Clemylia commited on
Commit
4e3a39c
·
verified ·
1 Parent(s): 81e7656

Premier modèle d'architecture gemma from scratch

Browse files
Files changed (3) hide show
  1. README.md +54 -0
  2. tokenizer.json +2064 -0
  3. tokenizer_config.json +20 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: Nephaella
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # Nephaella
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 0.0005
35
+ - train_batch_size: 8
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 4
39
+ - total_train_batch_size: 32
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 4
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 5.0.0
52
+ - Pytorch 2.10.0+cpu
53
+ - Datasets 4.0.0
54
+ - Tokenizers 0.22.2
tokenizer.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<pad>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "</s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<mask>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "प्रश्न:",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": false
59
+ },
60
+ {
61
+ "id": 6,
62
+ "content": "उत्तर:",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": false
68
+ }
69
+ ],
70
+ "normalizer": {
71
+ "type": "Replace",
72
+ "pattern": {
73
+ "String": " "
74
+ },
75
+ "content": "▁"
76
+ },
77
+ "pre_tokenizer": null,
78
+ "post_processor": {
79
+ "type": "TemplateProcessing",
80
+ "single": [
81
+ {
82
+ "Sequence": {
83
+ "id": "A",
84
+ "type_id": 0
85
+ }
86
+ }
87
+ ],
88
+ "pair": [
89
+ {
90
+ "Sequence": {
91
+ "id": "A",
92
+ "type_id": 0
93
+ }
94
+ },
95
+ {
96
+ "Sequence": {
97
+ "id": "B",
98
+ "type_id": 1
99
+ }
100
+ }
101
+ ],
102
+ "special_tokens": {}
103
+ },
104
+ "decoder": {
105
+ "type": "Sequence",
106
+ "decoders": [
107
+ {
108
+ "type": "Replace",
109
+ "pattern": {
110
+ "String": "▁"
111
+ },
112
+ "content": " "
113
+ },
114
+ {
115
+ "type": "ByteFallback"
116
+ },
117
+ {
118
+ "type": "Fuse"
119
+ }
120
+ ]
121
+ },
122
+ "model": {
123
+ "type": "BPE",
124
+ "dropout": null,
125
+ "unk_token": "<unk>",
126
+ "continuing_subword_prefix": null,
127
+ "end_of_word_suffix": null,
128
+ "fuse_unk": true,
129
+ "byte_fallback": true,
130
+ "ignore_merges": false,
131
+ "vocab": {
132
+ "<pad>": 0,
133
+ "</s>": 1,
134
+ "<s>": 2,
135
+ "<unk>": 3,
136
+ "<mask>": 4,
137
+ "प्रश्न:": 5,
138
+ "उत्तर:": 6,
139
+ "▁क": 7,
140
+ "▁प": 8,
141
+ "▁ह": 9,
142
+ "▁स": 10,
143
+ "▁म": 11,
144
+ "▁है": 12,
145
+ "्र": 13,
146
+ "र्": 14,
147
+ "या": 15,
148
+ "ें": 16,
149
+ "▁के": 17,
150
+ "▁ज": 18,
151
+ "▁ब": 19,
152
+ "▁ए": 20,
153
+ "ता": 21,
154
+ "▁प्र": 22,
155
+ "िक": 23,
156
+ "▁में": 24,
157
+ "▁उ": 25,
158
+ "ने": 26,
159
+ "▁अ": 27,
160
+ "▁कर": 28,
161
+ "▁का": 29,
162
+ "ों": 30,
163
+ "ना": 31,
164
+ "▁व": 32,
165
+ "▁ल": 33,
166
+ "▁पर": 34,
167
+ "▁कि": 35,
168
+ "▁हैं": 36,
169
+ "▁औ": 37,
170
+ "▁और": 38,
171
+ "लए": 39,
172
+ "ित": 40,
173
+ "▁द": 41,
174
+ "▁को": 42,
175
+ "ार": 43,
176
+ "क्": 44,
177
+ "▁त": 45,
178
+ "▁एक": 46,
179
+ "▁आ": 47,
180
+ "▁ग": 48,
181
+ "▁की": 49,
182
+ "ॉड": 50,
183
+ "▁(": 51,
184
+ "▁मॉड": 52,
185
+ "से": 53,
186
+ "्य": 54,
187
+ "▁[": 55,
188
+ "▁ट": 56,
189
+ "▁सं": 57,
190
+ "▁से": 58,
191
+ "▁मॉडल": 59,
192
+ "मा": 60,
193
+ "▁किया": 61,
194
+ "▁भ": 62,
195
+ "▁र": 63,
196
+ "ते": 64,
197
+ "▁न": 65,
198
+ "▁श": 66,
199
+ "कन": 67,
200
+ "ां": 68,
201
+ "▁लि": 69,
202
+ "स्": 70,
203
+ "ड़": 71,
204
+ "▁जा": 72,
205
+ "्ष": 73,
206
+ "▁लिए": 74,
207
+ "ोग": 75,
208
+ "लएम": 76,
209
+ "्या": 77,
210
+ "▁\"": 78,
211
+ "ाष": 79,
212
+ "▁उप": 80,
213
+ "▁एलए": 81,
214
+ "▁एलएलएम": 82,
215
+ "त्": 83,
216
+ "▁ड": 84,
217
+ "योग": 85,
218
+ "ाषा": 86,
219
+ "ोकन": 87,
220
+ "▁जो": 88,
221
+ "▁सा": 89,
222
+ "▁भाषा": 90,
223
+ "▁उपयोग": 91,
224
+ "कि": 92,
225
+ "के": 93,
226
+ "रण": 94,
227
+ "ाल": 95,
228
+ "20": 96,
229
+ "रा": 97,
230
+ "ेट": 98,
231
+ "ड़े": 99,
232
+ "दर्": 100,
233
+ "▁जि": 101,
234
+ "▁मा": 102,
235
+ "▁वि": 103,
236
+ "टी": 104,
237
+ "ती": 105,
238
+ "दा": 106,
239
+ "ूप": 107,
240
+ "▁य": 108,
241
+ "ेक्": 109,
242
+ "▁अन": 110,
243
+ "न्": 111,
244
+ "ूल": 112,
245
+ "▁थ": 113,
246
+ "▁रूप": 114,
247
+ "▁बड़े": 115,
248
+ "ाद": 116,
249
+ "▁इ": 117,
250
+ "▁जी": 118,
251
+ "▁या": 119,
252
+ "▁टोकन": 120,
253
+ "ंत": 121,
254
+ "पी": 122,
255
+ "ेटा": 123,
256
+ "▁पै": 124,
257
+ "▁हो": 125,
258
+ "िक्ष": 126,
259
+ "▁गया": 127,
260
+ "▁जाता": 128,
261
+ "▁प्रश": 129,
262
+ "ही": 130,
263
+ "्व": 131,
264
+ "मान": 132,
265
+ "र्म": 133,
266
+ "र्य": 134,
267
+ "▁[1": 135,
268
+ "▁सम": 136,
269
+ "▁साथ": 137,
270
+ "▁डेटा": 138,
271
+ "le": 139,
272
+ "ब्": 140,
273
+ "शन": 141,
274
+ "▁च": 142,
275
+ "ांस": 143,
276
+ "▁था": 144,
277
+ "▁नि": 145,
278
+ "▁ने": 146,
279
+ "▁अनु": 147,
280
+ "▁ट्र": 148,
281
+ "{\\": 149,
282
+ "ंग": 150,
283
+ "टर": 151,
284
+ "नी": 152,
285
+ "ला": 153,
286
+ "ल्": 154,
287
+ "▁1": 155,
288
+ "▁i": 156,
289
+ "र्क": 157,
290
+ "ूर्": 158,
291
+ "ैसे": 159,
292
+ "र्मर": 160,
293
+ "ांसफ": 161,
294
+ "▁उत्": 162,
295
+ "▁शब्": 163,
296
+ "▁करने": 164,
297
+ "ति": 165,
298
+ "नि": 166,
299
+ "मी": 167,
300
+ "ाव": 168,
301
+ "ोड": 169,
302
+ "201": 170,
303
+ "क्ष": 171,
304
+ "▁दे": 172,
305
+ "▁दो": 173,
306
+ "▁करता": 174,
307
+ "▁जीपी": 175,
308
+ "▁ट्रांसफ": 176,
309
+ "ty": 177,
310
+ "नक": 178,
311
+ "ीन": 179,
312
+ "▁पा": 180,
313
+ "▁बी": 181,
314
+ "▁यह": 182,
315
+ "▁सक": 183,
316
+ "▁क्ष": 184,
317
+ "▁जिस": 185,
318
+ "▁मूल": 186,
319
+ "▁कार्य": 187,
320
+ "▁प्रशिक्ष": 188,
321
+ "la": 189,
322
+ "ज़": 190,
323
+ "तर": 191,
324
+ "ष्": 192,
325
+ "कार": 193,
326
+ "धिक": 194,
327
+ "मता": 195,
328
+ "सेट": 196,
329
+ "▁आप": 197,
330
+ "▁गए": 198,
331
+ "▁वा": 199,
332
+ "▁हम": 200,
333
+ "दर्भ": 201,
334
+ "▁द्व": 202,
335
+ "▁वाल": 203,
336
+ "▁करना": 204,
337
+ "▁क्षमता": 205,
338
+ "▁संदर्भ": 206,
339
+ "▁डेटासेट": 207,
340
+ "di": 208,
341
+ "sp": 209,
342
+ "ys": 210,
343
+ "ंड": 211,
344
+ "आई": 212,
345
+ "ओं": 213,
346
+ "ढ़": 214,
347
+ "भी": 215,
348
+ "ले": 216,
349
+ "सं": 217,
350
+ "िल": 218,
351
+ "ौर": 219,
352
+ "▁ख": 220,
353
+ "▁फ": 221,
354
+ "त्र": 222,
355
+ "हीं": 223,
356
+ "िया": 224,
357
+ "्रे": 225,
358
+ "▁{\\": 226,
359
+ "▁इस": 227,
360
+ "▁कम": 228,
361
+ "▁तर": 229,
362
+ "▁रह": 230,
363
+ "disp": 231,
364
+ "lays": 232,
365
+ "tyle": 233,
366
+ "▁परि": 234,
367
+ "▁पाठ": 235,
368
+ "▁बना": 236,
369
+ "ार्मर": 237,
370
+ "▁अधिक": 238,
371
+ "▁शब्द": 239,
372
+ "▁प्रदर्": 240,
373
+ "displays": 241,
374
+ "displaystyle": 242,
375
+ "▁ट्रांसफार्मर": 243,
376
+ "वल": 244,
377
+ "हु": 245,
378
+ "ीक": 246,
379
+ "ुन": 247,
380
+ "क्त": 248,
381
+ "भाव": 249,
382
+ "स्त": 250,
383
+ "ारा": 251,
384
+ "ारी": 252,
385
+ "▁तक": 253,
386
+ "▁मश": 254,
387
+ "माने": 255,
388
+ "▁201": 256,
389
+ "▁एआई": 257,
390
+ "▁विश": 258,
391
+ "▁करते": 259,
392
+ "▁नहीं": 260,
393
+ "▁पूर्": 261,
394
+ "▁जीपीटी": 262,
395
+ "▁द्वारा": 263,
396
+ "▁पैमाने": 264,
397
+ "▁प्रदर्शन": 265,
398
+ "आर": 266,
399
+ "चर": 267,
400
+ "जी": 268,
401
+ "रे": 269,
402
+ "वि": 270,
403
+ "ाग": 271,
404
+ "▁)": 272,
405
+ "▁G": 273,
406
+ "इज़": 274,
407
+ "किट": 275,
408
+ "क्र": 276,
409
+ "दाह": 277,
410
+ "न्ह": 278,
411
+ "पाद": 279,
412
+ "ष्ट": 280,
413
+ "स्ट": 281,
414
+ "ोडर": 282,
415
+ "▁[3": 283,
416
+ "▁अप": 284,
417
+ "▁जब": 285,
418
+ "▁तो": 286,
419
+ "▁भी": 287,
420
+ "▁लग": 288,
421
+ "▁ही": 289,
422
+ "▁हु": 290,
423
+ "ंत्र": 291,
424
+ "इज़र": 292,
425
+ "▁आर्": 293,
426
+ "▁परत": 294,
427
+ "▁रहे": 295,
428
+ "▁विक": 296,
429
+ "▁समय": 297,
430
+ "दाहरण": 298,
431
+ "मान्य": 299,
432
+ "ेक्चर": 300,
433
+ "▁प्रत": 301,
434
+ "▁मशीन": 302,
435
+ "नाइज़र": 303,
436
+ "▁तंत्र": 304,
437
+ "▁आर्किट": 305,
438
+ "▁आर्किटेक्चर": 306,
439
+ "4]": 307,
440
+ "en": 308,
441
+ "eq": 309,
442
+ "og": 310,
443
+ "ok": 311,
444
+ "एम": 312,
445
+ "टव": 313,
446
+ "यू": 314,
447
+ "शल": 315,
448
+ "सी": 316,
449
+ "ाय": 317,
450
+ "ीय": 318,
451
+ "ुर": 319,
452
+ "ृत": 320,
453
+ "ेष": 321,
454
+ "▁ध": 322,
455
+ "ंतर": 323,
456
+ "ईआर": 324,
457
+ "करण": 325,
458
+ "खते": 326,
459
+ "बसे": 327,
460
+ "लता": 328,
461
+ "वाद": 329,
462
+ "िका": 330,
463
+ "ेंद": 331,
464
+ "▁[2": 332,
465
+ "▁": 333,
466
+ "क": 334,
467
+ "ा": 335,
468
+ "र": 336,
469
+ "े": 337,
470
+ "्": 338,
471
+ "ि": 339,
472
+ "न": 340,
473
+ "ं": 341,
474
+ "त": 342,
475
+ "म": 343,
476
+ "स": 344,
477
+ "प": 345,
478
+ "ह": 346,
479
+ "ल": 347,
480
+ "ी": 348,
481
+ "ो": 349,
482
+ "य": 350,
483
+ "ए": 351,
484
+ "ै": 352,
485
+ "ट": 353,
486
+ "व": 354,
487
+ "द": 355,
488
+ "ब": 356,
489
+ "ज": 357,
490
+ "ग": 358,
491
+ "ड": 359,
492
+ "श": 360,
493
+ ",": 361,
494
+ "।": 362,
495
+ "ू": 363,
496
+ "ष": 364,
497
+ "ु": 365,
498
+ "उ": 366,
499
+ "भ": 367,
500
+ "अ": 368,
501
+ "आ": 369,
502
+ "च": 370,
503
+ "1": 371,
504
+ "औ": 372,
505
+ "ण": 373,
506
+ "ॉ": 374,
507
+ "़": 375,
508
+ ")": 376,
509
+ "\"": 377,
510
+ "(": 378,
511
+ "0": 379,
512
+ "थ": 380,
513
+ "2": 381,
514
+ "ख": 382,
515
+ "ध": 383,
516
+ "[": 384,
517
+ "]": 385,
518
+ "e": 386,
519
+ "-": 387,
520
+ "ई": 388,
521
+ "इ": 389,
522
+ "फ": 390,
523
+ "l": 391,
524
+ "i": 392,
525
+ "s": 393,
526
+ "t": 394,
527
+ "{": 395,
528
+ "}": 396,
529
+ "o": 397,
530
+ "3": 398,
531
+ "y": 399,
532
+ "ौ": 400,
533
+ ".": 401,
534
+ "\\": 402,
535
+ "4": 403,
536
+ "ृ": 404,
537
+ "ठ": 405,
538
+ "a": 406,
539
+ "p": 407,
540
+ "r": 408,
541
+ "ओ": 409,
542
+ "छ": 410,
543
+ "9": 411,
544
+ "5": 412,
545
+ "7": 413,
546
+ "8": 414,
547
+ "k": 415,
548
+ "d": 416,
549
+ "ढ": 417,
550
+ "P": 418,
551
+ "n": 419,
552
+ "x": 420,
553
+ "ँ": 421,
554
+ ":": 422,
555
+ "G": 423,
556
+ "T": 424,
557
+ "我": 425,
558
+ "6": 426,
559
+ "M": 427,
560
+ "N": 428,
561
+ "g": 429,
562
+ "q": 430,
563
+ "झ": 431,
564
+ "S": 432,
565
+ "घ": 433,
566
+ "ञ": 434,
567
+ "'": 435,
568
+ "=": 436,
569
+ "?": 437,
570
+ "A": 438,
571
+ "V": 439,
572
+ "f": 440,
573
+ "型": 441,
574
+ "I": 442,
575
+ "L": 443,
576
+ "_": 444,
577
+ "c": 445,
578
+ "u": 446,
579
+ "ः": 447,
580
+ "ऑ": 448,
581
+ "$": 449,
582
+ "O": 450,
583
+ "m": 451,
584
+ "|": 452,
585
+ "⁡": 453,
586
+ "一": 454,
587
+ "个": 455,
588
+ "小": 456,
589
+ "是": 457,
590
+ "模": 458,
591
+ "的": 459,
592
+ "言": 460,
593
+ "语": 461,
594
+ "+": 462,
595
+ ";": 463,
596
+ ">": 464,
597
+ "C": 465,
598
+ "D": 466,
599
+ "Q": 467,
600
+ "^": 468,
601
+ "w": 469,
602
+ "ऊ": 470,
603
+ "ऐ": 471,
604
+ "∑": 472,
605
+ "−": 473,
606
+ "。": 474,
607
+ "不": 475,
608
+ "中": 476,
609
+ "主": 477,
610
+ "之": 478,
611
+ "了": 479,
612
+ "人": 480,
613
+ "会": 481,
614
+ "但": 482,
615
+ "其": 483,
616
+ "发": 484,
617
+ "员": 485,
618
+ "喜": 486,
619
+ "处": 487,
620
+ "复": 488,
621
+ "太": 489,
622
+ "常": 490,
623
+ "年": 491,
624
+ "开": 492,
625
+ "很": 493,
626
+ "微": 494,
627
+ "效": 495,
628
+ "有": 496,
629
+ "杂": 497,
630
+ "欢": 498,
631
+ "率": 499
632
+ },
633
+ "merges": [
634
+ [
635
+ "▁",
636
+ "क"
637
+ ],
638
+ [
639
+ "▁",
640
+ "प"
641
+ ],
642
+ [
643
+ "▁",
644
+ "ह"
645
+ ],
646
+ [
647
+ "▁",
648
+ "स"
649
+ ],
650
+ [
651
+ "▁",
652
+ "म"
653
+ ],
654
+ [
655
+ "▁ह",
656
+ "ै"
657
+ ],
658
+ [
659
+ "्",
660
+ "र"
661
+ ],
662
+ [
663
+ "र",
664
+ "्"
665
+ ],
666
+ [
667
+ "य",
668
+ "ा"
669
+ ],
670
+ [
671
+ "े",
672
+ "ं"
673
+ ],
674
+ [
675
+ "▁",
676
+ "के"
677
+ ],
678
+ [
679
+ "▁क",
680
+ "े"
681
+ ],
682
+ [
683
+ "▁",
684
+ "ज"
685
+ ],
686
+ [
687
+ "▁",
688
+ "ब"
689
+ ],
690
+ [
691
+ "▁",
692
+ "ए"
693
+ ],
694
+ [
695
+ "त",
696
+ "ा"
697
+ ],
698
+ [
699
+ "▁प",
700
+ "्र"
701
+ ],
702
+ [
703
+ "ि",
704
+ "क"
705
+ ],
706
+ [
707
+ "▁म",
708
+ "ें"
709
+ ],
710
+ [
711
+ "▁",
712
+ "उ"
713
+ ],
714
+ [
715
+ "न",
716
+ "े"
717
+ ],
718
+ [
719
+ "▁",
720
+ "अ"
721
+ ],
722
+ [
723
+ "▁क",
724
+ "र"
725
+ ],
726
+ [
727
+ "▁क",
728
+ "ा"
729
+ ],
730
+ [
731
+ "ो",
732
+ "ं"
733
+ ],
734
+ [
735
+ "न",
736
+ "ा"
737
+ ],
738
+ [
739
+ "▁",
740
+ "व"
741
+ ],
742
+ [
743
+ "▁",
744
+ "ल"
745
+ ],
746
+ [
747
+ "▁प",
748
+ "र"
749
+ ],
750
+ [
751
+ "▁",
752
+ "कि"
753
+ ],
754
+ [
755
+ "▁क",
756
+ "ि"
757
+ ],
758
+ [
759
+ "▁है",
760
+ "ं"
761
+ ],
762
+ [
763
+ "▁",
764
+ "औ"
765
+ ],
766
+ [
767
+ "▁औ",
768
+ "र"
769
+ ],
770
+ [
771
+ "ल",
772
+ "ए"
773
+ ],
774
+ [
775
+ "ि",
776
+ "त"
777
+ ],
778
+ [
779
+ "▁",
780
+ "द"
781
+ ],
782
+ [
783
+ "▁क",
784
+ "ो"
785
+ ],
786
+ [
787
+ "ा",
788
+ "र"
789
+ ],
790
+ [
791
+ "क",
792
+ "्"
793
+ ],
794
+ [
795
+ "▁",
796
+ "त"
797
+ ],
798
+ [
799
+ "▁ए",
800
+ "क"
801
+ ],
802
+ [
803
+ "▁",
804
+ "आ"
805
+ ],
806
+ [
807
+ "▁",
808
+ "ग"
809
+ ],
810
+ [
811
+ "▁क",
812
+ "ी"
813
+ ],
814
+ [
815
+ "ॉ",
816
+ "ड"
817
+ ],
818
+ [
819
+ "▁",
820
+ "("
821
+ ],
822
+ [
823
+ "▁म",
824
+ "ॉड"
825
+ ],
826
+ [
827
+ "स",
828
+ "े"
829
+ ],
830
+ [
831
+ "्",
832
+ "य"
833
+ ],
834
+ [
835
+ "▁",
836
+ "["
837
+ ],
838
+ [
839
+ "▁",
840
+ "ट"
841
+ ],
842
+ [
843
+ "▁",
844
+ "सं"
845
+ ],
846
+ [
847
+ "▁स",
848
+ "ं"
849
+ ],
850
+ [
851
+ "▁",
852
+ "से"
853
+ ],
854
+ [
855
+ "▁स",
856
+ "े"
857
+ ],
858
+ [
859
+ "▁मॉड",
860
+ "ल"
861
+ ],
862
+ [
863
+ "म",
864
+ "ा"
865
+ ],
866
+ [
867
+ "▁क",
868
+ "िया"
869
+ ],
870
+ [
871
+ "▁कि",
872
+ "या"
873
+ ],
874
+ [
875
+ "▁",
876
+ "भ"
877
+ ],
878
+ [
879
+ "▁",
880
+ "र"
881
+ ],
882
+ [
883
+ "त",
884
+ "े"
885
+ ],
886
+ [
887
+ "▁",
888
+ "न"
889
+ ],
890
+ [
891
+ "▁",
892
+ "श"
893
+ ],
894
+ [
895
+ "क",
896
+ "न"
897
+ ],
898
+ [
899
+ "ा",
900
+ "ं"
901
+ ],
902
+ [
903
+ "▁ल",
904
+ "ि"
905
+ ],
906
+ [
907
+ "स",
908
+ "्"
909
+ ],
910
+ [
911
+ "ड",
912
+ "़"
913
+ ],
914
+ [
915
+ "▁ज",
916
+ "ा"
917
+ ],
918
+ [
919
+ "्",
920
+ "ष"
921
+ ],
922
+ [
923
+ "▁लि",
924
+ "ए"
925
+ ],
926
+ [
927
+ "ो",
928
+ "ग"
929
+ ],
930
+ [
931
+ "ल",
932
+ "एम"
933
+ ],
934
+ [
935
+ "लए",
936
+ "म"
937
+ ],
938
+ [
939
+ "्",
940
+ "या"
941
+ ],
942
+ [
943
+ "्य",
944
+ "ा"
945
+ ],
946
+ [
947
+ "▁",
948
+ "\""
949
+ ],
950
+ [
951
+ "ा",
952
+ "ष"
953
+ ],
954
+ [
955
+ "▁उ",
956
+ "प"
957
+ ],
958
+ [
959
+ "▁ए",
960
+ "लए"
961
+ ],
962
+ [
963
+ "▁एलए",
964
+ "लएम"
965
+ ],
966
+ [
967
+ "त",
968
+ "्"
969
+ ],
970
+ [
971
+ "▁",
972
+ "ड"
973
+ ],
974
+ [
975
+ "य",
976
+ "ोग"
977
+ ],
978
+ [
979
+ "ाष",
980
+ "ा"
981
+ ],
982
+ [
983
+ "ो",
984
+ "कन"
985
+ ],
986
+ [
987
+ "▁ज",
988
+ "ो"
989
+ ],
990
+ [
991
+ "▁स",
992
+ "ा"
993
+ ],
994
+ [
995
+ "▁भ",
996
+ "ाषा"
997
+ ],
998
+ [
999
+ "▁उप",
1000
+ "योग"
1001
+ ],
1002
+ [
1003
+ "क",
1004
+ "ि"
1005
+ ],
1006
+ [
1007
+ "क",
1008
+ "े"
1009
+ ],
1010
+ [
1011
+ "र",
1012
+ "ण"
1013
+ ],
1014
+ [
1015
+ "ा",
1016
+ "ल"
1017
+ ],
1018
+ [
1019
+ "2",
1020
+ "0"
1021
+ ],
1022
+ [
1023
+ "र",
1024
+ "ा"
1025
+ ],
1026
+ [
1027
+ "े",
1028
+ "ट"
1029
+ ],
1030
+ [
1031
+ "ड़",
1032
+ "े"
1033
+ ],
1034
+ [
1035
+ "द",
1036
+ "र्"
1037
+ ],
1038
+ [
1039
+ "▁ज",
1040
+ "ि"
1041
+ ],
1042
+ [
1043
+ "▁",
1044
+ "मा"
1045
+ ],
1046
+ [
1047
+ "▁म",
1048
+ "ा"
1049
+ ],
1050
+ [
1051
+ "▁",
1052
+ "वि"
1053
+ ],
1054
+ [
1055
+ "▁व",
1056
+ "ि"
1057
+ ],
1058
+ [
1059
+ "ट",
1060
+ "ी"
1061
+ ],
1062
+ [
1063
+ "त",
1064
+ "ी"
1065
+ ],
1066
+ [
1067
+ "द",
1068
+ "ा"
1069
+ ],
1070
+ [
1071
+ "ू",
1072
+ "प"
1073
+ ],
1074
+ [
1075
+ "▁",
1076
+ "य"
1077
+ ],
1078
+ [
1079
+ "े",
1080
+ "क्"
1081
+ ],
1082
+ [
1083
+ "▁अ",
1084
+ "न"
1085
+ ],
1086
+ [
1087
+ "न",
1088
+ "्"
1089
+ ],
1090
+ [
1091
+ "ू",
1092
+ "ल"
1093
+ ],
1094
+ [
1095
+ "▁",
1096
+ "थ"
1097
+ ],
1098
+ [
1099
+ "▁र",
1100
+ "ूप"
1101
+ ],
1102
+ [
1103
+ "▁ब",
1104
+ "ड़े"
1105
+ ],
1106
+ [
1107
+ "ा",
1108
+ "द"
1109
+ ],
1110
+ [
1111
+ "▁",
1112
+ "इ"
1113
+ ],
1114
+ [
1115
+ "▁",
1116
+ "जी"
1117
+ ],
1118
+ [
1119
+ "▁ज",
1120
+ "ी"
1121
+ ],
1122
+ [
1123
+ "▁",
1124
+ "या"
1125
+ ],
1126
+ [
1127
+ "▁य",
1128
+ "ा"
1129
+ ],
1130
+ [
1131
+ "▁ट",
1132
+ "ोकन"
1133
+ ],
1134
+ [
1135
+ "ं",
1136
+ "त"
1137
+ ],
1138
+ [
1139
+ "प",
1140
+ "ी"
1141
+ ],
1142
+ [
1143
+ "ेट",
1144
+ "ा"
1145
+ ],
1146
+ [
1147
+ "▁प",
1148
+ "ै"
1149
+ ],
1150
+ [
1151
+ "▁ह",
1152
+ "ो"
1153
+ ],
1154
+ [
1155
+ "ि",
1156
+ "क्ष"
1157
+ ],
1158
+ [
1159
+ "िक",
1160
+ "्ष"
1161
+ ],
1162
+ [
1163
+ "▁ग",
1164
+ "या"
1165
+ ],
1166
+ [
1167
+ "▁जा",
1168
+ "ता"
1169
+ ],
1170
+ [
1171
+ "▁प्र",
1172
+ "श"
1173
+ ],
1174
+ [
1175
+ "ह",
1176
+ "ी"
1177
+ ],
1178
+ [
1179
+ "्",
1180
+ "व"
1181
+ ],
1182
+ [
1183
+ "मा",
1184
+ "न"
1185
+ ],
1186
+ [
1187
+ "र्",
1188
+ "म"
1189
+ ],
1190
+ [
1191
+ "र",
1192
+ "्य"
1193
+ ],
1194
+ [
1195
+ "र्",
1196
+ "य"
1197
+ ],
1198
+ [
1199
+ "▁[",
1200
+ "1"
1201
+ ],
1202
+ [
1203
+ "▁स",
1204
+ "म"
1205
+ ],
1206
+ [
1207
+ "▁सा",
1208
+ "थ"
1209
+ ],
1210
+ [
1211
+ "▁ड",
1212
+ "ेटा"
1213
+ ],
1214
+ [
1215
+ "l",
1216
+ "e"
1217
+ ],
1218
+ [
1219
+ "ब",
1220
+ "्"
1221
+ ],
1222
+ [
1223
+ "श",
1224
+ "न"
1225
+ ],
1226
+ [
1227
+ "▁",
1228
+ "च"
1229
+ ],
1230
+ [
1231
+ "ां",
1232
+ "स"
1233
+ ],
1234
+ [
1235
+ "▁थ",
1236
+ "ा"
1237
+ ],
1238
+ [
1239
+ "▁",
1240
+ "नि"
1241
+ ],
1242
+ [
1243
+ "▁न",
1244
+ "ि"
1245
+ ],
1246
+ [
1247
+ "▁",
1248
+ "ने"
1249
+ ],
1250
+ [
1251
+ "▁न",
1252
+ "े"
1253
+ ],
1254
+ [
1255
+ "▁अन",
1256
+ "ु"
1257
+ ],
1258
+ [
1259
+ "▁ट",
1260
+ "्र"
1261
+ ],
1262
+ [
1263
+ "{",
1264
+ "\\"
1265
+ ],
1266
+ [
1267
+ "ं",
1268
+ "ग"
1269
+ ],
1270
+ [
1271
+ "ट",
1272
+ "र"
1273
+ ],
1274
+ [
1275
+ "न",
1276
+ "ी"
1277
+ ],
1278
+ [
1279
+ "ल",
1280
+ "ा"
1281
+ ],
1282
+ [
1283
+ "ल",
1284
+ "्"
1285
+ ],
1286
+ [
1287
+ "▁",
1288
+ "1"
1289
+ ],
1290
+ [
1291
+ "▁",
1292
+ "i"
1293
+ ],
1294
+ [
1295
+ "र्",
1296
+ "क"
1297
+ ],
1298
+ [
1299
+ "ू",
1300
+ "र्"
1301
+ ],
1302
+ [
1303
+ "ै",
1304
+ "से"
1305
+ ],
1306
+ [
1307
+ "र्म",
1308
+ "र"
1309
+ ],
1310
+ [
1311
+ "ांस",
1312
+ "फ"
1313
+ ],
1314
+ [
1315
+ "▁उ",
1316
+ "त्"
1317
+ ],
1318
+ [
1319
+ "▁श",
1320
+ "ब्"
1321
+ ],
1322
+ [
1323
+ "▁कर",
1324
+ "ने"
1325
+ ],
1326
+ [
1327
+ "त",
1328
+ "ि"
1329
+ ],
1330
+ [
1331
+ "न",
1332
+ "ि"
1333
+ ],
1334
+ [
1335
+ "म",
1336
+ "ी"
1337
+ ],
1338
+ [
1339
+ "ा",
1340
+ "व"
1341
+ ],
1342
+ [
1343
+ "ो",
1344
+ "ड"
1345
+ ],
1346
+ [
1347
+ "20",
1348
+ "1"
1349
+ ],
1350
+ [
1351
+ "क",
1352
+ "्ष"
1353
+ ],
1354
+ [
1355
+ "क्",
1356
+ "ष"
1357
+ ],
1358
+ [
1359
+ "▁द",
1360
+ "े"
1361
+ ],
1362
+ [
1363
+ "▁द",
1364
+ "ो"
1365
+ ],
1366
+ [
1367
+ "▁कर",
1368
+ "ता"
1369
+ ],
1370
+ [
1371
+ "▁जी",
1372
+ "पी"
1373
+ ],
1374
+ [
1375
+ "▁ट्र",
1376
+ "ांसफ"
1377
+ ],
1378
+ [
1379
+ "t",
1380
+ "y"
1381
+ ],
1382
+ [
1383
+ "न",
1384
+ "क"
1385
+ ],
1386
+ [
1387
+ "ी",
1388
+ "न"
1389
+ ],
1390
+ [
1391
+ "▁प",
1392
+ "ा"
1393
+ ],
1394
+ [
1395
+ "▁ब",
1396
+ "ी"
1397
+ ],
1398
+ [
1399
+ "▁य",
1400
+ "ह"
1401
+ ],
1402
+ [
1403
+ "▁स",
1404
+ "क"
1405
+ ],
1406
+ [
1407
+ "▁",
1408
+ "क्ष"
1409
+ ],
1410
+ [
1411
+ "▁क",
1412
+ "्ष"
1413
+ ],
1414
+ [
1415
+ "▁जि",
1416
+ "स"
1417
+ ],
1418
+ [
1419
+ "▁म",
1420
+ "ूल"
1421
+ ],
1422
+ [
1423
+ "▁का",
1424
+ "र्य"
1425
+ ],
1426
+ [
1427
+ "▁प्रश",
1428
+ "िक्ष"
1429
+ ],
1430
+ [
1431
+ "l",
1432
+ "a"
1433
+ ],
1434
+ [
1435
+ "ज",
1436
+ "़"
1437
+ ],
1438
+ [
1439
+ "त",
1440
+ "र"
1441
+ ],
1442
+ [
1443
+ "ष",
1444
+ "्"
1445
+ ],
1446
+ [
1447
+ "क",
1448
+ "ार"
1449
+ ],
1450
+ [
1451
+ "ध",
1452
+ "िक"
1453
+ ],
1454
+ [
1455
+ "म",
1456
+ "ता"
1457
+ ],
1458
+ [
1459
+ "स",
1460
+ "ेट"
1461
+ ],
1462
+ [
1463
+ "से",
1464
+ "ट"
1465
+ ],
1466
+ [
1467
+ "▁आ",
1468
+ "प"
1469
+ ],
1470
+ [
1471
+ "▁ग",
1472
+ "ए"
1473
+ ],
1474
+ [
1475
+ "▁व",
1476
+ "ा"
1477
+ ],
1478
+ [
1479
+ "▁ह",
1480
+ "म"
1481
+ ],
1482
+ [
1483
+ "दर्",
1484
+ "भ"
1485
+ ],
1486
+ [
1487
+ "▁द",
1488
+ "्व"
1489
+ ],
1490
+ [
1491
+ "▁व",
1492
+ "ाल"
1493
+ ],
1494
+ [
1495
+ "▁वा",
1496
+ "ल"
1497
+ ],
1498
+ [
1499
+ "▁कर",
1500
+ "ना"
1501
+ ],
1502
+ [
1503
+ "▁क्ष",
1504
+ "मता"
1505
+ ],
1506
+ [
1507
+ "▁सं",
1508
+ "दर्भ"
1509
+ ],
1510
+ [
1511
+ "▁डेटा",
1512
+ "सेट"
1513
+ ],
1514
+ [
1515
+ "d",
1516
+ "i"
1517
+ ],
1518
+ [
1519
+ "s",
1520
+ "p"
1521
+ ],
1522
+ [
1523
+ "y",
1524
+ "s"
1525
+ ],
1526
+ [
1527
+ "ं",
1528
+ "ड"
1529
+ ],
1530
+ [
1531
+ "आ",
1532
+ "ई"
1533
+ ],
1534
+ [
1535
+ "ओ",
1536
+ "ं"
1537
+ ],
1538
+ [
1539
+ "ढ",
1540
+ "़"
1541
+ ],
1542
+ [
1543
+ "भ",
1544
+ "ी"
1545
+ ],
1546
+ [
1547
+ "ल",
1548
+ "े"
1549
+ ],
1550
+ [
1551
+ "स",
1552
+ "ं"
1553
+ ],
1554
+ [
1555
+ "ि",
1556
+ "ल"
1557
+ ],
1558
+ [
1559
+ "ौ",
1560
+ "र"
1561
+ ],
1562
+ [
1563
+ "▁",
1564
+ "ख"
1565
+ ],
1566
+ [
1567
+ "▁",
1568
+ "फ"
1569
+ ],
1570
+ [
1571
+ "त",
1572
+ "्र"
1573
+ ],
1574
+ [
1575
+ "त्",
1576
+ "र"
1577
+ ],
1578
+ [
1579
+ "ही",
1580
+ "ं"
1581
+ ],
1582
+ [
1583
+ "ि",
1584
+ "या"
1585
+ ],
1586
+ [
1587
+ "्",
1588
+ "रे"
1589
+ ],
1590
+ [
1591
+ "्र",
1592
+ "े"
1593
+ ],
1594
+ [
1595
+ "▁",
1596
+ "{\\"
1597
+ ],
1598
+ [
1599
+ "▁इ",
1600
+ "स"
1601
+ ],
1602
+ [
1603
+ "▁क",
1604
+ "म"
1605
+ ],
1606
+ [
1607
+ "▁",
1608
+ "तर"
1609
+ ],
1610
+ [
1611
+ "▁त",
1612
+ "र"
1613
+ ],
1614
+ [
1615
+ "▁र",
1616
+ "ह"
1617
+ ],
1618
+ [
1619
+ "di",
1620
+ "sp"
1621
+ ],
1622
+ [
1623
+ "la",
1624
+ "ys"
1625
+ ],
1626
+ [
1627
+ "ty",
1628
+ "le"
1629
+ ],
1630
+ [
1631
+ "▁पर",
1632
+ "ि"
1633
+ ],
1634
+ [
1635
+ "▁पा",
1636
+ "ठ"
1637
+ ],
1638
+ [
1639
+ "▁ब",
1640
+ "ना"
1641
+ ],
1642
+ [
1643
+ "ा",
1644
+ "र्मर"
1645
+ ],
1646
+ [
1647
+ "▁अ",
1648
+ "धिक"
1649
+ ],
1650
+ [
1651
+ "▁शब्",
1652
+ "द"
1653
+ ],
1654
+ [
1655
+ "▁प्र",
1656
+ "दर्"
1657
+ ],
1658
+ [
1659
+ "disp",
1660
+ "lays"
1661
+ ],
1662
+ [
1663
+ "displays",
1664
+ "tyle"
1665
+ ],
1666
+ [
1667
+ "▁ट्रांसफ",
1668
+ "ार्मर"
1669
+ ],
1670
+ [
1671
+ "व",
1672
+ "ल"
1673
+ ],
1674
+ [
1675
+ "ह",
1676
+ "ु"
1677
+ ],
1678
+ [
1679
+ "ी",
1680
+ "क"
1681
+ ],
1682
+ [
1683
+ "ु",
1684
+ "न"
1685
+ ],
1686
+ [
1687
+ "क्",
1688
+ "त"
1689
+ ],
1690
+ [
1691
+ "भ",
1692
+ "ाव"
1693
+ ],
1694
+ [
1695
+ "स्",
1696
+ "त"
1697
+ ],
1698
+ [
1699
+ "ा",
1700
+ "रा"
1701
+ ],
1702
+ [
1703
+ "ार",
1704
+ "ा"
1705
+ ],
1706
+ [
1707
+ "ार",
1708
+ "ी"
1709
+ ],
1710
+ [
1711
+ "▁त",
1712
+ "क"
1713
+ ],
1714
+ [
1715
+ "▁म",
1716
+ "श"
1717
+ ],
1718
+ [
1719
+ "मा",
1720
+ "ने"
1721
+ ],
1722
+ [
1723
+ "मान",
1724
+ "े"
1725
+ ],
1726
+ [
1727
+ "▁",
1728
+ "201"
1729
+ ],
1730
+ [
1731
+ "▁ए",
1732
+ "आई"
1733
+ ],
1734
+ [
1735
+ "▁वि",
1736
+ "श"
1737
+ ],
1738
+ [
1739
+ "▁कर",
1740
+ "ते"
1741
+ ],
1742
+ [
1743
+ "▁न",
1744
+ "हीं"
1745
+ ],
1746
+ [
1747
+ "▁प",
1748
+ "ूर्"
1749
+ ],
1750
+ [
1751
+ "▁जीपी",
1752
+ "टी"
1753
+ ],
1754
+ [
1755
+ "▁द्व",
1756
+ "ारा"
1757
+ ],
1758
+ [
1759
+ "▁पै",
1760
+ "माने"
1761
+ ],
1762
+ [
1763
+ "▁प्रदर्",
1764
+ "शन"
1765
+ ],
1766
+ [
1767
+ "आ",
1768
+ "र"
1769
+ ],
1770
+ [
1771
+ "च",
1772
+ "र"
1773
+ ],
1774
+ [
1775
+ "ज",
1776
+ "ी"
1777
+ ],
1778
+ [
1779
+ "र",
1780
+ "े"
1781
+ ],
1782
+ [
1783
+ "व",
1784
+ "ि"
1785
+ ],
1786
+ [
1787
+ "ा",
1788
+ "ग"
1789
+ ],
1790
+ [
1791
+ "▁",
1792
+ ")"
1793
+ ],
1794
+ [
1795
+ "▁",
1796
+ "G"
1797
+ ],
1798
+ [
1799
+ "इ",
1800
+ "ज़"
1801
+ ],
1802
+ [
1803
+ "कि",
1804
+ "ट"
1805
+ ],
1806
+ [
1807
+ "क",
1808
+ "्र"
1809
+ ],
1810
+ [
1811
+ "क्",
1812
+ "र"
1813
+ ],
1814
+ [
1815
+ "दा",
1816
+ "ह"
1817
+ ],
1818
+ [
1819
+ "न्",
1820
+ "ह"
1821
+ ],
1822
+ [
1823
+ "प",
1824
+ "ाद"
1825
+ ],
1826
+ [
1827
+ "ष्",
1828
+ "ट"
1829
+ ],
1830
+ [
1831
+ "स्",
1832
+ "ट"
1833
+ ],
1834
+ [
1835
+ "ोड",
1836
+ "र"
1837
+ ],
1838
+ [
1839
+ "▁[",
1840
+ "3"
1841
+ ],
1842
+ [
1843
+ "▁अ",
1844
+ "प"
1845
+ ],
1846
+ [
1847
+ "▁ज",
1848
+ "ब"
1849
+ ],
1850
+ [
1851
+ "▁त",
1852
+ "ो"
1853
+ ],
1854
+ [
1855
+ "▁",
1856
+ "भी"
1857
+ ],
1858
+ [
1859
+ "▁भ",
1860
+ "ी"
1861
+ ],
1862
+ [
1863
+ "▁ल",
1864
+ "ग"
1865
+ ],
1866
+ [
1867
+ "▁",
1868
+ "ही"
1869
+ ],
1870
+ [
1871
+ "▁ह",
1872
+ "ी"
1873
+ ],
1874
+ [
1875
+ "▁",
1876
+ "हु"
1877
+ ],
1878
+ [
1879
+ "▁ह",
1880
+ "ु"
1881
+ ],
1882
+ [
1883
+ "ं",
1884
+ "त्र"
1885
+ ],
1886
+ [
1887
+ "ंत",
1888
+ "्र"
1889
+ ],
1890
+ [
1891
+ "इज़",
1892
+ "र"
1893
+ ],
1894
+ [
1895
+ "▁आ",
1896
+ "र्"
1897
+ ],
1898
+ [
1899
+ "▁पर",
1900
+ "त"
1901
+ ],
1902
+ [
1903
+ "▁रह",
1904
+ "े"
1905
+ ],
1906
+ [
1907
+ "▁व",
1908
+ "िक"
1909
+ ],
1910
+ [
1911
+ "▁वि",
1912
+ "क"
1913
+ ],
1914
+ [
1915
+ "▁सम",
1916
+ "य"
1917
+ ],
1918
+ [
1919
+ "दाह",
1920
+ "रण"
1921
+ ],
1922
+ [
1923
+ "मान",
1924
+ "्य"
1925
+ ],
1926
+ [
1927
+ "ेक्",
1928
+ "चर"
1929
+ ],
1930
+ [
1931
+ "▁प्र",
1932
+ "त"
1933
+ ],
1934
+ [
1935
+ "▁मश",
1936
+ "ीन"
1937
+ ],
1938
+ [
1939
+ "ना",
1940
+ "इज़र"
1941
+ ],
1942
+ [
1943
+ "▁त",
1944
+ "ंत्र"
1945
+ ],
1946
+ [
1947
+ "▁आर्",
1948
+ "किट"
1949
+ ],
1950
+ [
1951
+ "▁आर्किट",
1952
+ "ेक्चर"
1953
+ ],
1954
+ [
1955
+ "4",
1956
+ "]"
1957
+ ],
1958
+ [
1959
+ "e",
1960
+ "n"
1961
+ ],
1962
+ [
1963
+ "e",
1964
+ "q"
1965
+ ],
1966
+ [
1967
+ "o",
1968
+ "g"
1969
+ ],
1970
+ [
1971
+ "o",
1972
+ "k"
1973
+ ],
1974
+ [
1975
+ "ए",
1976
+ "म"
1977
+ ],
1978
+ [
1979
+ "ट",
1980
+ "व"
1981
+ ],
1982
+ [
1983
+ "य",
1984
+ "ू"
1985
+ ],
1986
+ [
1987
+ "श",
1988
+ "ल"
1989
+ ],
1990
+ [
1991
+ "स",
1992
+ "ी"
1993
+ ],
1994
+ [
1995
+ "ा",
1996
+ "य"
1997
+ ],
1998
+ [
1999
+ "ी",
2000
+ "य"
2001
+ ],
2002
+ [
2003
+ "ु",
2004
+ "र"
2005
+ ],
2006
+ [
2007
+ "ृ",
2008
+ "त"
2009
+ ],
2010
+ [
2011
+ "े",
2012
+ "ष"
2013
+ ],
2014
+ [
2015
+ "▁",
2016
+ "ध"
2017
+ ],
2018
+ [
2019
+ "ं",
2020
+ "तर"
2021
+ ],
2022
+ [
2023
+ "ंत",
2024
+ "र"
2025
+ ],
2026
+ [
2027
+ "ई",
2028
+ "आर"
2029
+ ],
2030
+ [
2031
+ "क",
2032
+ "रण"
2033
+ ],
2034
+ [
2035
+ "ख",
2036
+ "ते"
2037
+ ],
2038
+ [
2039
+ "ब",
2040
+ "से"
2041
+ ],
2042
+ [
2043
+ "ल",
2044
+ "ता"
2045
+ ],
2046
+ [
2047
+ "व",
2048
+ "ाद"
2049
+ ],
2050
+ [
2051
+ "िक",
2052
+ "ा"
2053
+ ],
2054
+ [
2055
+ "ें",
2056
+ "द"
2057
+ ],
2058
+ [
2059
+ "▁[",
2060
+ "2"
2061
+ ]
2062
+ ]
2063
+ }
2064
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "extra_special_tokens": [
6
+ "<pad>",
7
+ "</s>",
8
+ "<s>",
9
+ "<mask>",
10
+ "प्रश्न:",
11
+ "उत्तर:"
12
+ ],
13
+ "is_local": true,
14
+ "mask_token": "<mask>",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "<pad>",
17
+ "tokenizer_class": "GemmaTokenizer",
18
+ "unk_token": "<unk>",
19
+ "vocab_file": "tokenizer-gemma/tokenizer.model"
20
+ }