Upload tokenizer
Browse files- tokenizer_config.json +4 -56
tokenizer_config.json
CHANGED
|
@@ -1,62 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<cls>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<pad>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "<eos>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "<unk>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"31": {
|
| 36 |
-
"content": "|",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"32": {
|
| 44 |
-
"content": "<mask>",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
}
|
| 51 |
-
},
|
| 52 |
-
"additional_special_tokens": [
|
| 53 |
-
"|"
|
| 54 |
-
],
|
| 55 |
-
"bos_token": "<cls>",
|
| 56 |
-
"clean_up_tokenization_spaces": false,
|
| 57 |
"cls_token": "<cls>",
|
| 58 |
"eos_token": "<eos>",
|
| 59 |
-
"extra_special_tokens":
|
|
|
|
|
|
|
| 60 |
"mask_token": "<mask>",
|
| 61 |
"model_max_length": 1000000000000000019884624838656,
|
| 62 |
"pad_token": "<pad>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"cls_token": "<cls>",
|
| 4 |
"eos_token": "<eos>",
|
| 5 |
+
"extra_special_tokens": [
|
| 6 |
+
"|"
|
| 7 |
+
],
|
| 8 |
"mask_token": "<mask>",
|
| 9 |
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
"pad_token": "<pad>",
|