Commit
•
7ad65d1
1
Parent(s):
eeeebbd
change tokenizer_class from PreTrainedTokenizerFast to BertTokenizerFast
Browse files- special_tokens_map.json +5 -5
- tokenizer.json +21 -21
- tokenizer_config.json +15 -12
- unigram.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"bos_token": "<s>",
|
| 6 |
-
"cls_token": "
|
| 7 |
"eos_token": "</s>",
|
| 8 |
-
"mask_token": "
|
| 9 |
-
"pad_token": "
|
| 10 |
-
"sep_token": "
|
| 11 |
"unk_token": "<unk>"
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"[EOD]"
|
| 4 |
],
|
| 5 |
"bos_token": "<s>",
|
| 6 |
+
"cls_token": "[CLS]",
|
| 7 |
"eos_token": "</s>",
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
"unk_token": "<unk>"
|
| 12 |
}
|
tokenizer.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
| 8 |
-
"content": "
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
|
@@ -23,7 +23,7 @@
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
-
"content": "
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
|
@@ -32,7 +32,7 @@
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
-
"content": "
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
-
"content": "
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
@@ -50,7 +50,7 @@
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 5,
|
| 53 |
-
"content": "
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
@@ -86,7 +86,7 @@
|
|
| 86 |
"single": [
|
| 87 |
{
|
| 88 |
"SpecialToken": {
|
| 89 |
-
"id": "
|
| 90 |
"type_id": 0
|
| 91 |
}
|
| 92 |
},
|
|
@@ -98,7 +98,7 @@
|
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"SpecialToken": {
|
| 101 |
-
"id": "
|
| 102 |
"type_id": 0
|
| 103 |
}
|
| 104 |
}
|
|
@@ -106,7 +106,7 @@
|
|
| 106 |
"pair": [
|
| 107 |
{
|
| 108 |
"SpecialToken": {
|
| 109 |
-
"id": "
|
| 110 |
"type_id": 0
|
| 111 |
}
|
| 112 |
},
|
|
@@ -118,7 +118,7 @@
|
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"SpecialToken": {
|
| 121 |
-
"id": "
|
| 122 |
"type_id": 0
|
| 123 |
}
|
| 124 |
},
|
|
@@ -130,28 +130,28 @@
|
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"SpecialToken": {
|
| 133 |
-
"id": "
|
| 134 |
"type_id": 1
|
| 135 |
}
|
| 136 |
}
|
| 137 |
],
|
| 138 |
"special_tokens": {
|
| 139 |
-
"
|
| 140 |
-
"id": "
|
| 141 |
"ids": [
|
| 142 |
2
|
| 143 |
],
|
| 144 |
"tokens": [
|
| 145 |
-
"
|
| 146 |
]
|
| 147 |
},
|
| 148 |
-
"
|
| 149 |
-
"id": "
|
| 150 |
"ids": [
|
| 151 |
3
|
| 152 |
],
|
| 153 |
"tokens": [
|
| 154 |
-
"
|
| 155 |
]
|
| 156 |
}
|
| 157 |
}
|
|
@@ -172,7 +172,7 @@
|
|
| 172 |
"unk_id": 0,
|
| 173 |
"vocab": [
|
| 174 |
[
|
| 175 |
-
"
|
| 176 |
-1000.0
|
| 177 |
],
|
| 178 |
[
|
|
@@ -180,19 +180,19 @@
|
|
| 180 |
-1000.0
|
| 181 |
],
|
| 182 |
[
|
| 183 |
-
"
|
| 184 |
-1000.0
|
| 185 |
],
|
| 186 |
[
|
| 187 |
-
"
|
| 188 |
-1000.0
|
| 189 |
],
|
| 190 |
[
|
| 191 |
-
"
|
| 192 |
-1000.0
|
| 193 |
],
|
| 194 |
[
|
| 195 |
-
"
|
| 196 |
-1000.0
|
| 197 |
],
|
| 198 |
[
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
| 8 |
+
"content": "[PAD]",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
+
"content": "[CLS]",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
+
"content": "[SEP]",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
+
"content": "[MASK]",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 5,
|
| 53 |
+
"content": "[EOD]",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
|
|
| 86 |
"single": [
|
| 87 |
{
|
| 88 |
"SpecialToken": {
|
| 89 |
+
"id": "[CLS]",
|
| 90 |
"type_id": 0
|
| 91 |
}
|
| 92 |
},
|
|
|
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"SpecialToken": {
|
| 101 |
+
"id": "[SEP]",
|
| 102 |
"type_id": 0
|
| 103 |
}
|
| 104 |
}
|
|
|
|
| 106 |
"pair": [
|
| 107 |
{
|
| 108 |
"SpecialToken": {
|
| 109 |
+
"id": "[CLS]",
|
| 110 |
"type_id": 0
|
| 111 |
}
|
| 112 |
},
|
|
|
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"SpecialToken": {
|
| 121 |
+
"id": "[SEP]",
|
| 122 |
"type_id": 0
|
| 123 |
}
|
| 124 |
},
|
|
|
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"SpecialToken": {
|
| 133 |
+
"id": "[SEP]",
|
| 134 |
"type_id": 1
|
| 135 |
}
|
| 136 |
}
|
| 137 |
],
|
| 138 |
"special_tokens": {
|
| 139 |
+
"[CLS]": {
|
| 140 |
+
"id": "[CLS]",
|
| 141 |
"ids": [
|
| 142 |
2
|
| 143 |
],
|
| 144 |
"tokens": [
|
| 145 |
+
"[CLS]"
|
| 146 |
]
|
| 147 |
},
|
| 148 |
+
"[SEP]": {
|
| 149 |
+
"id": "[SEP]",
|
| 150 |
"ids": [
|
| 151 |
3
|
| 152 |
],
|
| 153 |
"tokens": [
|
| 154 |
+
"[SEP]"
|
| 155 |
]
|
| 156 |
}
|
| 157 |
}
|
|
|
|
| 172 |
"unk_id": 0,
|
| 173 |
"vocab": [
|
| 174 |
[
|
| 175 |
+
"[PAD]",
|
| 176 |
-1000.0
|
| 177 |
],
|
| 178 |
[
|
|
|
|
| 180 |
-1000.0
|
| 181 |
],
|
| 182 |
[
|
| 183 |
+
"[CLS]",
|
| 184 |
-1000.0
|
| 185 |
],
|
| 186 |
[
|
| 187 |
+
"[SEP]",
|
| 188 |
-1000.0
|
| 189 |
],
|
| 190 |
[
|
| 191 |
+
"[MASK]",
|
| 192 |
-1000.0
|
| 193 |
],
|
| 194 |
[
|
| 195 |
+
"[EOD]",
|
| 196 |
-1000.0
|
| 197 |
],
|
| 198 |
[
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
@@ -25,7 +25,7 @@
|
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
-
"content": "
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"4": {
|
| 36 |
-
"content": "
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"5": {
|
| 44 |
-
"content": "
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
@@ -66,17 +66,20 @@
|
|
| 66 |
}
|
| 67 |
},
|
| 68 |
"additional_special_tokens": [
|
| 69 |
-
"
|
| 70 |
],
|
| 71 |
"bos_token": "<s>",
|
| 72 |
"clean_up_tokenization_spaces": false,
|
| 73 |
-
"cls_token": "
|
| 74 |
-
"
|
|
|
|
| 75 |
"eos_token": "</s>",
|
| 76 |
-
"mask_token": "
|
| 77 |
"model_max_length": 2048,
|
| 78 |
-
"pad_token": "
|
| 79 |
-
"sep_token": "
|
| 80 |
-
"
|
|
|
|
|
|
|
| 81 |
"unk_token": "<unk>"
|
| 82 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
|
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
|
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"5": {
|
| 44 |
+
"content": "[EOD]",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 66 |
}
|
| 67 |
},
|
| 68 |
"additional_special_tokens": [
|
| 69 |
+
"[EOD]"
|
| 70 |
],
|
| 71 |
"bos_token": "<s>",
|
| 72 |
"clean_up_tokenization_spaces": false,
|
| 73 |
+
"cls_token": "[CLS]",
|
| 74 |
+
"do_lower_case": false,
|
| 75 |
+
"eod_token": "[EOD]",
|
| 76 |
"eos_token": "</s>",
|
| 77 |
+
"mask_token": "[MASK]",
|
| 78 |
"model_max_length": 2048,
|
| 79 |
+
"pad_token": "[PAD]",
|
| 80 |
+
"sep_token": "[SEP]",
|
| 81 |
+
"strip_accents": false,
|
| 82 |
+
"tokenize_chinese_chars": false,
|
| 83 |
+
"tokenizer_class": "BertTokenizer",
|
| 84 |
"unk_token": "<unk>"
|
| 85 |
}
|
unigram.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|