Upload VIT5-base-Distractors-Generation tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +21 -3
- spiece.model +3 -0
- tokenizer.json +14 -2
- tokenizer_config.json +7 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<sep>": 36096
|
| 3 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -97,8 +97,20 @@
|
|
| 97 |
"<extra_id_94>",
|
| 98 |
"<extra_id_95>"
|
| 99 |
],
|
| 100 |
-
"eos_token":
|
| 101 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
"sep_token": {
|
| 103 |
"content": "<sep>",
|
| 104 |
"lstrip": false,
|
|
@@ -106,5 +118,11 @@
|
|
| 106 |
"rstrip": false,
|
| 107 |
"single_word": false
|
| 108 |
},
|
| 109 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
}
|
|
|
|
| 97 |
"<extra_id_94>",
|
| 98 |
"<extra_id_95>"
|
| 99 |
],
|
| 100 |
+
"eos_token": {
|
| 101 |
+
"content": "</s>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false
|
| 106 |
+
},
|
| 107 |
+
"pad_token": {
|
| 108 |
+
"content": "<pad>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false
|
| 113 |
+
},
|
| 114 |
"sep_token": {
|
| 115 |
"content": "<sep>",
|
| 116 |
"lstrip": false,
|
|
|
|
| 118 |
"rstrip": false,
|
| 119 |
"single_word": false
|
| 120 |
},
|
| 121 |
+
"unk_token": {
|
| 122 |
+
"content": "<unk>",
|
| 123 |
+
"lstrip": false,
|
| 124 |
+
"normalized": false,
|
| 125 |
+
"rstrip": false,
|
| 126 |
+
"single_word": false
|
| 127 |
+
}
|
| 128 |
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
|
| 3 |
+
size 820370
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 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": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": "BatchLongest",
|
| 11 |
+
"direction": "Right",
|
| 12 |
+
"pad_to_multiple_of": null,
|
| 13 |
+
"pad_id": 0,
|
| 14 |
+
"pad_type_id": 0,
|
| 15 |
+
"pad_token": "<pad>"
|
| 16 |
+
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -903,10 +903,17 @@
|
|
| 903 |
"eos_token": "</s>",
|
| 904 |
"extra_ids": 96,
|
| 905 |
"extra_special_tokens": {},
|
|
|
|
| 906 |
"model_max_length": 512,
|
|
|
|
| 907 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 908 |
"sep_token": "<sep>",
|
| 909 |
"sp_model_kwargs": {},
|
|
|
|
| 910 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
|
|
| 911 |
"unk_token": "<unk>"
|
| 912 |
}
|
|
|
|
| 903 |
"eos_token": "</s>",
|
| 904 |
"extra_ids": 96,
|
| 905 |
"extra_special_tokens": {},
|
| 906 |
+
"max_length": 512,
|
| 907 |
"model_max_length": 512,
|
| 908 |
+
"pad_to_multiple_of": null,
|
| 909 |
"pad_token": "<pad>",
|
| 910 |
+
"pad_token_type_id": 0,
|
| 911 |
+
"padding_side": "right",
|
| 912 |
"sep_token": "<sep>",
|
| 913 |
"sp_model_kwargs": {},
|
| 914 |
+
"stride": 0,
|
| 915 |
"tokenizer_class": "T5Tokenizer",
|
| 916 |
+
"truncation_side": "right",
|
| 917 |
+
"truncation_strategy": "longest_first",
|
| 918 |
"unk_token": "<unk>"
|
| 919 |
}
|