,
848
  "normalized": false,
849
  "rstrip": false,
850
  "single_word": false,
851
- "special": false
852
  },
853
- "106": {
854
- "content": "<start_of_turn>",
855
  "lstrip": false,
856
  "normalized": false,
857
  "rstrip": false,
858
  "single_word": false,
859
  "special": true
860
  },
861
- "107": {
862
- "content": "<end_of_turn>",
863
  "lstrip": false,
864
  "normalized": false,
865
  "rstrip": false,
866
  "single_word": false,
867
  "special": true
868
  },
869
- "108": {
870
- "content": "\n",
871
  "lstrip": false,
872
  "normalized": false,
873
  "rstrip": false,
874
  "single_word": false,
875
- "special": false
876
  },
877
- "109": {
878
- "content": "\n\n",
879
  "lstrip": false,
880
  "normalized": false,
881
  "rstrip": false,
882
  "single_word": false,
883
- "special": false
884
  },
885
- "110": {
886
- "content": "\n\n\n",
887
  "lstrip": false,
888
  "normalized": false,
889
  "rstrip": false,
890
  "single_word": false,
891
- "special": false
892
  },
893
- "111": {
894
- "content": "\n\n\n\n",
895
  "lstrip": false,
896
  "normalized": false,
897
  "rstrip": false,
898
  "single_word": false,
899
- "special": false
900
  },
901
- "112": {
902
- "content": "\n\n\n\n\n",
903
  "lstrip": false,
904
  "normalized": false,
905
  "rstrip": false,
906
  "single_word": false,
907
- "special": false
908
  },
909
- "113": {
910
- "content": "\n\n\n\n\n\n",
911
  "lstrip": false,
912
  "normalized": false,
913
  "rstrip": false,
914
  "single_word": false,
915
- "special": false
916
  },
917
- "114": {
918
- "content": "\n\n\n\n\n\n\n",
919
  "lstrip": false,
920
  "normalized": false,
921
  "rstrip": false,
922
  "single_word": false,
923
- "special": false
924
  },
925
- "115": {
926
- "content": "\n\n\n\n\n\n\n\n",
927
  "lstrip": false,
928
  "normalized": false,
929
  "rstrip": false,
930
  "single_word": false,
931
- "special": false
932
  },
933
- "116": {
934
- "content": "\n\n\n\n\n\n\n\n\n",
935
  "lstrip": false,
936
  "normalized": false,
937
  "rstrip": false,
938
  "single_word": false,
939
- "special": false
940
  },
941
- "117": {
942
- "content": "\n\n\n\n\n\n\n\n\n\n",
943
  "lstrip": false,
944
  "normalized": false,
945
  "rstrip": false,
946
  "single_word": false,
947
- "special": false
948
  },
949
- "118": {
950
- "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
  "lstrip": false,
952
  "normalized": false,
953
  "rstrip": false,
954
  "single_word": false,
955
- "special": false
956
  },
957
- "119": {
958
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
  "lstrip": false,
960
  "normalized": false,
961
  "rstrip": false,
962
  "single_word": false,
963
- "special": false
964
  },
965
- "120": {
966
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
  "lstrip": false,
968
  "normalized": false,
969
  "rstrip": false,
970
  "single_word": false,
971
- "special": false
972
  },
973
- "121": {
974
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
  "lstrip": false,
976
  "normalized": false,
977
  "rstrip": false,
978
  "single_word": false,
979
- "special": false
980
  },
981
- "122": {
982
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
  "lstrip": false,
984
  "normalized": false,
985
  "rstrip": false,
986
  "single_word": false,
987
- "special": false
988
  },
989
- "123": {
990
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
  "lstrip": false,
992
  "normalized": false,
993
  "rstrip": false,
994
  "single_word": false,
995
- "special": false
996
  },
997
- "124": {
998
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
  "lstrip": false,
1000
  "normalized": false,
1001
  "rstrip": false,
1002
  "single_word": false,
1003
- "special": false
1004
  },
1005
- "125": {
1006
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
  "lstrip": false,
1008
  "normalized": false,
1009
  "rstrip": false,
1010
  "single_word": false,
1011
- "special": false
1012
  },
1013
- "126": {
1014
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
  "lstrip": false,
1016
  "normalized": false,
1017
  "rstrip": false,
1018
  "single_word": false,
1019
- "special": false
1020
  },
1021
- "127": {
1022
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
  "lstrip": false,
1024
  "normalized": false,
1025
  "rstrip": false,
1026
  "single_word": false,
1027
- "special": false
1028
  },
1029
- "128": {
1030
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
  "lstrip": false,
1032
  "normalized": false,
1033
  "rstrip": false,
1034
  "single_word": false,
1035
- "special": false
1036
  },
1037
- "129": {
1038
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
  "lstrip": false,
1040
  "normalized": false,
1041
  "rstrip": false,
1042
  "single_word": false,
1043
- "special": false
1044
  },
1045
- "130": {
1046
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
  "lstrip": false,
1048
  "normalized": false,
1049
  "rstrip": false,
1050
  "single_word": false,
1051
- "special": false
1052
  },
1053
- "131": {
1054
- "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",
1055
  "lstrip": false,
1056
  "normalized": false,
1057
  "rstrip": false,
1058
  "single_word": false,
1059
- "special": false
1060
  },
1061
- "132": {
1062
- "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",
1063
  "lstrip": false,
1064
  "normalized": false,
1065
  "rstrip": false,
1066
  "single_word": false,
1067
- "special": false
1068
  },
1069
- "133": {
1070
- "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",
1071
  "lstrip": false,
1072
  "normalized": false,
1073
  "rstrip": false,
1074
  "single_word": false,
1075
- "special": false
1076
  },
1077
- "134": {
1078
- "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",
1079
  "lstrip": false,
1080
  "normalized": false,
1081
  "rstrip": false,
1082
  "single_word": false,
1083
- "special": false
1084
- },
1085
- "135": {
1086
- "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",
1087
- "lstrip": false,
1088
- "normalized": false,
1089
- "rstrip": false,
1090
- "single_word": false,
1091
- "special": false
1092
- },
1093
- "136": {
1094
- "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",
1095
- "lstrip": false,
1096
- "normalized": false,
1097
- "rstrip": false,
1098
- "single_word": false,
1099
- "special": false
1100
- },
1101
- "137": {
1102
- "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",
1103
- "lstrip": false,
1104
- "normalized": false,
1105
- "rstrip": false,
1106
- "single_word": false,
1107
- "special": false
1108
- },
1109
- "138": {
1110
- "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",
1111
- "lstrip": false,
1112
- "normalized": false,
1113
- "rstrip": false,
1114
- "single_word": false,
1115
- "special": false
1116
- },
1117
- "139": {
1118
- "content": "▁▁",
1119
- "lstrip": false,
1120
- "normalized": false,
1121
- "rstrip": false,
1122
- "single_word": false,
1123
- "special": false
1124
- },
1125
- "140": {
1126
- "content": "▁▁▁",
1127
- "lstrip": false,
1128
- "normalized": false,
1129
- "rstrip": false,
1130
- "single_word": false,
1131
- "special": false
1132
- },
1133
- "141": {
1134
- "content": "▁▁▁▁",
1135
- "lstrip": false,
1136
- "normalized": false,
1137
- "rstrip": false,
1138
- "single_word": false,
1139
- "special": false
1140
- },
1141
- "142": {
1142
- "content": "▁▁▁▁▁",
1143
- "lstrip": false,
1144
- "normalized": false,
1145
- "rstrip": false,
1146
- "single_word": false,
1147
- "special": false
1148
- },
1149
- "143": {
1150
- "content": "▁▁▁▁▁▁",
1151
- "lstrip": false,
1152
- "normalized": false,
1153
- "rstrip": false,
1154
- "single_word": false,
1155
- "special": false
1156
- },
1157
- "144": {
1158
- "content": "▁▁▁▁▁▁▁",
1159
- "lstrip": false,
1160
- "normalized": false,
1161
- "rstrip": false,
1162
- "single_word": false,
1163
- "special": false
1164
- },
1165
- "145": {
1166
- "content": "▁▁▁▁▁▁▁▁",
1167
- "lstrip": false,
1168
- "normalized": false,
1169
- "rstrip": false,
1170
- "single_word": false,
1171
- "special": false
1172
- },
1173
- "146": {
1174
- "content": "▁▁▁▁▁▁▁▁▁",
1175
- "lstrip": false,
1176
- "normalized": false,
1177
- "rstrip": false,
1178
- "single_word": false,
1179
- "special": false
1180
- },
1181
- "147": {
1182
- "content": "▁▁▁▁▁▁▁▁▁▁",
1183
- "lstrip": false,
1184
- "normalized": false,
1185
- "rstrip": false,
1186
- "single_word": false,
1187
- "special": false
1188
- },
1189
- "148": {
1190
- "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
- "lstrip": false,
1192
- "normalized": false,
1193
- "rstrip": false,
1194
- "single_word": false,
1195
- "special": false
1196
- },
1197
- "149": {
1198
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
- "lstrip": false,
1200
- "normalized": false,
1201
- "rstrip": false,
1202
- "single_word": false,
1203
- "special": false
1204
- },
1205
- "150": {
1206
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
- "lstrip": false,
1208
- "normalized": false,
1209
- "rstrip": false,
1210
- "single_word": false,
1211
- "special": false
1212
- },
1213
- "151": {
1214
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
- "lstrip": false,
1216
- "normalized": false,
1217
- "rstrip": false,
1218
- "single_word": false,
1219
- "special": false
1220
- },
1221
- "152": {
1222
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
- "lstrip": false,
1224
- "normalized": false,
1225
- "rstrip": false,
1226
- "single_word": false,
1227
- "special": false
1228
- },
1229
- "153": {
1230
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
- "lstrip": false,
1232
- "normalized": false,
1233
- "rstrip": false,
1234
- "single_word": false,
1235
- "special": false
1236
- },
1237
- "154": {
1238
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
- "lstrip": false,
1240
- "normalized": false,
1241
- "rstrip": false,
1242
- "single_word": false,
1243
- "special": false
1244
- },
1245
- "155": {
1246
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
- "lstrip": false,
1248
- "normalized": false,
1249
- "rstrip": false,
1250
- "single_word": false,
1251
- "special": false
1252
- },
1253
- "156": {
1254
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
- "lstrip": false,
1256
- "normalized": false,
1257
- "rstrip": false,
1258
- "single_word": false,
1259
- "special": false
1260
- },
1261
- "157": {
1262
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
- "lstrip": false,
1264
- "normalized": false,
1265
- "rstrip": false,
1266
- "single_word": false,
1267
- "special": false
1268
- },
1269
- "158": {
1270
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
- "lstrip": false,
1272
- "normalized": false,
1273
- "rstrip": false,
1274
- "single_word": false,
1275
- "special": false
1276
- },
1277
- "159": {
1278
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
- "lstrip": false,
1280
- "normalized": false,
1281
- "rstrip": false,
1282
- "single_word": false,
1283
- "special": false
1284
- },
1285
- "160": {
1286
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
- "lstrip": false,
1288
- "normalized": false,
1289
- "rstrip": false,
1290
- "single_word": false,
1291
- "special": false
1292
- },
1293
- "161": {
1294
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
- "lstrip": false,
1296
- "normalized": false,
1297
- "rstrip": false,
1298
- "single_word": false,
1299
- "special": false
1300
- },
1301
- "162": {
1302
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
- "lstrip": false,
1304
- "normalized": false,
1305
- "rstrip": false,
1306
- "single_word": false,
1307
- "special": false
1308
- },
1309
- "163": {
1310
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
- "lstrip": false,
1312
- "normalized": false,
1313
- "rstrip": false,
1314
- "single_word": false,
1315
- "special": false
1316
- },
1317
- "164": {
1318
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
- "lstrip": false,
1320
- "normalized": false,
1321
- "rstrip": false,
1322
- "single_word": false,
1323
- "special": false
1324
- },
1325
- "165": {
1326
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
- "lstrip": false,
1328
- "normalized": false,
1329
- "rstrip": false,
1330
- "single_word": false,
1331
- "special": false
1332
- },
1333
- "166": {
1334
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
- "lstrip": false,
1336
- "normalized": false,
1337
- "rstrip": false,
1338
- "single_word": false,
1339
- "special": false
1340
- },
1341
- "167": {
1342
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
- "lstrip": false,
1344
- "normalized": false,
1345
- "rstrip": false,
1346
- "single_word": false,
1347
- "special": false
1348
- },
1349
- "168": {
1350
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
- "lstrip": false,
1352
- "normalized": false,
1353
- "rstrip": false,
1354
- "single_word": false,
1355
- "special": false
1356
- },
1357
- "169": {
1358
- "content": "<table>",
1359
- "lstrip": false,
1360
- "normalized": false,
1361
- "rstrip": false,
1362
- "single_word": false,
1363
- "special": false
1364
- },
1365
- "170": {
1366
- "content": "<caption>",
1367
- "lstrip": false,
1368
- "normalized": false,
1369
- "rstrip": false,
1370
- "single_word": false,
1371
- "special": false
1372
- },
1373
- "171": {
1374
- "content": "<thead>",
1375
- "lstrip": false,
1376
- "normalized": false,
1377
- "rstrip": false,
1378
- "single_word": false,
1379
- "special": false
1380
- },
1381
- "172": {
1382
- "content": "<tbody>",
1383
- "lstrip": false,
1384
- "normalized": false,
1385
- "rstrip": false,
1386
- "single_word": false,
1387
- "special": false
1388
- },
1389
- "173": {
1390
- "content": "<tfoot>",
1391
- "lstrip": false,
1392
- "normalized": false,
1393
- "rstrip": false,
1394
- "single_word": false,
1395
- "special": false
1396
- },
1397
- "174": {
1398
- "content": "<tr>",
1399
- "lstrip": false,
1400
- "normalized": false,
1401
- "rstrip": false,
1402
- "single_word": false,
1403
- "special": false
1404
- },
1405
- "175": {
1406
- "content": "<th>",
1407
- "lstrip": false,
1408
- "normalized": false,
1409
- "rstrip": false,
1410
- "single_word": false,
1411
- "special": false
1412
- },
1413
- "176": {
1414
- "content": "<td>",
1415
- "lstrip": false,
1416
- "normalized": false,
1417
- "rstrip": false,
1418
- "single_word": false,
1419
- "special": false
1420
- },
1421
- "177": {
1422
- "content": "</table>",
1423
- "lstrip": false,
1424
- "normalized": false,
1425
- "rstrip": false,
1426
- "single_word": false,
1427
- "special": false
1428
- },
1429
- "178": {
1430
- "content": "</caption>",
1431
- "lstrip": false,
1432
- "normalized": false,
1433
- "rstrip": false,
1434
- "single_word": false,
1435
- "special": false
1436
- },
1437
- "179": {
1438
- "content": "</thead>",
1439
- "lstrip": false,
1440
- "normalized": false,
1441
- "rstrip": false,
1442
- "single_word": false,
1443
- "special": false
1444
- },
1445
- "180": {
1446
- "content": "</tbody>",
1447
- "lstrip": false,
1448
- "normalized": false,
1449
- "rstrip": false,
1450
- "single_word": false,
1451
- "special": false
1452
- },
1453
- "181": {
1454
- "content": "</tfoot>",
1455
- "lstrip": false,
1456
- "normalized": false,
1457
- "rstrip": false,
1458
- "single_word": false,
1459
- "special": false
1460
- },
1461
- "182": {
1462
- "content": "</tr>",
1463
- "lstrip": false,
1464
- "normalized": false,
1465
- "rstrip": false,
1466
- "single_word": false,
1467
- "special": false
1468
- },
1469
- "183": {
1470
- "content": "</th>",
1471
- "lstrip": false,
1472
- "normalized": false,
1473
- "rstrip": false,
1474
- "single_word": false,
1475
- "special": false
1476
- },
1477
- "184": {
1478
- "content": "</td>",
1479
- "lstrip": false,
1480
- "normalized": false,
1481
- "rstrip": false,
1482
- "single_word": false,
1483
- "special": false
1484
- },
1485
- "185": {
1486
- "content": "<h1>",
1487
- "lstrip": false,
1488
- "normalized": false,
1489
- "rstrip": false,
1490
- "single_word": false,
1491
- "special": false
1492
- },
1493
- "186": {
1494
- "content": "<h2>",
1495
- "lstrip": false,
1496
- "normalized": false,
1497
- "rstrip": false,
1498
- "single_word": false,
1499
- "special": false
1500
- },
1501
- "187": {
1502
- "content": "<h3>",
1503
- "lstrip": false,
1504
- "normalized": false,
1505
- "rstrip": false,
1506
- "single_word": false,
1507
- "special": false
1508
- },
1509
- "188": {
1510
- "content": "<h4>",
1511
- "lstrip": false,
1512
- "normalized": false,
1513
- "rstrip": false,
1514
- "single_word": false,
1515
- "special": false
1516
- },
1517
- "189": {
1518
- "content": "<h5>",
1519
- "lstrip": false,
1520
- "normalized": false,
1521
- "rstrip": false,
1522
- "single_word": false,
1523
- "special": false
1524
- },
1525
- "190": {
1526
- "content": "<h6>",
1527
- "lstrip": false,
1528
- "normalized": false,
1529
- "rstrip": false,
1530
- "single_word": false,
1531
- "special": false
1532
- },
1533
- "191": {
1534
- "content": "<blockquote>",
1535
- "lstrip": false,
1536
- "normalized": false,
1537
- "rstrip": false,
1538
- "single_word": false,
1539
- "special": false
1540
- },
1541
- "192": {
1542
- "content": "</h1>",
1543
- "lstrip": false,
1544
- "normalized": false,
1545
- "rstrip": false,
1546
- "single_word": false,
1547
- "special": false
1548
- },
1549
- "193": {
1550
- "content": "</h2>",
1551
- "lstrip": false,
1552
- "normalized": false,
1553
- "rstrip": false,
1554
- "single_word": false,
1555
- "special": false
1556
- },
1557
- "194": {
1558
- "content": "</h3>",
1559
- "lstrip": false,
1560
- "normalized": false,
1561
- "rstrip": false,
1562
- "single_word": false,
1563
- "special": false
1564
- },
1565
- "195": {
1566
- "content": "</h4>",
1567
- "lstrip": false,
1568
- "normalized": false,
1569
- "rstrip": false,
1570
- "single_word": false,
1571
- "special": false
1572
- },
1573
- "196": {
1574
- "content": "</h5>",
1575
- "lstrip": false,
1576
- "normalized": false,
1577
- "rstrip": false,
1578
- "single_word": false,
1579
- "special": false
1580
- },
1581
- "197": {
1582
- "content": "</h6>",
1583
- "lstrip": false,
1584
- "normalized": false,
1585
- "rstrip": false,
1586
- "single_word": false,
1587
- "special": false
1588
- },
1589
- "198": {
1590
- "content": "</blockquote>",
1591
- "lstrip": false,
1592
- "normalized": false,
1593
- "rstrip": false,
1594
- "single_word": false,
1595
- "special": false
1596
- },
1597
- "199": {
1598
- "content": "<strong>",
1599
- "lstrip": false,
1600
- "normalized": false,
1601
- "rstrip": false,
1602
- "single_word": false,
1603
- "special": false
1604
- },
1605
- "200": {
1606
- "content": "<em>",
1607
- "lstrip": false,
1608
- "normalized": false,
1609
- "rstrip": false,
1610
- "single_word": false,
1611
- "special": false
1612
- },
1613
- "201": {
1614
- "content": "<b>",
1615
- "lstrip": false,
1616
- "normalized": false,
1617
- "rstrip": false,
1618
- "single_word": false,
1619
- "special": false
1620
- },
1621
- "202": {
1622
- "content": "<i>",
1623
- "lstrip": false,
1624
- "normalized": false,
1625
- "rstrip": false,
1626
- "single_word": false,
1627
- "special": false
1628
- },
1629
- "203": {
1630
- "content": "<u>",
1631
- "lstrip": false,
1632
- "normalized": false,
1633
- "rstrip": false,
1634
- "single_word": false,
1635
- "special": false
1636
- },
1637
- "204": {
1638
- "content": "<s>",
1639
- "lstrip": false,
1640
- "normalized": false,
1641
- "rstrip": false,
1642
- "single_word": false,
1643
- "special": false
1644
- },
1645
- "205": {
1646
- "content": "<sub>",
1647
- "lstrip": false,
1648
- "normalized": false,
1649
- "rstrip": false,
1650
- "single_word": false,
1651
- "special": false
1652
- },
1653
- "206": {
1654
- "content": "<sup>",
1655
- "lstrip": false,
1656
- "normalized": false,
1657
- "rstrip": false,
1658
- "single_word": false,
1659
- "special": false
1660
- },
1661
- "207": {
1662
- "content": "<code>",
1663
- "lstrip": false,
1664
- "normalized": false,
1665
- "rstrip": false,
1666
- "single_word": false,
1667
- "special": false
1668
- },
1669
- "208": {
1670
- "content": "</strong>",
1671
- "lstrip": false,
1672
- "normalized": false,
1673
- "rstrip": false,
1674
- "single_word": false,
1675
- "special": false
1676
- },
1677
- "209": {
1678
- "content": "</em>",
1679
- "lstrip": false,
1680
- "normalized": false,
1681
- "rstrip": false,
1682
- "single_word": false,
1683
- "special": false
1684
- },
1685
- "210": {
1686
- "content": "</b>",
1687
- "lstrip": false,
1688
- "normalized": false,
1689
- "rstrip": false,
1690
- "single_word": false,
1691
- "special": false
1692
- },
1693
- "211": {
1694
- "content": "</i>",
1695
- "lstrip": false,
1696
- "normalized": false,
1697
- "rstrip": false,
1698
- "single_word": false,
1699
- "special": false
1700
- },
1701
- "212": {
1702
- "content": "</u>",
1703
- "lstrip": false,
1704
- "normalized": false,
1705
- "rstrip": false,
1706
- "single_word": false,
1707
- "special": false
1708
- },
1709
- "213": {
1710
- "content": "</s>",
1711
- "lstrip": false,
1712
- "normalized": false,
1713
- "rstrip": false,
1714
- "single_word": false,
1715
- "special": false
1716
- },
1717
- "214": {
1718
- "content": "</sub>",
1719
- "lstrip": false,
1720
- "normalized": false,
1721
- "rstrip": false,
1722
- "single_word": false,
1723
- "special": false
1724
- },
1725
- "215": {
1726
- "content": "</sup>",
1727
- "lstrip": false,
1728
- "normalized": false,
1729
- "rstrip": false,
1730
- "single_word": false,
1731
- "special": false
1732
- },
1733
- "216": {
1734
- "content": "</code>",
1735
- "lstrip": false,
1736
- "normalized": false,
1737
- "rstrip": false,
1738
- "single_word": false,
1739
- "special": false
1740
  }
1741
  },
1742
  "additional_special_tokens": [
1743
- "<start_of_turn>",
1744
- "<end_of_turn>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1745
  ],
1746
- "bos_token": "<bos>",
1747
  "clean_up_tokenization_spaces": false,
1748
- "eos_token": "<eos>",
1749
  "extra_special_tokens": {},
1750
- "model_max_length": 1000000000000000019884624838656,
 
 
1751
  "pad_token": "<pad>",
 
1752
  "sp_model_kwargs": {},
1753
- "spaces_between_special_tokens": false,
1754
- "tokenizer_class": "GemmaTokenizer",
1755
- "unk_token": "<unk>",
1756
- "use_default_system_prompt": false
1757
  }
 
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "128004": {
36
+ "content": "__af__",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
+ "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  },
43
+ "128005": {
44
+ "content": "__am__",
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
48
  "single_word": false,
49
+ "special": true
50
  },
51
+ "128006": {
52
+ "content": "__ar__",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
+ "special": true
58
  },
59
+ "128007": {
60
+ "content": "__ast__",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
64
  "single_word": false,
65
+ "special": true
66
  },
67
+ "128008": {
68
+ "content": "__az__",
69
  "lstrip": false,
70
  "normalized": false,
71
  "rstrip": false,
72
  "single_word": false,
73
+ "special": true
74
  },
75
+ "128009": {
76
+ "content": "__ba__",
77
  "lstrip": false,
78
  "normalized": false,
79
  "rstrip": false,
80
  "single_word": false,
81
+ "special": true
82
  },
83
+ "128010": {
84
+ "content": "__be__",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
88
  "single_word": false,
89
+ "special": true
90
  },
91
+ "128011": {
92
+ "content": "__bg__",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
96
  "single_word": false,
97
+ "special": true
98
  },
99
+ "128012": {
100
+ "content": "__bn__",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
104
  "single_word": false,
105
+ "special": true
106
  },
107
+ "128013": {
108
+ "content": "__br__",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
112
  "single_word": false,
113
+ "special": true
114
  },
115
+ "128014": {
116
+ "content": "__bs__",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
120
  "single_word": false,
121
+ "special": true
122
  },
123
+ "128015": {
124
+ "content": "__ca__",
125
  "lstrip": false,
126
  "normalized": false,
127
  "rstrip": false,
128
  "single_word": false,
129
+ "special": true
130
  },
131
+ "128016": {
132
+ "content": "__ceb__",
133
  "lstrip": false,
134
  "normalized": false,
135
  "rstrip": false,
136
  "single_word": false,
137
+ "special": true
138
  },
139
+ "128017": {
140
+ "content": "__cs__",
141
  "lstrip": false,
142
  "normalized": false,
143
  "rstrip": false,
144
  "single_word": false,
145
+ "special": true
146
  },
147
+ "128018": {
148
+ "content": "__cy__",
149
  "lstrip": false,
150
  "normalized": false,
151
  "rstrip": false,
152
  "single_word": false,
153
+ "special": true
154
  },
155
+ "128019": {
156
+ "content": "__da__",
157
  "lstrip": false,
158
  "normalized": false,
159
  "rstrip": false,
160
  "single_word": false,
161
+ "special": true
162
  },
163
+ "128020": {
164
+ "content": "__de__",
165
  "lstrip": false,
166
  "normalized": false,
167
  "rstrip": false,
168
  "single_word": false,
169
+ "special": true
170
  },
171
+ "128021": {
172
+ "content": "__el__",
173
  "lstrip": false,
174
  "normalized": false,
175
  "rstrip": false,
176
  "single_word": false,
177
+ "special": true
178
  },
179
+ "128022": {
180
+ "content": "__en__",
181
  "lstrip": false,
182
  "normalized": false,
183
  "rstrip": false,
184
  "single_word": false,
185
+ "special": true
186
  },
187
+ "128023": {
188
+ "content": "__es__",
189
  "lstrip": false,
190
  "normalized": false,
191
  "rstrip": false,
192
  "single_word": false,
193
+ "special": true
194
  },
195
+ "128024": {
196
+ "content": "__et__",
197
  "lstrip": false,
198
  "normalized": false,
199
  "rstrip": false,
200
  "single_word": false,
201
+ "special": true
202
  },
203
+ "128025": {
204
+ "content": "__fa__",
205
  "lstrip": false,
206
  "normalized": false,
207
  "rstrip": false,
208
  "single_word": false,
209
+ "special": true
210
  },
211
+ "128026": {
212
+ "content": "__ff__",
213
  "lstrip": false,
214
  "normalized": false,
215
  "rstrip": false,
216
  "single_word": false,
217
+ "special": true
218
  },
219
+ "128027": {
220
+ "content": "__fi__",
221
  "lstrip": false,
222
  "normalized": false,
223
  "rstrip": false,
224
  "single_word": false,
225
+ "special": true
226
  },
227
+ "128028": {
228
+ "content": "__fr__",
229
  "lstrip": false,
230
  "normalized": false,
231
  "rstrip": false,
232
  "single_word": false,
233
+ "special": true
234
  },
235
+ "128029": {
236
+ "content": "__fy__",
237
  "lstrip": false,
238
  "normalized": false,
239
  "rstrip": false,
240
  "single_word": false,
241
+ "special": true
242
  },
243
+ "128030": {
244
+ "content": "__ga__",
245
  "lstrip": false,
246
  "normalized": false,
247
  "rstrip": false,
248
  "single_word": false,
249
+ "special": true
250
  },
251
+ "128031": {
252
+ "content": "__gd__",
253
  "lstrip": false,
254
  "normalized": false,
255
  "rstrip": false,
256
  "single_word": false,
257
+ "special": true
258
  },
259
+ "128032": {
260
+ "content": "__gl__",
261
  "lstrip": false,
262
  "normalized": false,
263
  "rstrip": false,
264
  "single_word": false,
265
+ "special": true
266
  },
267
+ "128033": {
268
+ "content": "__gu__",
269
  "lstrip": false,
270
  "normalized": false,
271
  "rstrip": false,
272
  "single_word": false,
273
+ "special": true
274
  },
275
+ "128034": {
276
+ "content": "__ha__",
277
  "lstrip": false,
278
  "normalized": false,
279
  "rstrip": false,
280
  "single_word": false,
281
+ "special": true
282
  },
283
+ "128035": {
284
+ "content": "__he__",
285
  "lstrip": false,
286
  "normalized": false,
287
  "rstrip": false,
288
  "single_word": false,
289
+ "special": true
290
  },
291
+ "128036": {
292
+ "content": "__hi__",
293
  "lstrip": false,
294
  "normalized": false,
295
  "rstrip": false,
296
  "single_word": false,
297
+ "special": true
298
  },
299
+ "128037": {
300
+ "content": "__hr__",
301
  "lstrip": false,
302
  "normalized": false,
303
  "rstrip": false,
304
  "single_word": false,
305
+ "special": true
306
  },
307
+ "128038": {
308
+ "content": "__ht__",
309
  "lstrip": false,
310
  "normalized": false,
311
  "rstrip": false,
312
  "single_word": false,
313
+ "special": true
314
  },
315
+ "128039": {
316
+ "content": "__hu__",
317
  "lstrip": false,
318
  "normalized": false,
319
  "rstrip": false,
320
  "single_word": false,
321
+ "special": true
322
  },
323
+ "128040": {
324
+ "content": "__hy__",
325
  "lstrip": false,
326
  "normalized": false,
327
  "rstrip": false,
328
  "single_word": false,
329
+ "special": true
330
  },
331
+ "128041": {
332
+ "content": "__id__",
333
  "lstrip": false,
334
  "normalized": false,
335
  "rstrip": false,
336
  "single_word": false,
337
+ "special": true
338
  },
339
+ "128042": {
340
+ "content": "__ig__",
341
  "lstrip": false,
342
  "normalized": false,
343
  "rstrip": false,
344
  "single_word": false,
345
+ "special": true
346
  },
347
+ "128043": {
348
+ "content": "__ilo__",
349
  "lstrip": false,
350
  "normalized": false,
351
  "rstrip": false,
352
  "single_word": false,
353
+ "special": true
354
  },
355
+ "128044": {
356
+ "content": "__is__",
357
  "lstrip": false,
358
  "normalized": false,
359
  "rstrip": false,
360
  "single_word": false,
361
+ "special": true
362
  },
363
+ "128045": {
364
+ "content": "__it__",
365
  "lstrip": false,
366
  "normalized": false,
367
  "rstrip": false,
368
  "single_word": false,
369
+ "special": true
370
  },
371
+ "128046": {
372
+ "content": "__ja__",
373
  "lstrip": false,
374
  "normalized": false,
375
  "rstrip": false,
376
  "single_word": false,
377
+ "special": true
378
  },
379
+ "128047": {
380
+ "content": "__jv__",
381
  "lstrip": false,
382
  "normalized": false,
383
  "rstrip": false,
384
  "single_word": false,
385
+ "special": true
386
  },
387
+ "128048": {
388
+ "content": "__ka__",
389
  "lstrip": false,
390
  "normalized": false,
391
  "rstrip": false,
392
  "single_word": false,
393
+ "special": true
394
  },
395
+ "128049": {
396
+ "content": "__kk__",
397
  "lstrip": false,
398
  "normalized": false,
399
  "rstrip": false,
400
  "single_word": false,
401
+ "special": true
402
  },
403
+ "128050": {
404
+ "content": "__km__",
405
  "lstrip": false,
406
  "normalized": false,
407
  "rstrip": false,
408
  "single_word": false,
409
+ "special": true
410
  },
411
+ "128051": {
412
+ "content": "__kn__",
413
  "lstrip": false,
414
  "normalized": false,
415
  "rstrip": false,
416
  "single_word": false,
417
+ "special": true
418
  },
419
+ "128052": {
420
+ "content": "__ko__",
421
  "lstrip": false,
422
  "normalized": false,
423
  "rstrip": false,
424
  "single_word": false,
425
+ "special": true
426
  },
427
+ "128053": {
428
+ "content": "__lb__",
429
  "lstrip": false,
430
  "normalized": false,
431
  "rstrip": false,
432
  "single_word": false,
433
+ "special": true
434
  },
435
+ "128054": {
436
+ "content": "__lg__",
437
  "lstrip": false,
438
  "normalized": false,
439
  "rstrip": false,
440
  "single_word": false,
441
+ "special": true
442
  },
443
+ "128055": {
444
+ "content": "__ln__",
445
  "lstrip": false,
446
  "normalized": false,
447
  "rstrip": false,
448
  "single_word": false,
449
+ "special": true
450
  },
451
+ "128056": {
452
+ "content": "__lo__",
453
  "lstrip": false,
454
  "normalized": false,
455
  "rstrip": false,
456
  "single_word": false,
457
+ "special": true
458
  },
459
+ "128057": {
460
+ "content": "__lt__",
461
  "lstrip": false,
462
  "normalized": false,
463
  "rstrip": false,
464
  "single_word": false,
465
+ "special": true
466
  },
467
+ "128058": {
468
+ "content": "__lv__",
469
  "lstrip": false,
470
  "normalized": false,
471
  "rstrip": false,
472
  "single_word": false,
473
+ "special": true
474
  },
475
+ "128059": {
476
+ "content": "__mg__",
477
  "lstrip": false,
478
  "normalized": false,
479
  "rstrip": false,
480
  "single_word": false,
481
+ "special": true
482
  },
483
+ "128060": {
484
+ "content": "__mk__",
485
  "lstrip": false,
486
  "normalized": false,
487
  "rstrip": false,
488
  "single_word": false,
489
+ "special": true
490
  },
491
+ "128061": {
492
+ "content": "__ml__",
493
  "lstrip": false,
494
  "normalized": false,
495
  "rstrip": false,
496
  "single_word": false,
497
+ "special": true
498
  },
499
+ "128062": {
500
+ "content": "__mn__",
501
  "lstrip": false,
502
  "normalized": false,
503
  "rstrip": false,
504
  "single_word": false,
505
+ "special": true
506
  },
507
+ "128063": {
508
+ "content": "__mr__",
509
  "lstrip": false,
510
  "normalized": false,
511
  "rstrip": false,
512
  "single_word": false,
513
+ "special": true
514
  },
515
+ "128064": {
516
+ "content": "__ms__",
517
  "lstrip": false,
518
  "normalized": false,
519
  "rstrip": false,
520
  "single_word": false,
521
+ "special": true
522
  },
523
+ "128065": {
524
+ "content": "__my__",
525
  "lstrip": false,
526
  "normalized": false,
527
  "rstrip": false,
528
  "single_word": false,
529
+ "special": true
530
  },
531
+ "128066": {
532
+ "content": "__ne__",
533
  "lstrip": false,
534
  "normalized": false,
535
  "rstrip": false,
536
  "single_word": false,
537
+ "special": true
538
  },
539
+ "128067": {
540
+ "content": "__nl__",
541
  "lstrip": false,
542
  "normalized": false,
543
  "rstrip": false,
544
  "single_word": false,
545
+ "special": true
546
  },
547
+ "128068": {
548
+ "content": "__no__",
549
  "lstrip": false,
550
  "normalized": false,
551
  "rstrip": false,
552
  "single_word": false,
553
+ "special": true
554
  },
555
+ "128069": {
556
+ "content": "__ns__",
557
  "lstrip": false,
558
  "normalized": false,
559
  "rstrip": false,
560
  "single_word": false,
561
+ "special": true
562
  },
563
+ "128070": {
564
+ "content": "__oc__",
565
  "lstrip": false,
566
  "normalized": false,
567
  "rstrip": false,
568
  "single_word": false,
569
+ "special": true
570
  },
571
+ "128071": {
572
+ "content": "__or__",
573
  "lstrip": false,
574
  "normalized": false,
575
  "rstrip": false,
576
  "single_word": false,
577
+ "special": true
578
  },
579
+ "128072": {
580
+ "content": "__pa__",
581
  "lstrip": false,
582
  "normalized": false,
583
  "rstrip": false,
584
  "single_word": false,
585
+ "special": true
586
  },
587
+ "128073": {
588
+ "content": "__pl__",
589
  "lstrip": false,
590
  "normalized": false,
591
  "rstrip": false,
592
  "single_word": false,
593
+ "special": true
594
  },
595
+ "128074": {
596
+ "content": "__ps__",
597
  "lstrip": false,
598
  "normalized": false,
599
  "rstrip": false,
600
  "single_word": false,
601
+ "special": true
602
  },
603
+ "128075": {
604
+ "content": "__pt__",
605
  "lstrip": false,
606
  "normalized": false,
607
  "rstrip": false,
608
  "single_word": false,
609
  "special": true
610
  },
611
+ "128076": {
612
+ "content": "__ro__",
613
  "lstrip": false,
614
  "normalized": false,
615
  "rstrip": false,
616
  "single_word": false,
617
  "special": true
618
  },
619
+ "128077": {
620
+ "content": "__ru__",
621
  "lstrip": false,
622
  "normalized": false,
623
  "rstrip": false,
624
  "single_word": false,
625
+ "special": true
626
  },
627
+ "128078": {
628
+ "content": "__sd__",
629
  "lstrip": false,
630
  "normalized": false,
631
  "rstrip": false,
632
  "single_word": false,
633
+ "special": true
634
  },
635
+ "128079": {
636
+ "content": "__si__",
637
  "lstrip": false,
638
  "normalized": false,
639
  "rstrip": false,
640
  "single_word": false,
641
+ "special": true
642
  },
643
+ "128080": {
644
+ "content": "__sk__",
645
  "lstrip": false,
646
  "normalized": false,
647
  "rstrip": false,
648
  "single_word": false,
649
+ "special": true
650
  },
651
+ "128081": {
652
+ "content": "__sl__",
653
  "lstrip": false,
654
  "normalized": false,
655
  "rstrip": false,
656
  "single_word": false,
657
+ "special": true
658
  },
659
+ "128082": {
660
+ "content": "__so__",
661
  "lstrip": false,
662
  "normalized": false,
663
  "rstrip": false,
664
  "single_word": false,
665
+ "special": true
666
  },
667
+ "128083": {
668
+ "content": "__sq__",
669
  "lstrip": false,
670
  "normalized": false,
671
  "rstrip": false,
672
  "single_word": false,
673
+ "special": true
674
  },
675
+ "128084": {
676
+ "content": "__sr__",
677
  "lstrip": false,
678
  "normalized": false,
679
  "rstrip": false,
680
  "single_word": false,
681
+ "special": true
682
  },
683
+ "128085": {
684
+ "content": "__ss__",
685
  "lstrip": false,
686
  "normalized": false,
687
  "rstrip": false,
688
  "single_word": false,
689
+ "special": true
690
  },
691
+ "128086": {
692
+ "content": "__su__",
693
  "lstrip": false,
694
  "normalized": false,
695
  "rstrip": false,
696
  "single_word": false,
697
+ "special": true
698
  },
699
+ "128087": {
700
+ "content": "__sv__",
701
  "lstrip": false,
702
  "normalized": false,
703
  "rstrip": false,
704
  "single_word": false,
705
+ "special": true
706
  },
707
+ "128088": {
708
+ "content": "__sw__",
709
  "lstrip": false,
710
  "normalized": false,
711
  "rstrip": false,
712
  "single_word": false,
713
+ "special": true
714
  },
715
+ "128089": {
716
+ "content": "__ta__",
717
  "lstrip": false,
718
  "normalized": false,
719
  "rstrip": false,
720
  "single_word": false,
721
+ "special": true
722
  },
723
+ "128090": {
724
+ "content": "__th__",
725
  "lstrip": false,
726
  "normalized": false,
727
  "rstrip": false,
728
  "single_word": false,
729
+ "special": true
730
  },
731
+ "128091": {
732
+ "content": "__tl__",
733
  "lstrip": false,
734
  "normalized": false,
735
  "rstrip": false,
736
  "single_word": false,
737
+ "special": true
738
  },
739
+ "128092": {
740
+ "content": "__tn__",
741
  "lstrip": false,
742
  "normalized": false,
743
  "rstrip": false,
744
  "single_word": false,
745
+ "special": true
746
  },
747
+ "128093": {
748
+ "content": "__tr__",
749
  "lstrip": false,
750
  "normalized": false,
751
  "rstrip": false,
752
  "single_word": false,
753
+ "special": true
754
  },
755
+ "128094": {
756
+ "content": "__uk__",
757
  "lstrip": false,
758
  "normalized": false,
759
  "rstrip": false,
760
  "single_word": false,
761
+ "special": true
762
  },
763
+ "128095": {
764
+ "content": "__ur__",
765
  "lstrip": false,
766
  "normalized": false,
767
  "rstrip": false,
768
  "single_word": false,
769
+ "special": true
770
  },
771
+ "128096": {
772
+ "content": "__uz__",
773
  "lstrip": false,
774
  "normalized": false,
775
  "rstrip": false,
776
  "single_word": false,
777
+ "special": true
778
  },
779
+ "128097": {
780
+ "content": "__vi__",
781
  "lstrip": false,
782
  "normalized": false,
783
  "rstrip": false,
784
  "single_word": false,
785
+ "special": true
786
  },
787
+ "128098": {
788
+ "content": "__wo__",
789
  "lstrip": false,
790
  "normalized": false,
791
  "rstrip": false,
792
  "single_word": false,
793
+ "special": true
794
  },
795
+ "128099": {
796
+ "content": "__xh__",
797
  "lstrip": false,
798
  "normalized": false,
799
  "rstrip": false,
800
  "single_word": false,
801
+ "special": true
802
  },
803
+ "128100": {
804
+ "content": "__yi__",
805
  "lstrip": false,
806
  "normalized": false,
807
  "rstrip": false,
808
  "single_word": false,
809
+ "special": true
810
  },
811
+ "128101": {
812
+ "content": "__yo__",
813
  "lstrip": false,
814
  "normalized": false,
815
  "rstrip": false,
816
  "single_word": false,
817
+ "special": true
818
  },
819
+ "128102": {
820
+ "content": "__zh__",
821
  "lstrip": false,
822
  "normalized": false,
823
  "rstrip": false,
824
  "single_word": false,
825
+ "special": true
826
  },
827
+ "128103": {
828
+ "content": "__zu__",
829
  "lstrip": false,
830
  "normalized": false,
831
  "rstrip": false,
832
  "single_word": false,
833
+ "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
834
  }
835
  },
836
  "additional_special_tokens": [
837
+ "__af__",
838
+ "__am__",
839
+ "__ar__",
840
+ "__ast__",
841
+ "__az__",
842
+ "__ba__",
843
+ "__be__",
844
+ "__bg__",
845
+ "__bn__",
846
+ "__br__",
847
+ "__bs__",
848
+ "__ca__",
849
+ "__ceb__",
850
+ "__cs__",
851
+ "__cy__",
852
+ "__da__",
853
+ "__de__",
854
+ "__el__",
855
+ "__en__",
856
+ "__es__",
857
+ "__et__",
858
+ "__fa__",
859
+ "__ff__",
860
+ "__fi__",
861
+ "__fr__",
862
+ "__fy__",
863
+ "__ga__",
864
+ "__gd__",
865
+ "__gl__",
866
+ "__gu__",
867
+ "__ha__",
868
+ "__he__",
869
+ "__hi__",
870
+ "__hr__",
871
+ "__ht__",
872
+ "__hu__",
873
+ "__hy__",
874
+ "__id__",
875
+ "__ig__",
876
+ "__ilo__",
877
+ "__is__",
878
+ "__it__",
879
+ "__ja__",
880
+ "__jv__",
881
+ "__ka__",
882
+ "__kk__",
883
+ "__km__",
884
+ "__kn__",
885
+ "__ko__",
886
+ "__lb__",
887
+ "__lg__",
888
+ "__ln__",
889
+ "__lo__",
890
+ "__lt__",
891
+ "__lv__",
892
+ "__mg__",
893
+ "__mk__",
894
+ "__ml__",
895
+ "__mn__",
896
+ "__mr__",
897
+ "__ms__",
898
+ "__my__",
899
+ "__ne__",
900
+ "__nl__",
901
+ "__no__",
902
+ "__ns__",
903
+ "__oc__",
904
+ "__or__",
905
+ "__pa__",
906
+ "__pl__",
907
+ "__ps__",
908
+ "__pt__",
909
+ "__ro__",
910
+ "__ru__",
911
+ "__sd__",
912
+ "__si__",
913
+ "__sk__",
914
+ "__sl__",
915
+ "__so__",
916
+ "__sq__",
917
+ "__sr__",
918
+ "__ss__",
919
+ "__su__",
920
+ "__sv__",
921
+ "__sw__",
922
+ "__ta__",
923
+ "__th__",
924
+ "__tl__",
925
+ "__tn__",
926
+ "__tr__",
927
+ "__uk__",
928
+ "__ur__",
929
+ "__uz__",
930
+ "__vi__",
931
+ "__wo__",
932
+ "__xh__",
933
+ "__yi__",
934
+ "__yo__",
935
+ "__zh__",
936
+ "__zu__"
937
  ],
938
+ "bos_token": "<s>",
939
  "clean_up_tokenization_spaces": false,
940
+ "eos_token": "</s>",
941
  "extra_special_tokens": {},
942
+ "language_codes": "m2m100",
943
+ "model_max_length": 1024,
944
+ "num_madeup_words": 8,
945
  "pad_token": "<pad>",
946
+ "sep_token": "</s>",
947
  "sp_model_kwargs": {},
948
+ "src_lang": "en",
949
+ "tgt_lang": "ta",
950
+ "tokenizer_class": "M2M100Tokenizer",
951
+ "unk_token": "<unk>"
952
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1812825e4803cad79a0e9a2bce80522a09023d28aece225af33f9f7612408d82
3
- size 6225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf822e2bd53eead4ffb582af09beb757c5192f028b33ccfe0447aa0bb650db4
3
+ size 5969
vocab.json ADDED
The diff for this file is too large to render. See raw diff