Upload tokenizer
Browse files- tokenizer.json +3 -1
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
@@ -7,7 +7,9 @@
|
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
-
"strategy":
|
|
|
|
|
|
|
| 11 |
"direction": "Right",
|
| 12 |
"pad_to_multiple_of": null,
|
| 13 |
"pad_id": 0,
|
|
|
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
| 15 |
"pad_id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -101,11 +101,11 @@
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
|
|
|
| 104 |
"eos_token": "</s>",
|
| 105 |
"extra_ids": 100,
|
| 106 |
"model_max_length": 512,
|
| 107 |
"pad_token": "<pad>",
|
| 108 |
-
"special_tokens_map_file": null,
|
| 109 |
"tokenizer_class": "T5Tokenizer",
|
| 110 |
"unk_token": "<unk>"
|
| 111 |
}
|
|
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
"eos_token": "</s>",
|
| 106 |
"extra_ids": 100,
|
| 107 |
"model_max_length": 512,
|
| 108 |
"pad_token": "<pad>",
|
|
|
|
| 109 |
"tokenizer_class": "T5Tokenizer",
|
| 110 |
"unk_token": "<unk>"
|
| 111 |
}
|