Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- vocab.txt +69 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
vocab.txt
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[PAD]
|
| 2 |
+
[UNK]
|
| 3 |
+
[CLS]
|
| 4 |
+
[SEP]
|
| 5 |
+
[MASK]
|
| 6 |
+
AAA
|
| 7 |
+
AAU
|
| 8 |
+
AAG
|
| 9 |
+
AAC
|
| 10 |
+
AUA
|
| 11 |
+
AUU
|
| 12 |
+
AUG
|
| 13 |
+
AUC
|
| 14 |
+
AGA
|
| 15 |
+
AGU
|
| 16 |
+
AGG
|
| 17 |
+
AGC
|
| 18 |
+
ACA
|
| 19 |
+
ACU
|
| 20 |
+
ACG
|
| 21 |
+
ACC
|
| 22 |
+
UAA
|
| 23 |
+
UAU
|
| 24 |
+
UAG
|
| 25 |
+
UAC
|
| 26 |
+
UUA
|
| 27 |
+
UUU
|
| 28 |
+
UUG
|
| 29 |
+
UUC
|
| 30 |
+
UGA
|
| 31 |
+
UGU
|
| 32 |
+
UGG
|
| 33 |
+
UGC
|
| 34 |
+
UCA
|
| 35 |
+
UCU
|
| 36 |
+
UCG
|
| 37 |
+
UCC
|
| 38 |
+
GAA
|
| 39 |
+
GAU
|
| 40 |
+
GAG
|
| 41 |
+
GAC
|
| 42 |
+
GUA
|
| 43 |
+
GUU
|
| 44 |
+
GUG
|
| 45 |
+
GUC
|
| 46 |
+
GGA
|
| 47 |
+
GGU
|
| 48 |
+
GGG
|
| 49 |
+
GGC
|
| 50 |
+
GCA
|
| 51 |
+
GCU
|
| 52 |
+
GCG
|
| 53 |
+
GCC
|
| 54 |
+
CAA
|
| 55 |
+
CAU
|
| 56 |
+
CAG
|
| 57 |
+
CAC
|
| 58 |
+
CUA
|
| 59 |
+
CUU
|
| 60 |
+
CUG
|
| 61 |
+
CUC
|
| 62 |
+
CGA
|
| 63 |
+
CGU
|
| 64 |
+
CGG
|
| 65 |
+
CGC
|
| 66 |
+
CCA
|
| 67 |
+
CCU
|
| 68 |
+
CCG
|
| 69 |
+
CCC
|