Upload tokenizer
Browse files- tokenizer.json +5 -8
tokenizer.json
CHANGED
|
@@ -5,32 +5,29 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized": false
|
| 13 |
-
"special": true
|
| 14 |
}
|
| 15 |
],
|
| 16 |
"normalizer": null,
|
| 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",
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
| 8 |
+
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": false
|
|
|
|
| 14 |
}
|
| 15 |
],
|
| 16 |
"normalizer": null,
|
| 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",
|