새롭게 업데이트된 토크나이저
Browse files- added_tokens.json +8 -4
- special_tokens_map.json +58 -0
- tokenizer.json +43 -7
- tokenizer_config.json +49 -7
added_tokens.json
CHANGED
|
@@ -1,10 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"$~bos$": 50257,
|
| 3 |
-
"$~dev$":
|
| 4 |
"$~eos$": 50256,
|
| 5 |
-
"$~
|
|
|
|
|
|
|
|
|
|
| 6 |
"$~pad$": 50258,
|
| 7 |
-
"$~somebody$":
|
| 8 |
-
"$~
|
|
|
|
| 9 |
"$~unk$": 50259
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"$~bos$": 50257,
|
| 3 |
+
"$~dev$": 50260,
|
| 4 |
"$~eos$": 50256,
|
| 5 |
+
"$~func-continue$": 50263,
|
| 6 |
+
"$~func-time$": 50262,
|
| 7 |
+
"$~info$": 50264,
|
| 8 |
+
"$~me$": 50265,
|
| 9 |
"$~pad$": 50258,
|
| 10 |
+
"$~somebody$": 50266,
|
| 11 |
+
"$~tfot$": 50261,
|
| 12 |
+
"$~time$": 50267,
|
| 13 |
"$~unk$": 50259
|
| 14 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,62 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "$~bos$",
|
| 4 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "$~dev$",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "$~tfot$",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "$~func-time$",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "$~func-continue$",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "$~info$",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "$~me$",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "$~somebody$",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "$~time$",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
}
|
| 59 |
+
],
|
| 60 |
"bos_token": {
|
| 61 |
"content": "$~bos$",
|
| 62 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -41,8 +41,8 @@
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
| 44 |
-
"content": "$~
|
| 45 |
-
"single_word":
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
|
@@ -50,8 +50,8 @@
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
| 53 |
-
"content": "$~
|
| 54 |
-
"single_word":
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
|
@@ -59,8 +59,8 @@
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
| 62 |
-
"content": "$~
|
| 63 |
-
"single_word":
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
|
@@ -68,8 +68,44 @@
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
"content": "$~somebody$",
|
| 72 |
-
"single_word":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
"normalized": false,
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 50260,
|
| 44 |
+
"content": "$~dev$",
|
| 45 |
+
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 50261,
|
| 53 |
+
"content": "$~tfot$",
|
| 54 |
+
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 50262,
|
| 62 |
+
"content": "$~func-time$",
|
| 63 |
+
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 50263,
|
| 71 |
+
"content": "$~func-continue$",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 50264,
|
| 80 |
+
"content": "$~info$",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 50265,
|
| 89 |
+
"content": "$~me$",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 50266,
|
| 98 |
"content": "$~somebody$",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 50267,
|
| 107 |
+
"content": "$~time$",
|
| 108 |
+
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
"normalized": false,
|
tokenizer_config.json
CHANGED
|
@@ -35,38 +35,80 @@
|
|
| 35 |
"special": true
|
| 36 |
},
|
| 37 |
"50260": {
|
| 38 |
-
"content": "$~
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
| 42 |
-
"single_word":
|
| 43 |
"special": true
|
| 44 |
},
|
| 45 |
"50261": {
|
| 46 |
-
"content": "$~
|
| 47 |
"lstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
"rstrip": false,
|
| 50 |
-
"single_word":
|
| 51 |
"special": true
|
| 52 |
},
|
| 53 |
"50262": {
|
| 54 |
-
"content": "$~
|
| 55 |
"lstrip": false,
|
| 56 |
"normalized": false,
|
| 57 |
"rstrip": false,
|
| 58 |
-
"single_word":
|
| 59 |
"special": true
|
| 60 |
},
|
| 61 |
"50263": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"content": "$~somebody$",
|
| 63 |
"lstrip": false,
|
| 64 |
"normalized": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"single_word":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"special": true
|
| 68 |
}
|
| 69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
"bos_token": "$~bos$",
|
| 71 |
"clean_up_tokenization_spaces": true,
|
| 72 |
"eos_token": "$~eos$",
|
|
|
|
| 35 |
"special": true
|
| 36 |
},
|
| 37 |
"50260": {
|
| 38 |
+
"content": "$~dev$",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
"special": true
|
| 44 |
},
|
| 45 |
"50261": {
|
| 46 |
+
"content": "$~tfot$",
|
| 47 |
"lstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
"special": true
|
| 52 |
},
|
| 53 |
"50262": {
|
| 54 |
+
"content": "$~func-time$",
|
| 55 |
"lstrip": false,
|
| 56 |
"normalized": false,
|
| 57 |
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
"special": true
|
| 60 |
},
|
| 61 |
"50263": {
|
| 62 |
+
"content": "$~func-continue$",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"50264": {
|
| 70 |
+
"content": "$~info$",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"50265": {
|
| 78 |
+
"content": "$~me$",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"50266": {
|
| 86 |
"content": "$~somebody$",
|
| 87 |
"lstrip": false,
|
| 88 |
"normalized": false,
|
| 89 |
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"50267": {
|
| 94 |
+
"content": "$~time$",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
"special": true
|
| 100 |
}
|
| 101 |
},
|
| 102 |
+
"additional_special_tokens": [
|
| 103 |
+
"$~dev$",
|
| 104 |
+
"$~tfot$",
|
| 105 |
+
"$~func-time$",
|
| 106 |
+
"$~func-continue$",
|
| 107 |
+
"$~info$",
|
| 108 |
+
"$~me$",
|
| 109 |
+
"$~somebody$",
|
| 110 |
+
"$~time$"
|
| 111 |
+
],
|
| 112 |
"bos_token": "$~bos$",
|
| 113 |
"clean_up_tokenization_spaces": true,
|
| 114 |
"eos_token": "$~eos$",
|