Training done
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +42 -6
- tokenizer.json +0 -0
- tokenizer_config.json +39 -0
added_tokens.json
CHANGED
|
@@ -24,6 +24,8 @@
|
|
| 24 |
"</s_hsn_code>": 57580,
|
| 25 |
"</s_iban>": 57638,
|
| 26 |
"</s_iec>": 57606,
|
|
|
|
|
|
|
| 27 |
"</s_invoice_currency>": 57598,
|
| 28 |
"</s_invoice_date>": 57534,
|
| 29 |
"</s_invoice_no>": 57532,
|
|
@@ -88,6 +90,8 @@
|
|
| 88 |
"<s_iban>": 57637,
|
| 89 |
"<s_iec>": 57605,
|
| 90 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
| 91 |
"<s_invoice_currency>": 57597,
|
| 92 |
"<s_invoice_date>": 57533,
|
| 93 |
"<s_invoice_no>": 57531,
|
|
|
|
| 24 |
"</s_hsn_code>": 57580,
|
| 25 |
"</s_iban>": 57638,
|
| 26 |
"</s_iec>": 57606,
|
| 27 |
+
"</s_invoice >": 57651,
|
| 28 |
+
"</s_invoice>": 57653,
|
| 29 |
"</s_invoice_currency>": 57598,
|
| 30 |
"</s_invoice_date>": 57534,
|
| 31 |
"</s_invoice_no>": 57532,
|
|
|
|
| 90 |
"<s_iban>": 57637,
|
| 91 |
"<s_iec>": 57605,
|
| 92 |
"<s_iitcdip>": 57523,
|
| 93 |
+
"<s_invoice >": 57650,
|
| 94 |
+
"<s_invoice>": 57652,
|
| 95 |
"<s_invoice_currency>": 57597,
|
| 96 |
"<s_invoice_date>": 57533,
|
| 97 |
"<s_invoice_no>": 57531,
|
special_tokens_map.json
CHANGED
|
@@ -3,9 +3,27 @@
|
|
| 3 |
"<s_iitcdip>",
|
| 4 |
"<s_synthdog>"
|
| 5 |
],
|
| 6 |
-
"bos_token":
|
| 7 |
-
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"mask_token": {
|
| 10 |
"content": "<mask>",
|
| 11 |
"lstrip": true,
|
|
@@ -13,7 +31,25 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
|
|
|
| 3 |
"<s_iitcdip>",
|
| 4 |
"<s_synthdog>"
|
| 5 |
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<s>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"cls_token": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
"mask_token": {
|
| 28 |
"content": "<mask>",
|
| 29 |
"lstrip": true,
|
|
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false
|
| 33 |
},
|
| 34 |
+
"pad_token": {
|
| 35 |
+
"content": "<pad>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
},
|
| 41 |
+
"sep_token": {
|
| 42 |
+
"content": "</s>",
|
| 43 |
+
"lstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"single_word": false
|
| 47 |
+
},
|
| 48 |
+
"unk_token": {
|
| 49 |
+
"content": "<unk>",
|
| 50 |
+
"lstrip": false,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"single_word": false
|
| 54 |
+
}
|
| 55 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1063,6 +1063,38 @@
|
|
| 1063 |
"rstrip": false,
|
| 1064 |
"single_word": false,
|
| 1065 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1066 |
}
|
| 1067 |
},
|
| 1068 |
"additional_special_tokens": [
|
|
@@ -1074,11 +1106,18 @@
|
|
| 1074 |
"cls_token": "<s>",
|
| 1075 |
"eos_token": "</s>",
|
| 1076 |
"mask_token": "<mask>",
|
|
|
|
| 1077 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 1078 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 1079 |
"processor_class": "DonutProcessor",
|
| 1080 |
"sep_token": "</s>",
|
| 1081 |
"sp_model_kwargs": {},
|
|
|
|
| 1082 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 1083 |
"unk_token": "<unk>"
|
| 1084 |
}
|
|
|
|
| 1063 |
"rstrip": false,
|
| 1064 |
"single_word": false,
|
| 1065 |
"special": false
|
| 1066 |
+
},
|
| 1067 |
+
"57650": {
|
| 1068 |
+
"content": "<s_invoice >",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": true,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": false
|
| 1074 |
+
},
|
| 1075 |
+
"57651": {
|
| 1076 |
+
"content": "</s_invoice >",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": true,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": false
|
| 1082 |
+
},
|
| 1083 |
+
"57652": {
|
| 1084 |
+
"content": "<s_invoice>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": true,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": false
|
| 1090 |
+
},
|
| 1091 |
+
"57653": {
|
| 1092 |
+
"content": "</s_invoice>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": true,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": false
|
| 1098 |
}
|
| 1099 |
},
|
| 1100 |
"additional_special_tokens": [
|
|
|
|
| 1106 |
"cls_token": "<s>",
|
| 1107 |
"eos_token": "</s>",
|
| 1108 |
"mask_token": "<mask>",
|
| 1109 |
+
"max_length": 768,
|
| 1110 |
"model_max_length": 1000000000000000019884624838656,
|
| 1111 |
+
"pad_to_multiple_of": null,
|
| 1112 |
"pad_token": "<pad>",
|
| 1113 |
+
"pad_token_type_id": 0,
|
| 1114 |
+
"padding_side": "right",
|
| 1115 |
"processor_class": "DonutProcessor",
|
| 1116 |
"sep_token": "</s>",
|
| 1117 |
"sp_model_kwargs": {},
|
| 1118 |
+
"stride": 0,
|
| 1119 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 1120 |
+
"truncation_side": "right",
|
| 1121 |
+
"truncation_strategy": "longest_first",
|
| 1122 |
"unk_token": "<unk>"
|
| 1123 |
}
|