Upload ContactDoc fixed-vocab tokenizer
Browse files- tokenizer.json +0 -45
- tokenizer_config.json +0 -7
tokenizer.json
CHANGED
|
@@ -21,24 +21,6 @@
|
|
| 21 |
"normalized": false,
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
-
{
|
| 25 |
-
"id": 2,
|
| 26 |
-
"content": "<begin_contacts>",
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"rstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"special": true
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 3,
|
| 35 |
-
"content": "<end_contacts>",
|
| 36 |
-
"single_word": false,
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"rstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"special": true
|
| 41 |
-
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
"content": "<end>",
|
|
@@ -48,33 +30,6 @@
|
|
| 48 |
"normalized": false,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
-
{
|
| 52 |
-
"id": 5,
|
| 53 |
-
"content": "<newline>",
|
| 54 |
-
"single_word": false,
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"normalized": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"id": 6,
|
| 62 |
-
"content": "<end_of_document>",
|
| 63 |
-
"single_word": false,
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"normalized": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"id": 7,
|
| 71 |
-
"content": "<deterministic-positives-only>",
|
| 72 |
-
"single_word": false,
|
| 73 |
-
"lstrip": false,
|
| 74 |
-
"rstrip": false,
|
| 75 |
-
"normalized": false,
|
| 76 |
-
"special": true
|
| 77 |
-
},
|
| 78 |
{
|
| 79 |
"id": 27,
|
| 80 |
"content": "<UNK>",
|
|
|
|
| 21 |
"normalized": false,
|
| 22 |
"special": true
|
| 23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
{
|
| 25 |
"id": 4,
|
| 26 |
"content": "<end>",
|
|
|
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{
|
| 34 |
"id": 27,
|
| 35 |
"content": "<UNK>",
|
tokenizer_config.json
CHANGED
|
@@ -2,13 +2,6 @@
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<begin_sequence>",
|
| 4 |
"eos_token": "<end>",
|
| 5 |
-
"extra_special_tokens": [
|
| 6 |
-
"<begin_contacts>",
|
| 7 |
-
"<end_contacts>",
|
| 8 |
-
"<newline>",
|
| 9 |
-
"<end_of_document>",
|
| 10 |
-
"<deterministic-positives-only>"
|
| 11 |
-
],
|
| 12 |
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
"pad_token": "<pad>",
|
| 14 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<begin_sequence>",
|
| 4 |
"eos_token": "<end>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
"pad_token": "<pad>",
|
| 7 |
"tokenizer_class": "PreTrainedTokenizerFast",
|