Commit ·
79d3eae
1
Parent(s): 6de89f1
Training done
Browse files- added_tokens.json +14 -9
- special_tokens_map.json +1 -7
- tokenizer.json +14 -13
- tokenizer_config.json +143 -8
added_tokens.json
CHANGED
|
@@ -1,14 +1,19 @@
|
|
| 1 |
{
|
| 2 |
-
"</
|
| 3 |
-
"</
|
| 4 |
-
"</
|
| 5 |
-
"</
|
| 6 |
-
"<
|
| 7 |
-
"<
|
| 8 |
-
"<
|
| 9 |
-
"<
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"<s_iitcdip>": 57523,
|
| 11 |
"<s_johnson_electric>": 57533,
|
| 12 |
"<s_synthdog>": 57524,
|
| 13 |
-
"<sep/>": 57522
|
|
|
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"</s_1Pcode>": 57532,
|
| 4 |
+
"</s_1Tcode>": 57530,
|
| 5 |
+
"</s_Dcode>": 57528,
|
| 6 |
+
"</s_Qcode>": 57526,
|
| 7 |
+
"<mask>": 57521,
|
| 8 |
+
"<pad>": 1,
|
| 9 |
+
"<s>": 0,
|
| 10 |
+
"<s_1Pcode>": 57531,
|
| 11 |
+
"<s_1Tcode>": 57529,
|
| 12 |
+
"<s_Dcode>": 57527,
|
| 13 |
+
"<s_Qcode>": 57525,
|
| 14 |
"<s_iitcdip>": 57523,
|
| 15 |
"<s_johnson_electric>": 57533,
|
| 16 |
"<s_synthdog>": 57524,
|
| 17 |
+
"<sep/>": 57522,
|
| 18 |
+
"<unk>": 3
|
| 19 |
}
|
special_tokens_map.json
CHANGED
|
@@ -6,13 +6,7 @@
|
|
| 6 |
"bos_token": "<s>",
|
| 7 |
"cls_token": "<s>",
|
| 8 |
"eos_token": "</s>",
|
| 9 |
-
"mask_token":
|
| 10 |
-
"content": "<mask>",
|
| 11 |
-
"lstrip": true,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
"pad_token": "<pad>",
|
| 17 |
"sep_token": "</s>",
|
| 18 |
"unk_token": "<unk>"
|
|
|
|
| 6 |
"bos_token": "<s>",
|
| 7 |
"cls_token": "<s>",
|
| 8 |
"eos_token": "</s>",
|
| 9 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"pad_token": "<pad>",
|
| 11 |
"sep_token": "</s>",
|
| 12 |
"unk_token": "<unk>"
|
tokenizer.json
CHANGED
|
@@ -75,8 +75,8 @@
|
|
| 75 |
"id": 57523,
|
| 76 |
"content": "<s_iitcdip>",
|
| 77 |
"single_word": false,
|
| 78 |
-
"lstrip":
|
| 79 |
-
"rstrip":
|
| 80 |
"normalized": false,
|
| 81 |
"special": true
|
| 82 |
},
|
|
@@ -84,14 +84,14 @@
|
|
| 84 |
"id": 57524,
|
| 85 |
"content": "<s_synthdog>",
|
| 86 |
"single_word": false,
|
| 87 |
-
"lstrip":
|
| 88 |
-
"rstrip":
|
| 89 |
"normalized": false,
|
| 90 |
"special": true
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"id": 57525,
|
| 94 |
-
"content": "<
|
| 95 |
"single_word": false,
|
| 96 |
"lstrip": false,
|
| 97 |
"rstrip": false,
|
|
@@ -100,7 +100,7 @@
|
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"id": 57526,
|
| 103 |
-
"content": "</
|
| 104 |
"single_word": false,
|
| 105 |
"lstrip": false,
|
| 106 |
"rstrip": false,
|
|
@@ -109,7 +109,7 @@
|
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"id": 57527,
|
| 112 |
-
"content": "<
|
| 113 |
"single_word": false,
|
| 114 |
"lstrip": false,
|
| 115 |
"rstrip": false,
|
|
@@ -118,7 +118,7 @@
|
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"id": 57528,
|
| 121 |
-
"content": "</
|
| 122 |
"single_word": false,
|
| 123 |
"lstrip": false,
|
| 124 |
"rstrip": false,
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"id": 57529,
|
| 130 |
-
"content": "<
|
| 131 |
"single_word": false,
|
| 132 |
"lstrip": false,
|
| 133 |
"rstrip": false,
|
|
@@ -136,7 +136,7 @@
|
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"id": 57530,
|
| 139 |
-
"content": "</
|
| 140 |
"single_word": false,
|
| 141 |
"lstrip": false,
|
| 142 |
"rstrip": false,
|
|
@@ -145,7 +145,7 @@
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"id": 57531,
|
| 148 |
-
"content": "<
|
| 149 |
"single_word": false,
|
| 150 |
"lstrip": false,
|
| 151 |
"rstrip": false,
|
|
@@ -154,7 +154,7 @@
|
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"id": 57532,
|
| 157 |
-
"content": "</
|
| 158 |
"single_word": false,
|
| 159 |
"lstrip": false,
|
| 160 |
"rstrip": false,
|
|
@@ -230370,6 +230370,7 @@
|
|
| 230370 |
"<mask>",
|
| 230371 |
0.0
|
| 230372 |
]
|
| 230373 |
-
]
|
|
|
|
| 230374 |
}
|
| 230375 |
}
|
|
|
|
| 75 |
"id": 57523,
|
| 76 |
"content": "<s_iitcdip>",
|
| 77 |
"single_word": false,
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"rstrip": true,
|
| 80 |
"normalized": false,
|
| 81 |
"special": true
|
| 82 |
},
|
|
|
|
| 84 |
"id": 57524,
|
| 85 |
"content": "<s_synthdog>",
|
| 86 |
"single_word": false,
|
| 87 |
+
"lstrip": true,
|
| 88 |
+
"rstrip": true,
|
| 89 |
"normalized": false,
|
| 90 |
"special": true
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"id": 57525,
|
| 94 |
+
"content": "<s_Qcode>",
|
| 95 |
"single_word": false,
|
| 96 |
"lstrip": false,
|
| 97 |
"rstrip": false,
|
|
|
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"id": 57526,
|
| 103 |
+
"content": "</s_Qcode>",
|
| 104 |
"single_word": false,
|
| 105 |
"lstrip": false,
|
| 106 |
"rstrip": false,
|
|
|
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"id": 57527,
|
| 112 |
+
"content": "<s_Dcode>",
|
| 113 |
"single_word": false,
|
| 114 |
"lstrip": false,
|
| 115 |
"rstrip": false,
|
|
|
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"id": 57528,
|
| 121 |
+
"content": "</s_Dcode>",
|
| 122 |
"single_word": false,
|
| 123 |
"lstrip": false,
|
| 124 |
"rstrip": false,
|
|
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"id": 57529,
|
| 130 |
+
"content": "<s_1Tcode>",
|
| 131 |
"single_word": false,
|
| 132 |
"lstrip": false,
|
| 133 |
"rstrip": false,
|
|
|
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"id": 57530,
|
| 139 |
+
"content": "</s_1Tcode>",
|
| 140 |
"single_word": false,
|
| 141 |
"lstrip": false,
|
| 142 |
"rstrip": false,
|
|
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"id": 57531,
|
| 148 |
+
"content": "<s_1Pcode>",
|
| 149 |
"single_word": false,
|
| 150 |
"lstrip": false,
|
| 151 |
"rstrip": false,
|
|
|
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"id": 57532,
|
| 157 |
+
"content": "</s_1Pcode>",
|
| 158 |
"single_word": false,
|
| 159 |
"lstrip": false,
|
| 160 |
"rstrip": false,
|
|
|
|
| 230370 |
"<mask>",
|
| 230371 |
0.0
|
| 230372 |
]
|
| 230373 |
+
],
|
| 230374 |
+
"byte_fallback": false
|
| 230375 |
}
|
| 230376 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,16 +1,151 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "<s>",
|
| 5 |
"eos_token": "</s>",
|
| 6 |
-
"mask_token":
|
| 7 |
-
"__type": "AddedToken",
|
| 8 |
-
"content": "<mask>",
|
| 9 |
-
"lstrip": true,
|
| 10 |
-
"normalized": true,
|
| 11 |
-
"rstrip": false,
|
| 12 |
-
"single_word": false
|
| 13 |
-
},
|
| 14 |
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"processor_class": "DonutProcessor",
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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": "</s>",
|
| 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 |
+
"57521": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"57522": {
|
| 44 |
+
"content": "<sep/>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"57523": {
|
| 52 |
+
"content": "<s_iitcdip>",
|
| 53 |
+
"lstrip": true,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": true,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"57524": {
|
| 60 |
+
"content": "<s_synthdog>",
|
| 61 |
+
"lstrip": true,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": true,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"57525": {
|
| 68 |
+
"content": "<s_Qcode>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"57526": {
|
| 76 |
+
"content": "</s_Qcode>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"57527": {
|
| 84 |
+
"content": "<s_Dcode>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"57528": {
|
| 92 |
+
"content": "</s_Dcode>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"57529": {
|
| 100 |
+
"content": "<s_1Tcode>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"57530": {
|
| 108 |
+
"content": "</s_1Tcode>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"57531": {
|
| 116 |
+
"content": "<s_1Pcode>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"57532": {
|
| 124 |
+
"content": "</s_1Pcode>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"57533": {
|
| 132 |
+
"content": "<s_johnson_electric>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
}
|
| 139 |
+
},
|
| 140 |
+
"additional_special_tokens": [
|
| 141 |
+
"<s_iitcdip>",
|
| 142 |
+
"<s_synthdog>"
|
| 143 |
+
],
|
| 144 |
"bos_token": "<s>",
|
| 145 |
"clean_up_tokenization_spaces": true,
|
| 146 |
"cls_token": "<s>",
|
| 147 |
"eos_token": "</s>",
|
| 148 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
"model_max_length": 1000000000000000019884624838656,
|
| 150 |
"pad_token": "<pad>",
|
| 151 |
"processor_class": "DonutProcessor",
|