Redgalaxy2 commited on
Commit
836f7cb
·
verified ·
1 Parent(s): 5187b14

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -97,25 +97,7 @@
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
- "unk_token": {
115
- "content": "<unk>",
116
- "lstrip": false,
117
- "normalized": false,
118
- "rstrip": false,
119
- "single_word": false
120
- }
121
  }
 
97
  "<extra_id_94>",
98
  "<extra_id_95>"
99
  ],
100
+ "eos_token": "</s>",
101
+ "pad_token": "<pad>",
102
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  }
tokenizer.json CHANGED
@@ -1,14 +1,7 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": {
5
- "strategy": "BatchLongest",
6
- "direction": "Right",
7
- "pad_to_multiple_of": null,
8
- "pad_id": 0,
9
- "pad_type_id": 0,
10
- "pad_token": "<pad>"
11
- },
12
  "added_tokens": [
13
  {
14
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
tokenizer_config.json CHANGED
@@ -894,16 +894,9 @@
894
  "clean_up_tokenization_spaces": true,
895
  "eos_token": "</s>",
896
  "extra_ids": 96,
897
- "max_length": 64,
898
  "model_max_length": 1000000000000000019884624838656,
899
- "pad_to_multiple_of": null,
900
  "pad_token": "<pad>",
901
- "pad_token_type_id": 0,
902
- "padding_side": "right",
903
  "sp_model_kwargs": {},
904
- "stride": 0,
905
  "tokenizer_class": "T5Tokenizer",
906
- "truncation_side": "right",
907
- "truncation_strategy": "longest_first",
908
  "unk_token": "<unk>"
909
  }
 
894
  "clean_up_tokenization_spaces": true,
895
  "eos_token": "</s>",
896
  "extra_ids": 96,
 
897
  "model_max_length": 1000000000000000019884624838656,
 
898
  "pad_token": "<pad>",
 
 
899
  "sp_model_kwargs": {},
 
900
  "tokenizer_class": "T5Tokenizer",
 
 
901
  "unk_token": "<unk>"
902
  }