Upload folder using huggingface_hub
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +51 -1
- tokenizer_config.json +9 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"pad_token": "[PAD]",
|
| 3 |
"unk_token": "[UNK]"
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
"pad_token": "[PAD]",
|
| 4 |
"unk_token": "[UNK]"
|
| 5 |
}
|
tokenizer.json
CHANGED
|
@@ -20,13 +20,63 @@
|
|
| 20 |
"rstrip": false,
|
| 21 |
"normalized": false,
|
| 22 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"normalizer": null,
|
| 26 |
"pre_tokenizer": {
|
| 27 |
"type": "Whitespace"
|
| 28 |
},
|
| 29 |
-
"post_processor":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"decoder": null,
|
| 31 |
"model": {
|
| 32 |
"type": "WordLevel",
|
|
|
|
| 20 |
"rstrip": false,
|
| 21 |
"normalized": false,
|
| 22 |
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 112969,
|
| 26 |
+
"content": "[CLS]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": null,
|
| 35 |
"pre_tokenizer": {
|
| 36 |
"type": "Whitespace"
|
| 37 |
},
|
| 38 |
+
"post_processor": {
|
| 39 |
+
"type": "TemplateProcessing",
|
| 40 |
+
"single": [
|
| 41 |
+
{
|
| 42 |
+
"SpecialToken": {
|
| 43 |
+
"id": "[CLS]",
|
| 44 |
+
"type_id": 0
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"Sequence": {
|
| 49 |
+
"id": "A",
|
| 50 |
+
"type_id": 0
|
| 51 |
+
}
|
| 52 |
+
}
|
| 53 |
+
],
|
| 54 |
+
"pair": [
|
| 55 |
+
{
|
| 56 |
+
"Sequence": {
|
| 57 |
+
"id": "A",
|
| 58 |
+
"type_id": 0
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"Sequence": {
|
| 63 |
+
"id": "B",
|
| 64 |
+
"type_id": 1
|
| 65 |
+
}
|
| 66 |
+
}
|
| 67 |
+
],
|
| 68 |
+
"special_tokens": {
|
| 69 |
+
"[CLS]": {
|
| 70 |
+
"id": "[CLS]",
|
| 71 |
+
"ids": [
|
| 72 |
+
112969
|
| 73 |
+
],
|
| 74 |
+
"tokens": [
|
| 75 |
+
"[CLS]"
|
| 76 |
+
]
|
| 77 |
+
}
|
| 78 |
+
}
|
| 79 |
+
},
|
| 80 |
"decoder": null,
|
| 81 |
"model": {
|
| 82 |
"type": "WordLevel",
|
tokenizer_config.json
CHANGED
|
@@ -15,9 +15,18 @@
|
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
}
|
| 19 |
},
|
| 20 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 21 |
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
"pad_token": "[PAD]",
|
| 23 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
+
},
|
| 19 |
+
"112969": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
"clean_up_tokenization_spaces": true,
|
| 29 |
+
"cls_token": "[CLS]",
|
| 30 |
"model_max_length": 1000000000000000019884624838656,
|
| 31 |
"pad_token": "[PAD]",
|
| 32 |
"tokenizer_class": "PreTrainedTokenizerFast",
|