Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +33 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
@@ -62,6 +67,12 @@
|
|
| 62 |
"id": "A",
|
| 63 |
"type_id": 0
|
| 64 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
}
|
| 66 |
],
|
| 67 |
"pair": [
|
|
@@ -77,6 +88,12 @@
|
|
| 77 |
"type_id": 0
|
| 78 |
}
|
| 79 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
{
|
| 81 |
"SpecialToken": {
|
| 82 |
"id": "<s>",
|
|
@@ -88,9 +105,24 @@
|
|
| 88 |
"id": "B",
|
| 89 |
"type_id": 1
|
| 90 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
"<s>": {
|
| 95 |
"id": "<s>",
|
| 96 |
"ids": [
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 640,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 67 |
"id": "A",
|
| 68 |
"type_id": 0
|
| 69 |
}
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"SpecialToken": {
|
| 73 |
+
"id": "</s>",
|
| 74 |
+
"type_id": 0
|
| 75 |
+
}
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"pair": [
|
|
|
|
| 88 |
"type_id": 0
|
| 89 |
}
|
| 90 |
},
|
| 91 |
+
{
|
| 92 |
+
"SpecialToken": {
|
| 93 |
+
"id": "</s>",
|
| 94 |
+
"type_id": 0
|
| 95 |
+
}
|
| 96 |
+
},
|
| 97 |
{
|
| 98 |
"SpecialToken": {
|
| 99 |
"id": "<s>",
|
|
|
|
| 105 |
"id": "B",
|
| 106 |
"type_id": 1
|
| 107 |
}
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"SpecialToken": {
|
| 111 |
+
"id": "</s>",
|
| 112 |
+
"type_id": 1
|
| 113 |
+
}
|
| 114 |
}
|
| 115 |
],
|
| 116 |
"special_tokens": {
|
| 117 |
+
"</s>": {
|
| 118 |
+
"id": "</s>",
|
| 119 |
+
"ids": [
|
| 120 |
+
2
|
| 121 |
+
],
|
| 122 |
+
"tokens": [
|
| 123 |
+
"</s>"
|
| 124 |
+
]
|
| 125 |
+
},
|
| 126 |
"<s>": {
|
| 127 |
"id": "<s>",
|
| 128 |
"ids": [
|
tokenizer_config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": true,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
-
"pad_token":
|
| 36 |
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
|
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": true,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|