Upload folder using huggingface_hub
Browse files- added_tokens.json +101 -0
- special_tokens_map.json +103 -0
- tokenizer.json +2 -2
- tokenizer_config.json +912 -0
added_tokens.json
CHANGED
|
@@ -1,3 +1,104 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"[MASK]": 250101
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"--NME--": 250102,
|
| 3 |
+
"[E-0]": 250103,
|
| 4 |
+
"[E-10]": 250113,
|
| 5 |
+
"[E-11]": 250114,
|
| 6 |
+
"[E-12]": 250115,
|
| 7 |
+
"[E-13]": 250116,
|
| 8 |
+
"[E-14]": 250117,
|
| 9 |
+
"[E-15]": 250118,
|
| 10 |
+
"[E-16]": 250119,
|
| 11 |
+
"[E-17]": 250120,
|
| 12 |
+
"[E-18]": 250121,
|
| 13 |
+
"[E-19]": 250122,
|
| 14 |
+
"[E-1]": 250104,
|
| 15 |
+
"[E-20]": 250123,
|
| 16 |
+
"[E-21]": 250124,
|
| 17 |
+
"[E-22]": 250125,
|
| 18 |
+
"[E-23]": 250126,
|
| 19 |
+
"[E-24]": 250127,
|
| 20 |
+
"[E-25]": 250128,
|
| 21 |
+
"[E-26]": 250129,
|
| 22 |
+
"[E-27]": 250130,
|
| 23 |
+
"[E-28]": 250131,
|
| 24 |
+
"[E-29]": 250132,
|
| 25 |
+
"[E-2]": 250105,
|
| 26 |
+
"[E-30]": 250133,
|
| 27 |
+
"[E-31]": 250134,
|
| 28 |
+
"[E-32]": 250135,
|
| 29 |
+
"[E-33]": 250136,
|
| 30 |
+
"[E-34]": 250137,
|
| 31 |
+
"[E-35]": 250138,
|
| 32 |
+
"[E-36]": 250139,
|
| 33 |
+
"[E-37]": 250140,
|
| 34 |
+
"[E-38]": 250141,
|
| 35 |
+
"[E-39]": 250142,
|
| 36 |
+
"[E-3]": 250106,
|
| 37 |
+
"[E-40]": 250143,
|
| 38 |
+
"[E-41]": 250144,
|
| 39 |
+
"[E-42]": 250145,
|
| 40 |
+
"[E-43]": 250146,
|
| 41 |
+
"[E-44]": 250147,
|
| 42 |
+
"[E-45]": 250148,
|
| 43 |
+
"[E-46]": 250149,
|
| 44 |
+
"[E-47]": 250150,
|
| 45 |
+
"[E-48]": 250151,
|
| 46 |
+
"[E-49]": 250152,
|
| 47 |
+
"[E-4]": 250107,
|
| 48 |
+
"[E-50]": 250153,
|
| 49 |
+
"[E-51]": 250154,
|
| 50 |
+
"[E-52]": 250155,
|
| 51 |
+
"[E-53]": 250156,
|
| 52 |
+
"[E-54]": 250157,
|
| 53 |
+
"[E-55]": 250158,
|
| 54 |
+
"[E-56]": 250159,
|
| 55 |
+
"[E-57]": 250160,
|
| 56 |
+
"[E-58]": 250161,
|
| 57 |
+
"[E-59]": 250162,
|
| 58 |
+
"[E-5]": 250108,
|
| 59 |
+
"[E-60]": 250163,
|
| 60 |
+
"[E-61]": 250164,
|
| 61 |
+
"[E-62]": 250165,
|
| 62 |
+
"[E-63]": 250166,
|
| 63 |
+
"[E-64]": 250167,
|
| 64 |
+
"[E-65]": 250168,
|
| 65 |
+
"[E-66]": 250169,
|
| 66 |
+
"[E-67]": 250170,
|
| 67 |
+
"[E-68]": 250171,
|
| 68 |
+
"[E-69]": 250172,
|
| 69 |
+
"[E-6]": 250109,
|
| 70 |
+
"[E-70]": 250173,
|
| 71 |
+
"[E-71]": 250174,
|
| 72 |
+
"[E-72]": 250175,
|
| 73 |
+
"[E-73]": 250176,
|
| 74 |
+
"[E-74]": 250177,
|
| 75 |
+
"[E-75]": 250178,
|
| 76 |
+
"[E-76]": 250179,
|
| 77 |
+
"[E-77]": 250180,
|
| 78 |
+
"[E-78]": 250181,
|
| 79 |
+
"[E-79]": 250182,
|
| 80 |
+
"[E-7]": 250110,
|
| 81 |
+
"[E-80]": 250183,
|
| 82 |
+
"[E-81]": 250184,
|
| 83 |
+
"[E-82]": 250185,
|
| 84 |
+
"[E-83]": 250186,
|
| 85 |
+
"[E-84]": 250187,
|
| 86 |
+
"[E-85]": 250188,
|
| 87 |
+
"[E-86]": 250189,
|
| 88 |
+
"[E-87]": 250190,
|
| 89 |
+
"[E-88]": 250191,
|
| 90 |
+
"[E-89]": 250192,
|
| 91 |
+
"[E-8]": 250111,
|
| 92 |
+
"[E-90]": 250193,
|
| 93 |
+
"[E-91]": 250194,
|
| 94 |
+
"[E-92]": 250195,
|
| 95 |
+
"[E-93]": 250196,
|
| 96 |
+
"[E-94]": 250197,
|
| 97 |
+
"[E-95]": 250198,
|
| 98 |
+
"[E-96]": 250199,
|
| 99 |
+
"[E-97]": 250200,
|
| 100 |
+
"[E-98]": 250201,
|
| 101 |
+
"[E-99]": 250202,
|
| 102 |
+
"[E-9]": 250112,
|
| 103 |
"[MASK]": 250101
|
| 104 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,107 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "[CLS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"eos_token": "[SEP]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"--NME--",
|
| 4 |
+
"[E-0]",
|
| 5 |
+
"[E-1]",
|
| 6 |
+
"[E-2]",
|
| 7 |
+
"[E-3]",
|
| 8 |
+
"[E-4]",
|
| 9 |
+
"[E-5]",
|
| 10 |
+
"[E-6]",
|
| 11 |
+
"[E-7]",
|
| 12 |
+
"[E-8]",
|
| 13 |
+
"[E-9]",
|
| 14 |
+
"[E-10]",
|
| 15 |
+
"[E-11]",
|
| 16 |
+
"[E-12]",
|
| 17 |
+
"[E-13]",
|
| 18 |
+
"[E-14]",
|
| 19 |
+
"[E-15]",
|
| 20 |
+
"[E-16]",
|
| 21 |
+
"[E-17]",
|
| 22 |
+
"[E-18]",
|
| 23 |
+
"[E-19]",
|
| 24 |
+
"[E-20]",
|
| 25 |
+
"[E-21]",
|
| 26 |
+
"[E-22]",
|
| 27 |
+
"[E-23]",
|
| 28 |
+
"[E-24]",
|
| 29 |
+
"[E-25]",
|
| 30 |
+
"[E-26]",
|
| 31 |
+
"[E-27]",
|
| 32 |
+
"[E-28]",
|
| 33 |
+
"[E-29]",
|
| 34 |
+
"[E-30]",
|
| 35 |
+
"[E-31]",
|
| 36 |
+
"[E-32]",
|
| 37 |
+
"[E-33]",
|
| 38 |
+
"[E-34]",
|
| 39 |
+
"[E-35]",
|
| 40 |
+
"[E-36]",
|
| 41 |
+
"[E-37]",
|
| 42 |
+
"[E-38]",
|
| 43 |
+
"[E-39]",
|
| 44 |
+
"[E-40]",
|
| 45 |
+
"[E-41]",
|
| 46 |
+
"[E-42]",
|
| 47 |
+
"[E-43]",
|
| 48 |
+
"[E-44]",
|
| 49 |
+
"[E-45]",
|
| 50 |
+
"[E-46]",
|
| 51 |
+
"[E-47]",
|
| 52 |
+
"[E-48]",
|
| 53 |
+
"[E-49]",
|
| 54 |
+
"[E-50]",
|
| 55 |
+
"[E-51]",
|
| 56 |
+
"[E-52]",
|
| 57 |
+
"[E-53]",
|
| 58 |
+
"[E-54]",
|
| 59 |
+
"[E-55]",
|
| 60 |
+
"[E-56]",
|
| 61 |
+
"[E-57]",
|
| 62 |
+
"[E-58]",
|
| 63 |
+
"[E-59]",
|
| 64 |
+
"[E-60]",
|
| 65 |
+
"[E-61]",
|
| 66 |
+
"[E-62]",
|
| 67 |
+
"[E-63]",
|
| 68 |
+
"[E-64]",
|
| 69 |
+
"[E-65]",
|
| 70 |
+
"[E-66]",
|
| 71 |
+
"[E-67]",
|
| 72 |
+
"[E-68]",
|
| 73 |
+
"[E-69]",
|
| 74 |
+
"[E-70]",
|
| 75 |
+
"[E-71]",
|
| 76 |
+
"[E-72]",
|
| 77 |
+
"[E-73]",
|
| 78 |
+
"[E-74]",
|
| 79 |
+
"[E-75]",
|
| 80 |
+
"[E-76]",
|
| 81 |
+
"[E-77]",
|
| 82 |
+
"[E-78]",
|
| 83 |
+
"[E-79]",
|
| 84 |
+
"[E-80]",
|
| 85 |
+
"[E-81]",
|
| 86 |
+
"[E-82]",
|
| 87 |
+
"[E-83]",
|
| 88 |
+
"[E-84]",
|
| 89 |
+
"[E-85]",
|
| 90 |
+
"[E-86]",
|
| 91 |
+
"[E-87]",
|
| 92 |
+
"[E-88]",
|
| 93 |
+
"[E-89]",
|
| 94 |
+
"[E-90]",
|
| 95 |
+
"[E-91]",
|
| 96 |
+
"[E-92]",
|
| 97 |
+
"[E-93]",
|
| 98 |
+
"[E-94]",
|
| 99 |
+
"[E-95]",
|
| 100 |
+
"[E-96]",
|
| 101 |
+
"[E-97]",
|
| 102 |
+
"[E-98]",
|
| 103 |
+
"[E-99]"
|
| 104 |
+
],
|
| 105 |
"bos_token": "[CLS]",
|
| 106 |
"cls_token": "[CLS]",
|
| 107 |
"eos_token": "[SEP]",
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b38b963be88cfff37b4f83908ee2f8c1480c38ff03a5822512377c427e13b44e
|
| 3 |
+
size 16349848
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "[PAD]",
|
|
@@ -39,8 +40,919 @@
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"bos_token": "[CLS]",
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "[CLS]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "[PAD]",
|
|
|
|
| 40 |
"rstrip": false,
|
| 41 |
"single_word": false,
|
| 42 |
"special": true
|
| 43 |
+
},
|
| 44 |
+
"250102": {
|
| 45 |
+
"content": "--NME--",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"250103": {
|
| 53 |
+
"content": "[E-0]",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"250104": {
|
| 61 |
+
"content": "[E-1]",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"250105": {
|
| 69 |
+
"content": "[E-2]",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"250106": {
|
| 77 |
+
"content": "[E-3]",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"250107": {
|
| 85 |
+
"content": "[E-4]",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"250108": {
|
| 93 |
+
"content": "[E-5]",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"250109": {
|
| 101 |
+
"content": "[E-6]",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"250110": {
|
| 109 |
+
"content": "[E-7]",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"250111": {
|
| 117 |
+
"content": "[E-8]",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"250112": {
|
| 125 |
+
"content": "[E-9]",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"250113": {
|
| 133 |
+
"content": "[E-10]",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"250114": {
|
| 141 |
+
"content": "[E-11]",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"250115": {
|
| 149 |
+
"content": "[E-12]",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"250116": {
|
| 157 |
+
"content": "[E-13]",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"250117": {
|
| 165 |
+
"content": "[E-14]",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"250118": {
|
| 173 |
+
"content": "[E-15]",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"250119": {
|
| 181 |
+
"content": "[E-16]",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"250120": {
|
| 189 |
+
"content": "[E-17]",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"250121": {
|
| 197 |
+
"content": "[E-18]",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"250122": {
|
| 205 |
+
"content": "[E-19]",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"250123": {
|
| 213 |
+
"content": "[E-20]",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"250124": {
|
| 221 |
+
"content": "[E-21]",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"250125": {
|
| 229 |
+
"content": "[E-22]",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"250126": {
|
| 237 |
+
"content": "[E-23]",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"250127": {
|
| 245 |
+
"content": "[E-24]",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"250128": {
|
| 253 |
+
"content": "[E-25]",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"250129": {
|
| 261 |
+
"content": "[E-26]",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"250130": {
|
| 269 |
+
"content": "[E-27]",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"250131": {
|
| 277 |
+
"content": "[E-28]",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"250132": {
|
| 285 |
+
"content": "[E-29]",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"250133": {
|
| 293 |
+
"content": "[E-30]",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"250134": {
|
| 301 |
+
"content": "[E-31]",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"250135": {
|
| 309 |
+
"content": "[E-32]",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"250136": {
|
| 317 |
+
"content": "[E-33]",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"250137": {
|
| 325 |
+
"content": "[E-34]",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"250138": {
|
| 333 |
+
"content": "[E-35]",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"250139": {
|
| 341 |
+
"content": "[E-36]",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"250140": {
|
| 349 |
+
"content": "[E-37]",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"250141": {
|
| 357 |
+
"content": "[E-38]",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"250142": {
|
| 365 |
+
"content": "[E-39]",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"250143": {
|
| 373 |
+
"content": "[E-40]",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"250144": {
|
| 381 |
+
"content": "[E-41]",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"250145": {
|
| 389 |
+
"content": "[E-42]",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"250146": {
|
| 397 |
+
"content": "[E-43]",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"250147": {
|
| 405 |
+
"content": "[E-44]",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"250148": {
|
| 413 |
+
"content": "[E-45]",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"250149": {
|
| 421 |
+
"content": "[E-46]",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"250150": {
|
| 429 |
+
"content": "[E-47]",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"250151": {
|
| 437 |
+
"content": "[E-48]",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"250152": {
|
| 445 |
+
"content": "[E-49]",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"250153": {
|
| 453 |
+
"content": "[E-50]",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"250154": {
|
| 461 |
+
"content": "[E-51]",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"250155": {
|
| 469 |
+
"content": "[E-52]",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"250156": {
|
| 477 |
+
"content": "[E-53]",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"250157": {
|
| 485 |
+
"content": "[E-54]",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"250158": {
|
| 493 |
+
"content": "[E-55]",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"250159": {
|
| 501 |
+
"content": "[E-56]",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"250160": {
|
| 509 |
+
"content": "[E-57]",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"250161": {
|
| 517 |
+
"content": "[E-58]",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"250162": {
|
| 525 |
+
"content": "[E-59]",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"250163": {
|
| 533 |
+
"content": "[E-60]",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"250164": {
|
| 541 |
+
"content": "[E-61]",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"250165": {
|
| 549 |
+
"content": "[E-62]",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"250166": {
|
| 557 |
+
"content": "[E-63]",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"250167": {
|
| 565 |
+
"content": "[E-64]",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"250168": {
|
| 573 |
+
"content": "[E-65]",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"250169": {
|
| 581 |
+
"content": "[E-66]",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"250170": {
|
| 589 |
+
"content": "[E-67]",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"250171": {
|
| 597 |
+
"content": "[E-68]",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"250172": {
|
| 605 |
+
"content": "[E-69]",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"250173": {
|
| 613 |
+
"content": "[E-70]",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"250174": {
|
| 621 |
+
"content": "[E-71]",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"250175": {
|
| 629 |
+
"content": "[E-72]",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"250176": {
|
| 637 |
+
"content": "[E-73]",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"250177": {
|
| 645 |
+
"content": "[E-74]",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"250178": {
|
| 653 |
+
"content": "[E-75]",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"250179": {
|
| 661 |
+
"content": "[E-76]",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"250180": {
|
| 669 |
+
"content": "[E-77]",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"250181": {
|
| 677 |
+
"content": "[E-78]",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"250182": {
|
| 685 |
+
"content": "[E-79]",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"250183": {
|
| 693 |
+
"content": "[E-80]",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"250184": {
|
| 701 |
+
"content": "[E-81]",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"250185": {
|
| 709 |
+
"content": "[E-82]",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"250186": {
|
| 717 |
+
"content": "[E-83]",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"250187": {
|
| 725 |
+
"content": "[E-84]",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"250188": {
|
| 733 |
+
"content": "[E-85]",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"250189": {
|
| 741 |
+
"content": "[E-86]",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"250190": {
|
| 749 |
+
"content": "[E-87]",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"250191": {
|
| 757 |
+
"content": "[E-88]",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"250192": {
|
| 765 |
+
"content": "[E-89]",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"250193": {
|
| 773 |
+
"content": "[E-90]",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"250194": {
|
| 781 |
+
"content": "[E-91]",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"250195": {
|
| 789 |
+
"content": "[E-92]",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"250196": {
|
| 797 |
+
"content": "[E-93]",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"250197": {
|
| 805 |
+
"content": "[E-94]",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"250198": {
|
| 813 |
+
"content": "[E-95]",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"250199": {
|
| 821 |
+
"content": "[E-96]",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"250200": {
|
| 829 |
+
"content": "[E-97]",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"250201": {
|
| 837 |
+
"content": "[E-98]",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
},
|
| 844 |
+
"250202": {
|
| 845 |
+
"content": "[E-99]",
|
| 846 |
+
"lstrip": false,
|
| 847 |
+
"normalized": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"single_word": false,
|
| 850 |
+
"special": true
|
| 851 |
}
|
| 852 |
},
|
| 853 |
+
"additional_special_tokens": [
|
| 854 |
+
"--NME--",
|
| 855 |
+
"[E-0]",
|
| 856 |
+
"[E-1]",
|
| 857 |
+
"[E-2]",
|
| 858 |
+
"[E-3]",
|
| 859 |
+
"[E-4]",
|
| 860 |
+
"[E-5]",
|
| 861 |
+
"[E-6]",
|
| 862 |
+
"[E-7]",
|
| 863 |
+
"[E-8]",
|
| 864 |
+
"[E-9]",
|
| 865 |
+
"[E-10]",
|
| 866 |
+
"[E-11]",
|
| 867 |
+
"[E-12]",
|
| 868 |
+
"[E-13]",
|
| 869 |
+
"[E-14]",
|
| 870 |
+
"[E-15]",
|
| 871 |
+
"[E-16]",
|
| 872 |
+
"[E-17]",
|
| 873 |
+
"[E-18]",
|
| 874 |
+
"[E-19]",
|
| 875 |
+
"[E-20]",
|
| 876 |
+
"[E-21]",
|
| 877 |
+
"[E-22]",
|
| 878 |
+
"[E-23]",
|
| 879 |
+
"[E-24]",
|
| 880 |
+
"[E-25]",
|
| 881 |
+
"[E-26]",
|
| 882 |
+
"[E-27]",
|
| 883 |
+
"[E-28]",
|
| 884 |
+
"[E-29]",
|
| 885 |
+
"[E-30]",
|
| 886 |
+
"[E-31]",
|
| 887 |
+
"[E-32]",
|
| 888 |
+
"[E-33]",
|
| 889 |
+
"[E-34]",
|
| 890 |
+
"[E-35]",
|
| 891 |
+
"[E-36]",
|
| 892 |
+
"[E-37]",
|
| 893 |
+
"[E-38]",
|
| 894 |
+
"[E-39]",
|
| 895 |
+
"[E-40]",
|
| 896 |
+
"[E-41]",
|
| 897 |
+
"[E-42]",
|
| 898 |
+
"[E-43]",
|
| 899 |
+
"[E-44]",
|
| 900 |
+
"[E-45]",
|
| 901 |
+
"[E-46]",
|
| 902 |
+
"[E-47]",
|
| 903 |
+
"[E-48]",
|
| 904 |
+
"[E-49]",
|
| 905 |
+
"[E-50]",
|
| 906 |
+
"[E-51]",
|
| 907 |
+
"[E-52]",
|
| 908 |
+
"[E-53]",
|
| 909 |
+
"[E-54]",
|
| 910 |
+
"[E-55]",
|
| 911 |
+
"[E-56]",
|
| 912 |
+
"[E-57]",
|
| 913 |
+
"[E-58]",
|
| 914 |
+
"[E-59]",
|
| 915 |
+
"[E-60]",
|
| 916 |
+
"[E-61]",
|
| 917 |
+
"[E-62]",
|
| 918 |
+
"[E-63]",
|
| 919 |
+
"[E-64]",
|
| 920 |
+
"[E-65]",
|
| 921 |
+
"[E-66]",
|
| 922 |
+
"[E-67]",
|
| 923 |
+
"[E-68]",
|
| 924 |
+
"[E-69]",
|
| 925 |
+
"[E-70]",
|
| 926 |
+
"[E-71]",
|
| 927 |
+
"[E-72]",
|
| 928 |
+
"[E-73]",
|
| 929 |
+
"[E-74]",
|
| 930 |
+
"[E-75]",
|
| 931 |
+
"[E-76]",
|
| 932 |
+
"[E-77]",
|
| 933 |
+
"[E-78]",
|
| 934 |
+
"[E-79]",
|
| 935 |
+
"[E-80]",
|
| 936 |
+
"[E-81]",
|
| 937 |
+
"[E-82]",
|
| 938 |
+
"[E-83]",
|
| 939 |
+
"[E-84]",
|
| 940 |
+
"[E-85]",
|
| 941 |
+
"[E-86]",
|
| 942 |
+
"[E-87]",
|
| 943 |
+
"[E-88]",
|
| 944 |
+
"[E-89]",
|
| 945 |
+
"[E-90]",
|
| 946 |
+
"[E-91]",
|
| 947 |
+
"[E-92]",
|
| 948 |
+
"[E-93]",
|
| 949 |
+
"[E-94]",
|
| 950 |
+
"[E-95]",
|
| 951 |
+
"[E-96]",
|
| 952 |
+
"[E-97]",
|
| 953 |
+
"[E-98]",
|
| 954 |
+
"[E-99]"
|
| 955 |
+
],
|
| 956 |
"bos_token": "[CLS]",
|
| 957 |
"clean_up_tokenization_spaces": true,
|
| 958 |
"cls_token": "[CLS]",
|