special_tokens_map.json CHANGED
@@ -101,25 +101,7 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": {
105
- "content": "</s>",
106
- "lstrip": false,
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -931,10 +931,8 @@
931
  "device_map": "auto",
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
- "legacy": true,
935
  "model_max_length": 512,
936
  "pad_token": "<pad>",
937
- "sp_model_kwargs": {},
938
  "tokenizer_class": "T5Tokenizer",
939
  "unk_token": "<unk>"
940
  }
 
931
  "device_map": "auto",
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
 
934
  "model_max_length": 512,
935
  "pad_token": "<pad>",
 
936
  "tokenizer_class": "T5Tokenizer",
937
  "unk_token": "<unk>"
938
  }