Upload tokenizer
Browse files- special_tokens_map.json +2 -2
- tokenizer_config.json +7 -0
special_tokens_map.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<s>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"sep_token": {
|
| 38 |
"content": "</s>",
|
| 39 |
"lstrip": false,
|
| 40 |
-
"normalized":
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
|
|
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 37 |
"sep_token": {
|
| 38 |
"content": "</s>",
|
| 39 |
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
tokenizer_config.json
CHANGED
|
@@ -55,11 +55,18 @@
|
|
| 55 |
"do_lower_case": true,
|
| 56 |
"eos_token": "</s>",
|
| 57 |
"mask_token": "<mask>",
|
|
|
|
| 58 |
"model_max_length": 512,
|
|
|
|
| 59 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 60 |
"sep_token": "</s>",
|
|
|
|
| 61 |
"strip_accents": null,
|
| 62 |
"tokenize_chinese_chars": true,
|
| 63 |
"tokenizer_class": "MPNetTokenizer",
|
|
|
|
|
|
|
| 64 |
"unk_token": "[UNK]"
|
| 65 |
}
|
|
|
|
| 55 |
"do_lower_case": true,
|
| 56 |
"eos_token": "</s>",
|
| 57 |
"mask_token": "<mask>",
|
| 58 |
+
"max_length": 512,
|
| 59 |
"model_max_length": 512,
|
| 60 |
+
"pad_to_multiple_of": null,
|
| 61 |
"pad_token": "<pad>",
|
| 62 |
+
"pad_token_type_id": 0,
|
| 63 |
+
"padding_side": "right",
|
| 64 |
"sep_token": "</s>",
|
| 65 |
+
"stride": 0,
|
| 66 |
"strip_accents": null,
|
| 67 |
"tokenize_chinese_chars": true,
|
| 68 |
"tokenizer_class": "MPNetTokenizer",
|
| 69 |
+
"truncation_side": "right",
|
| 70 |
+
"truncation_strategy": "longest_first",
|
| 71 |
"unk_token": "[UNK]"
|
| 72 |
}
|