Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +3 -3
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -2121,7 +2121,7 @@
|
|
| 2121 |
"special": true
|
| 2122 |
},
|
| 2123 |
"265": {
|
| 2124 |
-
"content": "[DOMAIN=
|
| 2125 |
"lstrip": false,
|
| 2126 |
"normalized": false,
|
| 2127 |
"rstrip": false,
|
|
@@ -2129,7 +2129,7 @@
|
|
| 2129 |
"special": true
|
| 2130 |
},
|
| 2131 |
"266": {
|
| 2132 |
-
"content": "[DOMAIN=
|
| 2133 |
"lstrip": false,
|
| 2134 |
"normalized": false,
|
| 2135 |
"rstrip": false,
|
|
@@ -10720,7 +10720,7 @@
|
|
| 10720 |
"single_word": false,
|
| 10721 |
"special": true
|
| 10722 |
},
|
| 10723 |
-
"
|
| 10724 |
"content": "[EOS]",
|
| 10725 |
"lstrip": false,
|
| 10726 |
"normalized": false,
|
|
|
|
| 2121 |
"special": true
|
| 2122 |
},
|
| 2123 |
"265": {
|
| 2124 |
+
"content": "[DOMAIN=['CANONICAL ➝ Lexicography ➝ Thematic Word Lists ➝ Ura']]",
|
| 2125 |
"lstrip": false,
|
| 2126 |
"normalized": false,
|
| 2127 |
"rstrip": false,
|
|
|
|
| 2129 |
"special": true
|
| 2130 |
},
|
| 2131 |
"266": {
|
| 2132 |
+
"content": "[DOMAIN=lettre privée]",
|
| 2133 |
"lstrip": false,
|
| 2134 |
"normalized": false,
|
| 2135 |
"rstrip": false,
|
|
|
|
| 10720 |
"single_word": false,
|
| 10721 |
"special": true
|
| 10722 |
},
|
| 10723 |
+
"7117": {
|
| 10724 |
"content": "[EOS]",
|
| 10725 |
"lstrip": false,
|
| 10726 |
"normalized": false,
|