Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +8 -0
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -137,6 +137,14 @@
|
|
| 137 |
"single_word": false,
|
| 138 |
"special": true
|
| 139 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
"49152": {
|
| 141 |
"content": "<|PAD_TOKEN|>",
|
| 142 |
"lstrip": false,
|
|
|
|
| 137 |
"single_word": false,
|
| 138 |
"special": true
|
| 139 |
},
|
| 140 |
+
"24211": {
|
| 141 |
+
"content": "�",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
"49152": {
|
| 149 |
"content": "<|PAD_TOKEN|>",
|
| 150 |
"lstrip": false,
|