Added foreign names for more differences is nouns
Browse files- config.json +1 -1
- model.safetensors +1 -1
- special_tokens_map.json +24 -24
- tokenizer_config.json +11 -11
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "models/t5-1.
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "models/t5-1.3_base_nouns/",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242181160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d06e6b690a50fd664766b6bd2cc3a5a5f0c7a2e067b6936578225046a36ad21
|
3 |
size 242181160
|
special_tokens_map.json
CHANGED
@@ -63,13 +63,6 @@
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false
|
65 |
},
|
66 |
-
{
|
67 |
-
"content": "peẽ",
|
68 |
-
"lstrip": false,
|
69 |
-
"normalized": false,
|
70 |
-
"rstrip": false,
|
71 |
-
"single_word": false
|
72 |
-
},
|
73 |
{
|
74 |
"content": "[SUBJECT:2pp]",
|
75 |
"lstrip": false,
|
@@ -183,21 +176,21 @@
|
|
183 |
"single_word": false
|
184 |
},
|
185 |
{
|
186 |
-
"content": "
|
187 |
"lstrip": false,
|
188 |
"normalized": false,
|
189 |
"rstrip": false,
|
190 |
"single_word": false
|
191 |
},
|
192 |
{
|
193 |
-
"content": "
|
194 |
"lstrip": false,
|
195 |
"normalized": false,
|
196 |
"rstrip": false,
|
197 |
"single_word": false
|
198 |
},
|
199 |
{
|
200 |
-
"content": "[
|
201 |
"lstrip": false,
|
202 |
"normalized": false,
|
203 |
"rstrip": false,
|
@@ -253,14 +246,14 @@
|
|
253 |
"single_word": false
|
254 |
},
|
255 |
{
|
256 |
-
"content": "
|
257 |
"lstrip": false,
|
258 |
"normalized": false,
|
259 |
"rstrip": false,
|
260 |
"single_word": false
|
261 |
},
|
262 |
{
|
263 |
-
"content": "
|
264 |
"lstrip": false,
|
265 |
"normalized": false,
|
266 |
"rstrip": false,
|
@@ -351,14 +344,14 @@
|
|
351 |
"single_word": false
|
352 |
},
|
353 |
{
|
354 |
-
"content": "
|
355 |
"lstrip": false,
|
356 |
"normalized": false,
|
357 |
"rstrip": false,
|
358 |
"single_word": false
|
359 |
},
|
360 |
{
|
361 |
-
"content": "
|
362 |
"lstrip": false,
|
363 |
"normalized": false,
|
364 |
"rstrip": false,
|
@@ -399,6 +392,13 @@
|
|
399 |
"rstrip": false,
|
400 |
"single_word": false
|
401 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
{
|
403 |
"content": "gûi",
|
404 |
"lstrip": false,
|
@@ -428,21 +428,21 @@
|
|
428 |
"single_word": false
|
429 |
},
|
430 |
{
|
431 |
-
"content": "
|
432 |
"lstrip": false,
|
433 |
"normalized": false,
|
434 |
"rstrip": false,
|
435 |
"single_word": false
|
436 |
},
|
437 |
{
|
438 |
-
"content": "
|
439 |
"lstrip": false,
|
440 |
"normalized": false,
|
441 |
"rstrip": false,
|
442 |
"single_word": false
|
443 |
},
|
444 |
{
|
445 |
-
"content": "
|
446 |
"lstrip": false,
|
447 |
"normalized": false,
|
448 |
"rstrip": false,
|
@@ -526,7 +526,7 @@
|
|
526 |
"single_word": false
|
527 |
},
|
528 |
{
|
529 |
-
"content": "
|
530 |
"lstrip": false,
|
531 |
"normalized": false,
|
532 |
"rstrip": false,
|
@@ -540,21 +540,21 @@
|
|
540 |
"single_word": false
|
541 |
},
|
542 |
{
|
543 |
-
"content": "
|
544 |
"lstrip": false,
|
545 |
"normalized": false,
|
546 |
"rstrip": false,
|
547 |
"single_word": false
|
548 |
},
|
549 |
{
|
550 |
-
"content": "
|
551 |
"lstrip": false,
|
552 |
"normalized": false,
|
553 |
"rstrip": false,
|
554 |
"single_word": false
|
555 |
},
|
556 |
{
|
557 |
-
"content": "
|
558 |
"lstrip": false,
|
559 |
"normalized": false,
|
560 |
"rstrip": false,
|
@@ -610,7 +610,7 @@
|
|
610 |
"single_word": false
|
611 |
},
|
612 |
{
|
613 |
-
"content": "
|
614 |
"lstrip": false,
|
615 |
"normalized": false,
|
616 |
"rstrip": false,
|
@@ -624,7 +624,7 @@
|
|
624 |
"single_word": false
|
625 |
},
|
626 |
{
|
627 |
-
"content": "
|
628 |
"lstrip": false,
|
629 |
"normalized": false,
|
630 |
"rstrip": false,
|
@@ -729,7 +729,7 @@
|
|
729 |
"single_word": false
|
730 |
},
|
731 |
{
|
732 |
-
"content": "
|
733 |
"lstrip": false,
|
734 |
"normalized": false,
|
735 |
"rstrip": false,
|
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false
|
65 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
{
|
67 |
"content": "[SUBJECT:2pp]",
|
68 |
"lstrip": false,
|
|
|
176 |
"single_word": false
|
177 |
},
|
178 |
{
|
179 |
+
"content": "i",
|
180 |
"lstrip": false,
|
181 |
"normalized": false,
|
182 |
"rstrip": false,
|
183 |
"single_word": false
|
184 |
},
|
185 |
{
|
186 |
+
"content": "[GERUND_SUBJECT_PREFIX:1ppe]",
|
187 |
"lstrip": false,
|
188 |
"normalized": false,
|
189 |
"rstrip": false,
|
190 |
"single_word": false
|
191 |
},
|
192 |
{
|
193 |
+
"content": "[NEGATION_SUFFIX]",
|
194 |
"lstrip": false,
|
195 |
"normalized": false,
|
196 |
"rstrip": false,
|
|
|
246 |
"single_word": false
|
247 |
},
|
248 |
{
|
249 |
+
"content": "a",
|
250 |
"lstrip": false,
|
251 |
"normalized": false,
|
252 |
"rstrip": false,
|
253 |
"single_word": false
|
254 |
},
|
255 |
{
|
256 |
+
"content": "[SUBJECT:1ppe]",
|
257 |
"lstrip": false,
|
258 |
"normalized": false,
|
259 |
"rstrip": false,
|
|
|
344 |
"single_word": false
|
345 |
},
|
346 |
{
|
347 |
+
"content": "opo",
|
348 |
"lstrip": false,
|
349 |
"normalized": false,
|
350 |
"rstrip": false,
|
351 |
"single_word": false
|
352 |
},
|
353 |
{
|
354 |
+
"content": "nde",
|
355 |
"lstrip": false,
|
356 |
"normalized": false,
|
357 |
"rstrip": false,
|
|
|
392 |
"rstrip": false,
|
393 |
"single_word": false
|
394 |
},
|
395 |
+
{
|
396 |
+
"content": "s",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false
|
401 |
+
},
|
402 |
{
|
403 |
"content": "gûi",
|
404 |
"lstrip": false,
|
|
|
428 |
"single_word": false
|
429 |
},
|
430 |
{
|
431 |
+
"content": "namo",
|
432 |
"lstrip": false,
|
433 |
"normalized": false,
|
434 |
"rstrip": false,
|
435 |
"single_word": false
|
436 |
},
|
437 |
{
|
438 |
+
"content": "[GERUND_SUFFIX:CLASS_1:R]",
|
439 |
"lstrip": false,
|
440 |
"normalized": false,
|
441 |
"rstrip": false,
|
442 |
"single_word": false
|
443 |
},
|
444 |
{
|
445 |
+
"content": "endé",
|
446 |
"lstrip": false,
|
447 |
"normalized": false,
|
448 |
"rstrip": false,
|
|
|
526 |
"single_word": false
|
527 |
},
|
528 |
{
|
529 |
+
"content": "ixé",
|
530 |
"lstrip": false,
|
531 |
"normalized": false,
|
532 |
"rstrip": false,
|
|
|
540 |
"single_word": false
|
541 |
},
|
542 |
{
|
543 |
+
"content": "[SUBJECT_PREFIX:1ps]",
|
544 |
"lstrip": false,
|
545 |
"normalized": false,
|
546 |
"rstrip": false,
|
547 |
"single_word": false
|
548 |
},
|
549 |
{
|
550 |
+
"content": "ramo",
|
551 |
"lstrip": false,
|
552 |
"normalized": false,
|
553 |
"rstrip": false,
|
554 |
"single_word": false
|
555 |
},
|
556 |
{
|
557 |
+
"content": "pa",
|
558 |
"lstrip": false,
|
559 |
"normalized": false,
|
560 |
"rstrip": false,
|
|
|
610 |
"single_word": false
|
611 |
},
|
612 |
{
|
613 |
+
"content": "oro",
|
614 |
"lstrip": false,
|
615 |
"normalized": false,
|
616 |
"rstrip": false,
|
|
|
624 |
"single_word": false
|
625 |
},
|
626 |
{
|
627 |
+
"content": "[OBJECT:2ps:SUBJECT_1P]",
|
628 |
"lstrip": false,
|
629 |
"normalized": false,
|
630 |
"rstrip": false,
|
|
|
729 |
"single_word": false
|
730 |
},
|
731 |
{
|
732 |
+
"content": "peẽ",
|
733 |
"lstrip": false,
|
734 |
"normalized": false,
|
735 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1692,7 +1692,6 @@
|
|
1692 |
"[OBJECT:2pp]",
|
1693 |
"ta",
|
1694 |
"n'",
|
1695 |
-
"peẽ",
|
1696 |
"[SUBJECT:2pp]",
|
1697 |
"îe",
|
1698 |
"[GERUND_SUBJECT_PREFIX:3p]",
|
@@ -1709,9 +1708,9 @@
|
|
1709 |
"[GERUND_SUFFIX:CLASS_1]",
|
1710 |
"[GERUND_SUFFIX:CLASS_1:IYU]",
|
1711 |
"îo",
|
1712 |
-
"[NEGATION_SUFFIX]",
|
1713 |
"i",
|
1714 |
"[GERUND_SUBJECT_PREFIX:1ppe]",
|
|
|
1715 |
"[SUBJECT:3p]",
|
1716 |
"[IMPERATIVE_PREFIX:2pp]",
|
1717 |
"́",
|
@@ -1719,8 +1718,8 @@
|
|
1719 |
"a'e",
|
1720 |
"t",
|
1721 |
"[SUBJECT:1ps]",
|
1722 |
-
"[SUBJECT:1ppe]",
|
1723 |
"a",
|
|
|
1724 |
"[SUBJECT_PREFIX:1ppe]",
|
1725 |
"amo",
|
1726 |
"[OBJECT:2ps]",
|
@@ -1733,20 +1732,21 @@
|
|
1733 |
"[SUBJECT:1ppi]",
|
1734 |
"[PERMISSIVE_PREFIX:VOWEL]",
|
1735 |
"pe",
|
1736 |
-
"nde",
|
1737 |
"opo",
|
|
|
1738 |
"[OBJECT_MARKER:3p:DEFAULT]",
|
1739 |
"[GERUND_SUBJECT_PREFIX:2ps]",
|
1740 |
"[OBJECT:3p]",
|
1741 |
"îandé",
|
1742 |
"[OBJECT:2pp:SUBJECT_1P]",
|
|
|
1743 |
"gûi",
|
1744 |
"[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
|
1745 |
"[OBJECT_MARKER:3p:MONOSYLLABIC]",
|
1746 |
"peîepé",
|
|
|
1747 |
"[GERUND_SUFFIX:CLASS_1:R]",
|
1748 |
"endé",
|
1749 |
-
"namo",
|
1750 |
"[SUBJECT:2pp:OBJECT_1P]",
|
1751 |
"mo",
|
1752 |
"bo",
|
@@ -1758,11 +1758,11 @@
|
|
1758 |
"[SUBJECT_PREFIX:3p]",
|
1759 |
"r",
|
1760 |
"[NEGATION_SUFFIX:VOWEL_ENDING]",
|
1761 |
-
"[SUBJECT_PREFIX:1ps]",
|
1762 |
-
"[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
|
1763 |
"ixé",
|
1764 |
-
"
|
|
|
1765 |
"ramo",
|
|
|
1766 |
"ere",
|
1767 |
"[OBJECT:REFLEXIVE]",
|
1768 |
"[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]",
|
@@ -1770,9 +1770,9 @@
|
|
1770 |
"[GERUND_SUFFIX:CLASS_1:B]",
|
1771 |
"[OBJECT:3p:MONOSYLLABIC]",
|
1772 |
"[GERUND_SUFFIX:CLASS_1:CONSONANT]",
|
1773 |
-
"[OBJECT:2ps:SUBJECT_1P]",
|
1774 |
-
"[GERUND_SUBJECT_PREFIX:1ps]",
|
1775 |
"oro",
|
|
|
|
|
1776 |
"[PERMISSIVE_PREFIX:CONSONANT]",
|
1777 |
"í",
|
1778 |
"oré",
|
@@ -1787,7 +1787,7 @@
|
|
1787 |
"[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]",
|
1788 |
"[SUBJECT_PREFIX:1ppi]",
|
1789 |
"[SUBJECT_PREFIX:2ps]",
|
1790 |
-
"
|
1791 |
"[SPACE]"
|
1792 |
],
|
1793 |
"clean_up_tokenization_spaces": true,
|
|
|
1692 |
"[OBJECT:2pp]",
|
1693 |
"ta",
|
1694 |
"n'",
|
|
|
1695 |
"[SUBJECT:2pp]",
|
1696 |
"îe",
|
1697 |
"[GERUND_SUBJECT_PREFIX:3p]",
|
|
|
1708 |
"[GERUND_SUFFIX:CLASS_1]",
|
1709 |
"[GERUND_SUFFIX:CLASS_1:IYU]",
|
1710 |
"îo",
|
|
|
1711 |
"i",
|
1712 |
"[GERUND_SUBJECT_PREFIX:1ppe]",
|
1713 |
+
"[NEGATION_SUFFIX]",
|
1714 |
"[SUBJECT:3p]",
|
1715 |
"[IMPERATIVE_PREFIX:2pp]",
|
1716 |
"́",
|
|
|
1718 |
"a'e",
|
1719 |
"t",
|
1720 |
"[SUBJECT:1ps]",
|
|
|
1721 |
"a",
|
1722 |
+
"[SUBJECT:1ppe]",
|
1723 |
"[SUBJECT_PREFIX:1ppe]",
|
1724 |
"amo",
|
1725 |
"[OBJECT:2ps]",
|
|
|
1732 |
"[SUBJECT:1ppi]",
|
1733 |
"[PERMISSIVE_PREFIX:VOWEL]",
|
1734 |
"pe",
|
|
|
1735 |
"opo",
|
1736 |
+
"nde",
|
1737 |
"[OBJECT_MARKER:3p:DEFAULT]",
|
1738 |
"[GERUND_SUBJECT_PREFIX:2ps]",
|
1739 |
"[OBJECT:3p]",
|
1740 |
"îandé",
|
1741 |
"[OBJECT:2pp:SUBJECT_1P]",
|
1742 |
+
"s",
|
1743 |
"gûi",
|
1744 |
"[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
|
1745 |
"[OBJECT_MARKER:3p:MONOSYLLABIC]",
|
1746 |
"peîepé",
|
1747 |
+
"namo",
|
1748 |
"[GERUND_SUFFIX:CLASS_1:R]",
|
1749 |
"endé",
|
|
|
1750 |
"[SUBJECT:2pp:OBJECT_1P]",
|
1751 |
"mo",
|
1752 |
"bo",
|
|
|
1758 |
"[SUBJECT_PREFIX:3p]",
|
1759 |
"r",
|
1760 |
"[NEGATION_SUFFIX:VOWEL_ENDING]",
|
|
|
|
|
1761 |
"ixé",
|
1762 |
+
"[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
|
1763 |
+
"[SUBJECT_PREFIX:1ps]",
|
1764 |
"ramo",
|
1765 |
+
"pa",
|
1766 |
"ere",
|
1767 |
"[OBJECT:REFLEXIVE]",
|
1768 |
"[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]",
|
|
|
1770 |
"[GERUND_SUFFIX:CLASS_1:B]",
|
1771 |
"[OBJECT:3p:MONOSYLLABIC]",
|
1772 |
"[GERUND_SUFFIX:CLASS_1:CONSONANT]",
|
|
|
|
|
1773 |
"oro",
|
1774 |
+
"[GERUND_SUBJECT_PREFIX:1ps]",
|
1775 |
+
"[OBJECT:2ps:SUBJECT_1P]",
|
1776 |
"[PERMISSIVE_PREFIX:CONSONANT]",
|
1777 |
"í",
|
1778 |
"oré",
|
|
|
1787 |
"[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]",
|
1788 |
"[SUBJECT_PREFIX:1ppi]",
|
1789 |
"[SUBJECT_PREFIX:2ps]",
|
1790 |
+
"peẽ",
|
1791 |
"[SPACE]"
|
1792 |
],
|
1793 |
"clean_up_tokenization_spaces": true,
|