Complex Clauses

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d06e6b690a50fd664766b6bd2cc3a5a5f0c7a2e067b6936578225046a36ad21
+oid sha256:6429f08c9d32f73aca7ddb79ef42875ea88b53e600934f4c5dffe4b8ae5ac131
 size 242181160

special_tokens_map.json

@@ -63,6 +63,13 @@
       "rstrip": false,
       "single_word": false
     },
+    {
+      "content": "peẽ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
     {
       "content": "[SUBJECT:2pp]",
       "lstrip": false,
@@ -183,14 +190,14 @@
       "single_word": false
     },
     {
-      "content": "[GERUND_SUBJECT_PREFIX:1ppe]",
+      "content": "[NEGATION_SUFFIX]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "[NEGATION_SUFFIX]",
+      "content": "[GERUND_SUBJECT_PREFIX:1ppe]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -344,14 +351,14 @@
       "single_word": false
     },
     {
-      "content": "opo",
+      "content": "nde",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "nde",
+      "content": "opo",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -386,21 +393,14 @@
       "single_word": false
     },
     {
-      "content": "[OBJECT:2pp:SUBJECT_1P]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "s",
+      "content": "gûi",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "gûi",
+      "content": "[OBJECT:2pp:SUBJECT_1P]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -428,21 +428,21 @@
       "single_word": false
     },
     {
-      "content": "namo",
+      "content": "endé",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "[GERUND_SUFFIX:CLASS_1:R]",
+      "content": "namo",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "endé",
+      "content": "[GERUND_SUFFIX:CLASS_1:R]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -631,14 +631,14 @@
       "single_word": false
     },
     {
-      "content": "[PERMISSIVE_PREFIX:CONSONANT]",
+      "content": "í",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "í",
+      "content": "[PERMISSIVE_PREFIX:CONSONANT]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -729,7 +729,7 @@
       "single_word": false
     },
     {
-      "content": "peẽ",
+      "content": "s",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer_config.json

@@ -1692,6 +1692,7 @@
     "[OBJECT:2pp]",
     "ta",
     "n'",
+    "peẽ",
     "[SUBJECT:2pp]",
     "îe",
     "[GERUND_SUBJECT_PREFIX:3p]",
@@ -1709,8 +1710,8 @@
     "[GERUND_SUFFIX:CLASS_1:IYU]",
     "îo",
     "i",
-    "[GERUND_SUBJECT_PREFIX:1ppe]",
     "[NEGATION_SUFFIX]",
+    "[GERUND_SUBJECT_PREFIX:1ppe]",
     "[SUBJECT:3p]",
     "[IMPERATIVE_PREFIX:2pp]",
     "́",
@@ -1732,21 +1733,20 @@
     "[SUBJECT:1ppi]",
     "[PERMISSIVE_PREFIX:VOWEL]",
     "pe",
-    "opo",
     "nde",
+    "opo",
     "[OBJECT_MARKER:3p:DEFAULT]",
     "[GERUND_SUBJECT_PREFIX:2ps]",
     "[OBJECT:3p]",
     "îandé",
-    "[OBJECT:2pp:SUBJECT_1P]",
-    "s",
     "gûi",
+    "[OBJECT:2pp:SUBJECT_1P]",
     "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
     "[OBJECT_MARKER:3p:MONOSYLLABIC]",
     "peîepé",
+    "endé",
     "namo",
     "[GERUND_SUFFIX:CLASS_1:R]",
-    "endé",
     "[SUBJECT:2pp:OBJECT_1P]",
     "mo",
     "bo",
@@ -1773,8 +1773,8 @@
     "oro",
     "[GERUND_SUBJECT_PREFIX:1ps]",
     "[OBJECT:2ps:SUBJECT_1P]",
-    "[PERMISSIVE_PREFIX:CONSONANT]",
     "í",
+    "[PERMISSIVE_PREFIX:CONSONANT]",
     "oré",
     "umẽ",
     "[SUBJECT:2ps]",
@@ -1787,7 +1787,7 @@
     "[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]",
     "[SUBJECT_PREFIX:1ppi]",
     "[SUBJECT_PREFIX:2ps]",
-    "peẽ",
+    "s",
     "[SPACE]"
   ],
   "clean_up_tokenization_spaces": true,