Commit
•
6a0b57a
1
Parent(s):
009c636
Upload tokenizer
Browse files- special_tokens_map.json +21 -3
- tokenizer_config.json +4 -0
special_tokens_map.json
CHANGED
|
@@ -101,7 +101,25 @@
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
-
"eos_token":
|
| 105 |
-
|
| 106 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
}
|
|
|
|
| 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 |
}
|
tokenizer_config.json
CHANGED
|
@@ -930,8 +930,12 @@
|
|
| 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 |
}
|
|
|
|
| 930 |
"clean_up_tokenization_spaces": true,
|
| 931 |
"eos_token": "</s>",
|
| 932 |
"extra_ids": 100,
|
| 933 |
+
"max_length": 512,
|
| 934 |
"model_max_length": 512,
|
| 935 |
"pad_token": "<pad>",
|
| 936 |
+
"stride": 0,
|
| 937 |
"tokenizer_class": "T5Tokenizer",
|
| 938 |
+
"truncation_side": "right",
|
| 939 |
+
"truncation_strategy": "longest_first",
|
| 940 |
"unk_token": "<unk>"
|
| 941 |
}
|