Upload tokenizer.json
Browse files- tokenizer.json +52 -62
tokenizer.json
CHANGED
|
@@ -14,16 +14,16 @@
|
|
| 14 |
"pad_to_multiple_of": null,
|
| 15 |
"pad_id": 0,
|
| 16 |
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "[
|
| 18 |
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
| 22 |
-
"content": "[
|
| 23 |
-
"single_word":
|
| 24 |
-
"lstrip":
|
| 25 |
-
"rstrip":
|
| 26 |
-
"normalized":
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
{
|
|
@@ -155,17 +155,7 @@
|
|
| 155 |
},
|
| 156 |
"model": {
|
| 157 |
"type": "WordPiece",
|
| 158 |
-
"unk_token": "[
|
| 159 |
-
"continuing_subword_prefix": "##",
|
| 160 |
-
"max_input_chars_per_word": 100,
|
| 161 |
-
"vocab": {
|
| 162 |
-
"type": "WordPiece",
|
| 163 |
-
"prefix": "##",
|
| 164 |
-
"cleanup": false
|
| 165 |
-
},
|
| 166 |
-
"model": {
|
| 167 |
-
"type": "WordPiece",
|
| 168 |
-
"unk_token": "[MEEP]",
|
| 169 |
"continuing_subword_prefix": "##",
|
| 170 |
"max_input_chars_per_word": 100,
|
| 171 |
"vocab": {
|
|
@@ -30646,51 +30636,51 @@
|
|
| 30646 |
"##見": 30474,
|
| 30647 |
"##訁": 30475,
|
| 30648 |
"##語": 30476,
|
| 30649 |
-
"
|
| 30650 |
-
"
|
| 30651 |
-
"
|
| 30652 |
-
"
|
| 30653 |
-
"
|
| 30654 |
-
"
|
| 30655 |
-
"
|
| 30656 |
-
"
|
| 30657 |
-
"
|
| 30658 |
-
"
|
| 30659 |
-
"
|
| 30660 |
-
"
|
| 30661 |
-
"
|
| 30662 |
-
"
|
| 30663 |
-
"
|
| 30664 |
-
"
|
| 30665 |
-
"
|
| 30666 |
-
"
|
| 30667 |
-
"
|
| 30668 |
-
"
|
| 30669 |
-
"
|
| 30670 |
-
"
|
| 30671 |
-
"
|
| 30672 |
-
"
|
| 30673 |
-
"
|
| 30674 |
-
"
|
| 30675 |
-
"
|
| 30676 |
-
"
|
| 30677 |
-
"
|
| 30678 |
-
"
|
| 30679 |
-
"
|
| 30680 |
-
"
|
| 30681 |
-
"
|
| 30682 |
-
"
|
| 30683 |
-
"
|
| 30684 |
-
"
|
| 30685 |
-
"
|
| 30686 |
-
"
|
| 30687 |
-
"
|
| 30688 |
-
"
|
| 30689 |
-
"
|
| 30690 |
-
"
|
| 30691 |
-
"
|
| 30692 |
-
"
|
| 30693 |
-
"
|
| 30694 |
}
|
| 30695 |
}
|
| 30696 |
}
|
|
|
|
| 14 |
"pad_to_multiple_of": null,
|
| 15 |
"pad_id": 0,
|
| 16 |
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
| 22 |
+
"content": "[PAD]",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
{
|
|
|
|
| 155 |
},
|
| 156 |
"model": {
|
| 157 |
"type": "WordPiece",
|
| 158 |
+
"unk_token": "[UNK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
"continuing_subword_prefix": "##",
|
| 160 |
"max_input_chars_per_word": 100,
|
| 161 |
"vocab": {
|
|
|
|
| 30636 |
"##見": 30474,
|
| 30637 |
"##訁": 30475,
|
| 30638 |
"##語": 30476,
|
| 30639 |
+
"Ida Kor": 30477,
|
| 30640 |
+
"Vebe": 30478,
|
| 30641 |
+
"Vebe Vertenase": 30479,
|
| 30642 |
+
"Wim Mertens": 30480,
|
| 30643 |
+
"SOH Kofi": 30481,
|
| 30644 |
+
"SOH shrine": 30482,
|
| 30645 |
+
"SOH CAH": 30483,
|
| 30646 |
+
"WIM Hof": 30484,
|
| 30647 |
+
"WIM Mertens": 30485,
|
| 30648 |
+
"Vebe Kor": 30486,
|
| 30649 |
+
"Terri Summers": 30487,
|
| 30650 |
+
"Summers gets": 30488,
|
| 30651 |
+
"Summers licked": 30489,
|
| 30652 |
+
"Summers reveals": 30490,
|
| 30653 |
+
"Summers pussy licked like a dildo": 30491,
|
| 30654 |
+
"Vebe Summers": 30492,
|
| 30655 |
+
"Vebe Sweetheart": 30493,
|
| 30656 |
+
"Vebesz": 30494,
|
| 30657 |
+
"Vebe Android": 30495,
|
| 30658 |
+
"Vebe Noire": 30496,
|
| 30659 |
+
"Vebe Summers's pussy licked like a dildo": 30497,
|
| 30660 |
+
"Vebe iPhone iOS": 30498,
|
| 30661 |
+
"Vebe'Vt": 30499,
|
| 30662 |
+
"Vebes'": 30500,
|
| 30663 |
+
"Vebe's": 30501,
|
| 30664 |
+
"Vebes": 30502,
|
| 30665 |
+
"Vebes's": 30503,
|
| 30666 |
+
"Vebe du Lac": 30504,
|
| 30667 |
+
"Vebe ri": 30505,
|
| 30668 |
+
"Vebe EMR": 30506,
|
| 30669 |
+
"Vebe TECHNDROID": 30507,
|
| 30670 |
+
"Vebe mitt": 30508,
|
| 30671 |
+
"mitt Romney": 30509,
|
| 30672 |
+
"mitt Romney's": 30510,
|
| 30673 |
+
"Vebe MDM": 30511,
|
| 30674 |
+
"Lora Craft": 30512,
|
| 30675 |
+
"Vebe SDK, SDKs and VRTMs (Virtual Rots To Memories)": 30513,
|
| 30676 |
+
"Vebe Tok": 30514,
|
| 30677 |
+
"Vebe Vou sede": 30515,
|
| 30678 |
+
"Vebe pyedi yen pyere": 30516,
|
| 30679 |
+
"Vebe pye": 30517,
|
| 30680 |
+
"VebekOS": 30518,
|
| 30681 |
+
"VebekOS Vebeks": 30519,
|
| 30682 |
+
"Vebez": 30520,
|
| 30683 |
+
"Vebekz": 30521
|
| 30684 |
}
|
| 30685 |
}
|
| 30686 |
}
|