add tokenizer
Browse files- tokenizer.json +3 -6
tokenizer.json
CHANGED
|
@@ -17,20 +17,17 @@
|
|
| 17 |
"pre_tokenizer": {
|
| 18 |
"type": "ByteLevel",
|
| 19 |
"add_prefix_space": false,
|
| 20 |
-
"trim_offsets": true
|
| 21 |
-
"use_regex": true
|
| 22 |
},
|
| 23 |
"post_processor": {
|
| 24 |
"type": "ByteLevel",
|
| 25 |
"add_prefix_space": true,
|
| 26 |
-
"trim_offsets": false
|
| 27 |
-
"use_regex": true
|
| 28 |
},
|
| 29 |
"decoder": {
|
| 30 |
"type": "ByteLevel",
|
| 31 |
"add_prefix_space": true,
|
| 32 |
-
"trim_offsets": true
|
| 33 |
-
"use_regex": true
|
| 34 |
},
|
| 35 |
"model": {
|
| 36 |
"type": "BPE",
|
|
|
|
| 17 |
"pre_tokenizer": {
|
| 18 |
"type": "ByteLevel",
|
| 19 |
"add_prefix_space": false,
|
| 20 |
+
"trim_offsets": true
|
|
|
|
| 21 |
},
|
| 22 |
"post_processor": {
|
| 23 |
"type": "ByteLevel",
|
| 24 |
"add_prefix_space": true,
|
| 25 |
+
"trim_offsets": false
|
|
|
|
| 26 |
},
|
| 27 |
"decoder": {
|
| 28 |
"type": "ByteLevel",
|
| 29 |
"add_prefix_space": true,
|
| 30 |
+
"trim_offsets": true
|
|
|
|
| 31 |
},
|
| 32 |
"model": {
|
| 33 |
"type": "BPE",
|