williampepple1 commited on
Commit
1d14d63
·
verified ·
1 Parent(s): d868bbd

Upload 10 files

Browse files
added_tokens.json CHANGED
@@ -3,52 +3,52 @@
3
  "(Ḅẹ": 64113,
4
  "(Ḅẹ́": 64114,
5
  "(Ḅẹẹ": 64115,
6
- "-ág": 64116,
7
- "-ák": 64117,
8
- "-ál": 64118,
9
- "-án": 64119,
10
- "-áp": 64120,
11
- "-ár": 64121,
12
- "Anịsáa": 64122,
13
- "Anịḅọ": 64123,
14
- "Baá": 64124,
15
- "Bieoḅu": 64125,
16
- "Bál": 64126,
17
- "Báláma": 64127,
18
- "Bẹḅọ": 64128,
19
- "Bịrịḅọ": 64129,
20
- "Daá": 64130,
21
- "Daá,": 64131,
22
- "Daá.": 64132,
23
- "Daḅọ": 64133,
24
- "Daḅọ,": 64134,
25
- "Daḅọ.": 64135,
26
- "Deeḅọ": 64136,
27
- "Dipiḅọ": 64137,
28
- "Duá": 64138,
29
- "Dáp": 64139,
30
- "Dáppá": 64140,
31
- "Dáḅ": 64141,
32
- "Dáḅọ": 64142,
33
- "Dụḅa": 64143,
34
- "Dụḅaḅá": 64144,
35
- "Fúrúḅọ": 64145,
36
- "Fịnịḅọ": 64146,
37
- "Ibiḅọ": 64147,
38
- "Imiẹḅa": 64148,
39
- "Isiḅọ": 64149,
40
- "Iḅụ": 64150,
41
- "Iḅụbie": 64151,
42
- "Juuḅọ": 64152,
43
- "Juuḅọ,": 64153,
44
- "Juuḅọ?": 64154,
45
- "Kpápụ́": 64155,
46
- "Kál": 64156,
47
- "Kálá": 64157,
48
- "Kán": 64158,
49
- "Kóróḅo": 64159,
50
- "Kụ́rá": 64160,
51
- "Mán": 64161,
52
  "Ḅ": 64111,
53
  "ḅ": 64110
54
  }
 
3
  "(Ḅẹ": 64113,
4
  "(Ḅẹ́": 64114,
5
  "(Ḅẹẹ": 64115,
6
+ "(ḅụ": 64116,
7
+ "-ág": 64117,
8
+ "-ák": 64118,
9
+ "-ál": 64119,
10
+ "-án": 64120,
11
+ "-áp": 64121,
12
+ "-ár": 64122,
13
+ "-ḅẹ": 64123,
14
+ "Alaḅọ": 64124,
15
+ "Anịsáa": 64125,
16
+ "Anịḅọ": 64126,
17
+ "Baá": 64127,
18
+ "Bieoḅu": 64128,
19
+ "Bál": 64129,
20
+ "Báláma": 64130,
21
+ "Bẹḅọ": 64131,
22
+ "Bịrịḅọ": 64132,
23
+ "Daá": 64133,
24
+ "Daá,": 64134,
25
+ "Daá.": 64135,
26
+ "Daḅọ": 64136,
27
+ "Daḅọ,": 64137,
28
+ "Daḅọ.": 64138,
29
+ "Deeḅọ": 64139,
30
+ "Dipiḅọ": 64140,
31
+ "Duá": 64141,
32
+ "Dáp": 64142,
33
+ "Dáppá": 64143,
34
+ "Dáḅ": 64144,
35
+ "Dáḅọ": 64145,
36
+ "Dụḅa": 64146,
37
+ "Dụḅaḅá": 64147,
38
+ "Fúrúḅọ": 64148,
39
+ "Fịnịḅọ": 64149,
40
+ "Fụḅara": 64150,
41
+ "Ibiḅọ": 64151,
42
+ "Imiẹḅa": 64152,
43
+ "Isiḅọ": 64153,
44
+ "Iḅụ": 64154,
45
+ "Iḅụbie": 64155,
46
+ "Juuḅọ": 64156,
47
+ "Juuḅọ,": 64157,
48
+ "Juuḅọ?": 64158,
49
+ "Kpápụ́": 64159,
50
+ "Kál": 64160,
51
+ "Kálá": 64161,
52
  "Ḅ": 64111,
53
  "ḅ": 64110
54
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d06c4f02370062036eb342b70c769cd76b7bb2c7b356a2b50cd4bed206cadfb4
3
  size 308243464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57dfbadd5a90c1e26fbf5251bff44f42c3d9fd0c7f859748f0d018fa00d6091d
3
  size 308243464
tokenizer_config.json CHANGED
@@ -73,7 +73,7 @@
73
  "special": false
74
  },
75
  "64116": {
76
- "content": "-ág",
77
  "lstrip": false,
78
  "normalized": true,
79
  "rstrip": false,
@@ -81,7 +81,7 @@
81
  "special": false
82
  },
83
  "64117": {
84
- "content": "-ák",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
@@ -89,7 +89,7 @@
89
  "special": false
90
  },
91
  "64118": {
92
- "content": "-ál",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
@@ -97,7 +97,7 @@
97
  "special": false
98
  },
99
  "64119": {
100
- "content": "-án",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
@@ -105,7 +105,7 @@
105
  "special": false
106
  },
107
  "64120": {
108
- "content": "-áp",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  "special": false
114
  },
115
  "64121": {
116
- "content": "-ár",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
@@ -121,7 +121,7 @@
121
  "special": false
122
  },
123
  "64122": {
124
- "content": "Anịsáa",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
@@ -129,7 +129,7 @@
129
  "special": false
130
  },
131
  "64123": {
132
- "content": "Anịḅọ",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
@@ -137,7 +137,7 @@
137
  "special": false
138
  },
139
  "64124": {
140
- "content": "Baá",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
@@ -145,7 +145,7 @@
145
  "special": false
146
  },
147
  "64125": {
148
- "content": "Bieoḅu",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
@@ -153,7 +153,7 @@
153
  "special": false
154
  },
155
  "64126": {
156
- "content": "Bál",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
@@ -161,7 +161,7 @@
161
  "special": false
162
  },
163
  "64127": {
164
- "content": "Báláma",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
@@ -169,7 +169,7 @@
169
  "special": false
170
  },
171
  "64128": {
172
- "content": "Bẹḅọ",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
@@ -177,7 +177,7 @@
177
  "special": false
178
  },
179
  "64129": {
180
- "content": "Bịrịḅọ",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  "special": false
186
  },
187
  "64130": {
188
- "content": "Daá",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
@@ -193,7 +193,7 @@
193
  "special": false
194
  },
195
  "64131": {
196
- "content": "Daá,",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
@@ -201,7 +201,7 @@
201
  "special": false
202
  },
203
  "64132": {
204
- "content": "Daá.",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
@@ -209,7 +209,7 @@
209
  "special": false
210
  },
211
  "64133": {
212
- "content": "Daḅọ",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
@@ -217,7 +217,7 @@
217
  "special": false
218
  },
219
  "64134": {
220
- "content": "Daḅọ,",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
@@ -225,7 +225,7 @@
225
  "special": false
226
  },
227
  "64135": {
228
- "content": "Daḅọ.",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
@@ -233,7 +233,7 @@
233
  "special": false
234
  },
235
  "64136": {
236
- "content": "Deeḅọ",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
@@ -241,7 +241,7 @@
241
  "special": false
242
  },
243
  "64137": {
244
- "content": "Dipiḅọ",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
@@ -249,7 +249,7 @@
249
  "special": false
250
  },
251
  "64138": {
252
- "content": "Duá",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  "special": false
258
  },
259
  "64139": {
260
- "content": "Dáp",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
@@ -265,7 +265,7 @@
265
  "special": false
266
  },
267
  "64140": {
268
- "content": "Dáppá",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
@@ -273,7 +273,7 @@
273
  "special": false
274
  },
275
  "64141": {
276
- "content": "Dáḅ",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
@@ -281,7 +281,7 @@
281
  "special": false
282
  },
283
  "64142": {
284
- "content": "Dáḅọ",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
@@ -289,7 +289,7 @@
289
  "special": false
290
  },
291
  "64143": {
292
- "content": "Dụḅa",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
@@ -297,7 +297,7 @@
297
  "special": false
298
  },
299
  "64144": {
300
- "content": "Dụḅaḅá",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
@@ -305,7 +305,7 @@
305
  "special": false
306
  },
307
  "64145": {
308
- "content": "Fúrúḅọ",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
@@ -313,7 +313,7 @@
313
  "special": false
314
  },
315
  "64146": {
316
- "content": "Fịnịḅọ",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
@@ -321,7 +321,7 @@
321
  "special": false
322
  },
323
  "64147": {
324
- "content": "Ibiḅọ",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  "special": false
330
  },
331
  "64148": {
332
- "content": "Imiẹḅa",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
@@ -337,7 +337,7 @@
337
  "special": false
338
  },
339
  "64149": {
340
- "content": "Isiḅọ",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
@@ -345,7 +345,7 @@
345
  "special": false
346
  },
347
  "64150": {
348
- "content": "Iḅụ",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
@@ -353,7 +353,7 @@
353
  "special": false
354
  },
355
  "64151": {
356
- "content": "Iḅụbie",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
@@ -361,7 +361,7 @@
361
  "special": false
362
  },
363
  "64152": {
364
- "content": "Juuḅọ",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
@@ -369,7 +369,7 @@
369
  "special": false
370
  },
371
  "64153": {
372
- "content": "Juuḅọ,",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
@@ -377,7 +377,7 @@
377
  "special": false
378
  },
379
  "64154": {
380
- "content": "Juuḅọ?",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
@@ -385,7 +385,7 @@
385
  "special": false
386
  },
387
  "64155": {
388
- "content": "Kpápụ́",
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
@@ -393,7 +393,7 @@
393
  "special": false
394
  },
395
  "64156": {
396
- "content": "Kál",
397
  "lstrip": false,
398
  "normalized": true,
399
  "rstrip": false,
@@ -401,7 +401,7 @@
401
  "special": false
402
  },
403
  "64157": {
404
- "content": "Kálá",
405
  "lstrip": false,
406
  "normalized": true,
407
  "rstrip": false,
@@ -409,7 +409,7 @@
409
  "special": false
410
  },
411
  "64158": {
412
- "content": "Kán",
413
  "lstrip": false,
414
  "normalized": true,
415
  "rstrip": false,
@@ -417,7 +417,7 @@
417
  "special": false
418
  },
419
  "64159": {
420
- "content": "Kóróḅo",
421
  "lstrip": false,
422
  "normalized": true,
423
  "rstrip": false,
@@ -425,7 +425,7 @@
425
  "special": false
426
  },
427
  "64160": {
428
- "content": "Kụ́rá",
429
  "lstrip": false,
430
  "normalized": true,
431
  "rstrip": false,
@@ -433,7 +433,7 @@
433
  "special": false
434
  },
435
  "64161": {
436
- "content": "Mán",
437
  "lstrip": false,
438
  "normalized": true,
439
  "rstrip": false,
 
73
  "special": false
74
  },
75
  "64116": {
76
+ "content": "(ḅụ",
77
  "lstrip": false,
78
  "normalized": true,
79
  "rstrip": false,
 
81
  "special": false
82
  },
83
  "64117": {
84
+ "content": "-ág",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
 
89
  "special": false
90
  },
91
  "64118": {
92
+ "content": "-ák",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
 
97
  "special": false
98
  },
99
  "64119": {
100
+ "content": "-ál",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
 
105
  "special": false
106
  },
107
  "64120": {
108
+ "content": "-án",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
 
113
  "special": false
114
  },
115
  "64121": {
116
+ "content": "-áp",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
 
121
  "special": false
122
  },
123
  "64122": {
124
+ "content": "-ár",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
 
129
  "special": false
130
  },
131
  "64123": {
132
+ "content": "-ḅẹ",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
 
137
  "special": false
138
  },
139
  "64124": {
140
+ "content": "Alaḅọ",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
 
145
  "special": false
146
  },
147
  "64125": {
148
+ "content": "Anịsáa",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
 
153
  "special": false
154
  },
155
  "64126": {
156
+ "content": "Anịḅọ",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
 
161
  "special": false
162
  },
163
  "64127": {
164
+ "content": "Baá",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
 
169
  "special": false
170
  },
171
  "64128": {
172
+ "content": "Bieoḅu",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
 
177
  "special": false
178
  },
179
  "64129": {
180
+ "content": "Bál",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
 
185
  "special": false
186
  },
187
  "64130": {
188
+ "content": "Báláma",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
 
193
  "special": false
194
  },
195
  "64131": {
196
+ "content": "Bẹḅọ",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
 
201
  "special": false
202
  },
203
  "64132": {
204
+ "content": "Bịrịḅọ",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
 
209
  "special": false
210
  },
211
  "64133": {
212
+ "content": "Daá",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
 
217
  "special": false
218
  },
219
  "64134": {
220
+ "content": "Daá,",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
 
225
  "special": false
226
  },
227
  "64135": {
228
+ "content": "Daá.",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
 
233
  "special": false
234
  },
235
  "64136": {
236
+ "content": "Daḅọ",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
 
241
  "special": false
242
  },
243
  "64137": {
244
+ "content": "Daḅọ,",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
 
249
  "special": false
250
  },
251
  "64138": {
252
+ "content": "Daḅọ.",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
 
257
  "special": false
258
  },
259
  "64139": {
260
+ "content": "Deeḅọ",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
 
265
  "special": false
266
  },
267
  "64140": {
268
+ "content": "Dipiḅọ",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
 
273
  "special": false
274
  },
275
  "64141": {
276
+ "content": "Duá",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
 
281
  "special": false
282
  },
283
  "64142": {
284
+ "content": "Dáp",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
 
289
  "special": false
290
  },
291
  "64143": {
292
+ "content": "Dáppá",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
 
297
  "special": false
298
  },
299
  "64144": {
300
+ "content": "Dáḅ",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
 
305
  "special": false
306
  },
307
  "64145": {
308
+ "content": "Dáḅọ",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
 
313
  "special": false
314
  },
315
  "64146": {
316
+ "content": "Dụḅa",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
 
321
  "special": false
322
  },
323
  "64147": {
324
+ "content": "Dụḅaḅá",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
 
329
  "special": false
330
  },
331
  "64148": {
332
+ "content": "Fúrúḅọ",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
 
337
  "special": false
338
  },
339
  "64149": {
340
+ "content": "Fịnịḅọ",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
 
345
  "special": false
346
  },
347
  "64150": {
348
+ "content": "Fụḅara",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
 
353
  "special": false
354
  },
355
  "64151": {
356
+ "content": "Ibiḅọ",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
 
361
  "special": false
362
  },
363
  "64152": {
364
+ "content": "Imiẹḅa",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
 
369
  "special": false
370
  },
371
  "64153": {
372
+ "content": "Isiḅọ",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
 
377
  "special": false
378
  },
379
  "64154": {
380
+ "content": "Iḅụ",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
 
385
  "special": false
386
  },
387
  "64155": {
388
+ "content": "Iḅụbie",
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
 
393
  "special": false
394
  },
395
  "64156": {
396
+ "content": "Juuḅọ",
397
  "lstrip": false,
398
  "normalized": true,
399
  "rstrip": false,
 
401
  "special": false
402
  },
403
  "64157": {
404
+ "content": "Juuḅọ,",
405
  "lstrip": false,
406
  "normalized": true,
407
  "rstrip": false,
 
409
  "special": false
410
  },
411
  "64158": {
412
+ "content": "Juuḅọ?",
413
  "lstrip": false,
414
  "normalized": true,
415
  "rstrip": false,
 
417
  "special": false
418
  },
419
  "64159": {
420
+ "content": "Kpápụ́",
421
  "lstrip": false,
422
  "normalized": true,
423
  "rstrip": false,
 
425
  "special": false
426
  },
427
  "64160": {
428
+ "content": "Kál",
429
  "lstrip": false,
430
  "normalized": true,
431
  "rstrip": false,
 
433
  "special": false
434
  },
435
  "64161": {
436
+ "content": "Kálá",
437
  "lstrip": false,
438
  "normalized": true,
439
  "rstrip": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31e4bdc490aba23834ef93b7920b05e8818aeb62383dfa506506d5c1d598b825
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac01817229fd5f462ace947cfbd0c3801c02a95b415e4f4489378f25dc3cee9f
3
  size 5905