Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer.json +16 -2
- tokenizer_config.json +0 -7
special_tokens_map.json
CHANGED
@@ -101,25 +101,7 @@
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
-
"eos_token":
|
105 |
-
|
106 |
-
|
107 |
-
"normalized": false,
|
108 |
-
"rstrip": false,
|
109 |
-
"single_word": false
|
110 |
-
},
|
111 |
-
"pad_token": {
|
112 |
-
"content": "<pad>",
|
113 |
-
"lstrip": false,
|
114 |
-
"normalized": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"single_word": false
|
117 |
-
},
|
118 |
-
"unk_token": {
|
119 |
-
"content": "<unk>",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": false,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false
|
124 |
-
}
|
125 |
}
|
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
}
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 2,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 2
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
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,
|
tokenizer_config.json
CHANGED
@@ -930,15 +930,8 @@
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
-
"max_length": 2,
|
934 |
"model_max_length": 512,
|
935 |
-
"pad_to_multiple_of": null,
|
936 |
"pad_token": "<pad>",
|
937 |
-
"pad_token_type_id": 0,
|
938 |
-
"padding_side": "right",
|
939 |
-
"stride": 0,
|
940 |
"tokenizer_class": "T5Tokenizer",
|
941 |
-
"truncation_side": "right",
|
942 |
-
"truncation_strategy": "longest_first",
|
943 |
"unk_token": "<unk>"
|
944 |
}
|
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
|
|
933 |
"model_max_length": 512,
|
|
|
934 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
935 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
936 |
"unk_token": "<unk>"
|
937 |
}
|