Upload tokenizer
Browse files- added_tokens.json +2 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +10 -2
added_tokens.json
CHANGED
@@ -98,5 +98,6 @@
|
|
98 |
"<extra_id_97>": 32002,
|
99 |
"<extra_id_98>": 32001,
|
100 |
"<extra_id_99>": 32000,
|
101 |
-
"<extra_id_9>": 32090
|
|
|
102 |
}
|
|
|
98 |
"<extra_id_97>": 32002,
|
99 |
"<extra_id_98>": 32001,
|
100 |
"<extra_id_99>": 32000,
|
101 |
+
"<extra_id_9>": 32090,
|
102 |
+
"[PAD]": 32100
|
103 |
}
|
special_tokens_map.json
CHANGED
@@ -109,7 +109,7 @@
|
|
109 |
"single_word": false
|
110 |
},
|
111 |
"pad_token": {
|
112 |
-
"content": "
|
113 |
"lstrip": false,
|
114 |
"normalized": false,
|
115 |
"rstrip": false,
|
|
|
109 |
"single_word": false
|
110 |
},
|
111 |
"pad_token": {
|
112 |
+
"content": "[PAD]",
|
113 |
"lstrip": false,
|
114 |
"normalized": false,
|
115 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -823,6 +823,14 @@
|
|
823 |
"rstrip": false,
|
824 |
"single_word": false,
|
825 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
826 |
}
|
827 |
},
|
828 |
"additional_special_tokens": [
|
@@ -931,8 +939,8 @@
|
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
"legacy": true,
|
934 |
-
"model_max_length":
|
935 |
-
"pad_token": "
|
936 |
"sp_model_kwargs": {},
|
937 |
"tokenizer_class": "T5Tokenizer",
|
938 |
"unk_token": "<unk>"
|
|
|
823 |
"rstrip": false,
|
824 |
"single_word": false,
|
825 |
"special": true
|
826 |
+
},
|
827 |
+
"32100": {
|
828 |
+
"content": "[PAD]",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
}
|
835 |
},
|
836 |
"additional_special_tokens": [
|
|
|
939 |
"eos_token": "</s>",
|
940 |
"extra_ids": 100,
|
941 |
"legacy": true,
|
942 |
+
"model_max_length": 50,
|
943 |
+
"pad_token": "[PAD]",
|
944 |
"sp_model_kwargs": {},
|
945 |
"tokenizer_class": "T5Tokenizer",
|
946 |
"unk_token": "<unk>"
|