kiansheik commited on
Commit
d0dfd61
1 Parent(s): 12f53bf

Latest, but broken characters

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c8b330e8b3e8fbff4a45942c27fe14746e74b2cdbc5b4027ddca51fcbbf9c2b
3
  size 242185256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80dfecd26b9f6c7e6fecc204679f434def1ff66f0c81494fdbb784d1234b6a9
3
  size 242185256
special_tokens_map.json CHANGED
@@ -197,7 +197,7 @@
197
  "single_word": false
198
  },
199
  {
200
- "content": "i",
201
  "lstrip": false,
202
  "normalized": false,
203
  "rstrip": false,
@@ -211,7 +211,7 @@
211
  "single_word": false
212
  },
213
  {
214
- "content": "[NEGATION_SUFFIX]",
215
  "lstrip": false,
216
  "normalized": false,
217
  "rstrip": false,
@@ -267,14 +267,14 @@
267
  "single_word": false
268
  },
269
  {
270
- "content": "a",
271
  "lstrip": false,
272
  "normalized": false,
273
  "rstrip": false,
274
  "single_word": false
275
  },
276
  {
277
- "content": "[SUBJECT:1ps]",
278
  "lstrip": false,
279
  "normalized": false,
280
  "rstrip": false,
@@ -442,7 +442,7 @@
442
  "single_word": false
443
  },
444
  {
445
- "content": "namo",
446
  "lstrip": false,
447
  "normalized": false,
448
  "rstrip": false,
@@ -456,7 +456,7 @@
456
  "single_word": false
457
  },
458
  {
459
- "content": "[GERUND_SUFFIX:CLASS_1:R]",
460
  "lstrip": false,
461
  "normalized": false,
462
  "rstrip": false,
@@ -547,14 +547,14 @@
547
  "single_word": false
548
  },
549
  {
550
- "content": "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
551
  "lstrip": false,
552
  "normalized": false,
553
  "rstrip": false,
554
  "single_word": false
555
  },
556
  {
557
- "content": "ixé",
558
  "lstrip": false,
559
  "normalized": false,
560
  "rstrip": false,
@@ -631,28 +631,28 @@
631
  "single_word": false
632
  },
633
  {
634
- "content": "[GERUND_SUBJECT_PREFIX:1ps]",
635
  "lstrip": false,
636
  "normalized": false,
637
  "rstrip": false,
638
  "single_word": false
639
  },
640
  {
641
- "content": "[OBJECT:2ps:SUBJECT_1P]",
642
  "lstrip": false,
643
  "normalized": false,
644
  "rstrip": false,
645
  "single_word": false
646
  },
647
  {
648
- "content": "í",
649
  "lstrip": false,
650
  "normalized": false,
651
  "rstrip": false,
652
  "single_word": false
653
  },
654
  {
655
- "content": "[PERMISSIVE_PREFIX:CONSONANT]",
656
  "lstrip": false,
657
  "normalized": false,
658
  "rstrip": false,
 
197
  "single_word": false
198
  },
199
  {
200
+ "content": "[NEGATION_SUFFIX]",
201
  "lstrip": false,
202
  "normalized": false,
203
  "rstrip": false,
 
211
  "single_word": false
212
  },
213
  {
214
+ "content": "i",
215
  "lstrip": false,
216
  "normalized": false,
217
  "rstrip": false,
 
267
  "single_word": false
268
  },
269
  {
270
+ "content": "[SUBJECT:1ps]",
271
  "lstrip": false,
272
  "normalized": false,
273
  "rstrip": false,
274
  "single_word": false
275
  },
276
  {
277
+ "content": "a",
278
  "lstrip": false,
279
  "normalized": false,
280
  "rstrip": false,
 
442
  "single_word": false
443
  },
444
  {
445
+ "content": "[GERUND_SUFFIX:CLASS_1:R]",
446
  "lstrip": false,
447
  "normalized": false,
448
  "rstrip": false,
 
456
  "single_word": false
457
  },
458
  {
459
+ "content": "namo",
460
  "lstrip": false,
461
  "normalized": false,
462
  "rstrip": false,
 
547
  "single_word": false
548
  },
549
  {
550
+ "content": "ixé",
551
  "lstrip": false,
552
  "normalized": false,
553
  "rstrip": false,
554
  "single_word": false
555
  },
556
  {
557
+ "content": "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
558
  "lstrip": false,
559
  "normalized": false,
560
  "rstrip": false,
 
631
  "single_word": false
632
  },
633
  {
634
+ "content": "[OBJECT:2ps:SUBJECT_1P]",
635
  "lstrip": false,
636
  "normalized": false,
637
  "rstrip": false,
638
  "single_word": false
639
  },
640
  {
641
+ "content": "[GERUND_SUBJECT_PREFIX:1ps]",
642
  "lstrip": false,
643
  "normalized": false,
644
  "rstrip": false,
645
  "single_word": false
646
  },
647
  {
648
+ "content": "[PERMISSIVE_PREFIX:CONSONANT]",
649
  "lstrip": false,
650
  "normalized": false,
651
  "rstrip": false,
652
  "single_word": false
653
  },
654
  {
655
+ "content": "í",
656
  "lstrip": false,
657
  "normalized": false,
658
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -1727,9 +1727,9 @@
1727
  "[SUB_VERB]",
1728
  "[GERUND_SUFFIX:CLASS_1:IYU]",
1729
  "îo",
1730
- "i",
1731
- "[GERUND_SUBJECT_PREFIX:1ppe]",
1732
  "[NEGATION_SUFFIX]",
 
 
1733
  "[SUBJECT:3p]",
1734
  "[IMPERATIVE_PREFIX:2pp]",
1735
  "́",
@@ -1737,8 +1737,8 @@
1737
  "a'e",
1738
  "t",
1739
  "[SUBJECT:1ppe]",
1740
- "a",
1741
  "[SUBJECT:1ps]",
 
1742
  "[SUBJECT_PREFIX:1ppe]",
1743
  "amo",
1744
  "[OBJECT:2ps]",
@@ -1762,9 +1762,9 @@
1762
  "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
1763
  "[OBJECT_MARKER:3p:MONOSYLLABIC]",
1764
  "peîepé",
1765
- "namo",
1766
- "endé",
1767
  "[GERUND_SUFFIX:CLASS_1:R]",
 
 
1768
  "[SUBJECT:2pp:OBJECT_1P]",
1769
  "mo",
1770
  "bo",
@@ -1777,8 +1777,8 @@
1777
  "r",
1778
  "[NEGATION_SUFFIX:VOWEL_ENDING]",
1779
  "[SUBJECT_PREFIX:1ps]",
1780
- "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
1781
  "ixé",
 
1782
  "pa",
1783
  "ramo",
1784
  "ere",
@@ -1789,10 +1789,10 @@
1789
  "[OBJECT:3p:MONOSYLLABIC]",
1790
  "[GERUND_SUFFIX:CLASS_1:CONSONANT]",
1791
  "oro",
1792
- "[GERUND_SUBJECT_PREFIX:1ps]",
1793
  "[OBJECT:2ps:SUBJECT_1P]",
1794
- "í",
1795
  "[PERMISSIVE_PREFIX:CONSONANT]",
 
1796
  "oré",
1797
  "umẽ",
1798
  "[PLURIFORM_PREFIX:R]",
 
1727
  "[SUB_VERB]",
1728
  "[GERUND_SUFFIX:CLASS_1:IYU]",
1729
  "îo",
 
 
1730
  "[NEGATION_SUFFIX]",
1731
+ "[GERUND_SUBJECT_PREFIX:1ppe]",
1732
+ "i",
1733
  "[SUBJECT:3p]",
1734
  "[IMPERATIVE_PREFIX:2pp]",
1735
  "́",
 
1737
  "a'e",
1738
  "t",
1739
  "[SUBJECT:1ppe]",
 
1740
  "[SUBJECT:1ps]",
1741
+ "a",
1742
  "[SUBJECT_PREFIX:1ppe]",
1743
  "amo",
1744
  "[OBJECT:2ps]",
 
1762
  "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
1763
  "[OBJECT_MARKER:3p:MONOSYLLABIC]",
1764
  "peîepé",
 
 
1765
  "[GERUND_SUFFIX:CLASS_1:R]",
1766
+ "endé",
1767
+ "namo",
1768
  "[SUBJECT:2pp:OBJECT_1P]",
1769
  "mo",
1770
  "bo",
 
1777
  "r",
1778
  "[NEGATION_SUFFIX:VOWEL_ENDING]",
1779
  "[SUBJECT_PREFIX:1ps]",
 
1780
  "ixé",
1781
+ "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
1782
  "pa",
1783
  "ramo",
1784
  "ere",
 
1789
  "[OBJECT:3p:MONOSYLLABIC]",
1790
  "[GERUND_SUFFIX:CLASS_1:CONSONANT]",
1791
  "oro",
 
1792
  "[OBJECT:2ps:SUBJECT_1P]",
1793
+ "[GERUND_SUBJECT_PREFIX:1ps]",
1794
  "[PERMISSIVE_PREFIX:CONSONANT]",
1795
+ "í",
1796
  "oré",
1797
  "umẽ",
1798
  "[PLURIFORM_PREFIX:R]",