Upload folder using huggingface_hub
Browse files- special_tokens_map.json +30 -1
- tokenizer.json +235 -131
- tokenizer_config.json +236 -0
special_tokens_map.json
CHANGED
|
@@ -1 +1,30 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|tool_call_start|>",
|
| 4 |
+
"<|tool_call_end|>",
|
| 5 |
+
"<|tool_list_start|>",
|
| 6 |
+
"<|tool_list_end|>",
|
| 7 |
+
"<|source_analysis_start|>",
|
| 8 |
+
"<|source_analysis_end|>",
|
| 9 |
+
"<|source_start|>",
|
| 10 |
+
"<|source_end|>",
|
| 11 |
+
"<|im_start|>",
|
| 12 |
+
"<|im_end|>",
|
| 13 |
+
"<|answer_start|>",
|
| 14 |
+
"<|answer_end|>",
|
| 15 |
+
"<|text_start|>",
|
| 16 |
+
"<|text_end|>",
|
| 17 |
+
"<|translation_start|>",
|
| 18 |
+
"<|translation_end|>",
|
| 19 |
+
"<|back_translation_start|>",
|
| 20 |
+
"<|back_translation_end|>",
|
| 21 |
+
"<|ocr_correction_start|>",
|
| 22 |
+
"<|ocr_correction_end|>",
|
| 23 |
+
"<|json_scheme_start|>",
|
| 24 |
+
"<|json_scheme_end|>",
|
| 25 |
+
"<|source_interpretation_start|>",
|
| 26 |
+
"<|source_interpretation_end|>",
|
| 27 |
+
"<|query_start|>",
|
| 28 |
+
"<|query_end|>"
|
| 29 |
+
]
|
| 30 |
+
}
|
tokenizer.json
CHANGED
|
@@ -38,6 +38,240 @@
|
|
| 38 |
"rstrip": false,
|
| 39 |
"normalized": false,
|
| 40 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": null,
|
|
@@ -65585,33 +65819,7 @@
|
|
| 65585 |
"reste": 65506,
|
| 65586 |
"ĠMonat": 65507,
|
| 65587 |
"å·¥ä½ľ": 65508,
|
| 65588 |
-
"Ġdémocratique": 65509
|
| 65589 |
-
"Ġsejam": 65510,
|
| 65590 |
-
"ÑĥбеÑĢ": 65511,
|
| 65591 |
-
"Ġaccessoires": 65512,
|
| 65592 |
-
"Ġ709": 65513,
|
| 65593 |
-
"Ġménages": 65514,
|
| 65594 |
-
"Ġprodukty": 65515,
|
| 65595 |
-
"Ġsuum": 65516,
|
| 65596 |
-
"Ġinfluenc": 65517,
|
| 65597 |
-
"Ġcatching": 65518,
|
| 65598 |
-
"ĠÏĮÏĦαν": 65519,
|
| 65599 |
-
"737": 65520,
|
| 65600 |
-
"ĠоÑĤде": 65521,
|
| 65601 |
-
"Ġë°ı": 65522,
|
| 65602 |
-
"symptoms": 65523,
|
| 65603 |
-
"apac": 65524,
|
| 65604 |
-
"Ġdépou": 65525,
|
| 65605 |
-
"οÏįμεν": 65526,
|
| 65606 |
-
"Ġmagnifique": 65527,
|
| 65607 |
-
"Regular": 65528,
|
| 65608 |
-
"rals": 65529,
|
| 65609 |
-
"irii": 65530,
|
| 65610 |
-
"ĠÅĻÃŃ": 65531,
|
| 65611 |
-
"Ġinsulated": 65532,
|
| 65612 |
-
"Ġinsur": 65533,
|
| 65613 |
-
"Ġuprawn": 65534,
|
| 65614 |
-
"ειεÏĤ": 65535
|
| 65615 |
},
|
| 65616 |
"merges": [
|
| 65617 |
[
|
|
@@ -326665,110 +326873,6 @@
|
|
| 326665 |
[
|
| 326666 |
"Ġdémocra",
|
| 326667 |
"tique"
|
| 326668 |
-
],
|
| 326669 |
-
[
|
| 326670 |
-
"Ġse",
|
| 326671 |
-
"jam"
|
| 326672 |
-
],
|
| 326673 |
-
[
|
| 326674 |
-
"Ñĥб",
|
| 326675 |
-
"еÑĢ"
|
| 326676 |
-
],
|
| 326677 |
-
[
|
| 326678 |
-
"Ġaccess",
|
| 326679 |
-
"oires"
|
| 326680 |
-
],
|
| 326681 |
-
[
|
| 326682 |
-
"Ġ7",
|
| 326683 |
-
"09"
|
| 326684 |
-
],
|
| 326685 |
-
[
|
| 326686 |
-
"Ġmén",
|
| 326687 |
-
"ages"
|
| 326688 |
-
],
|
| 326689 |
-
[
|
| 326690 |
-
"Ġproduk",
|
| 326691 |
-
"ty"
|
| 326692 |
-
],
|
| 326693 |
-
[
|
| 326694 |
-
"Ġsu",
|
| 326695 |
-
"um"
|
| 326696 |
-
],
|
| 326697 |
-
[
|
| 326698 |
-
"Ġinflu",
|
| 326699 |
-
"enc"
|
| 326700 |
-
],
|
| 326701 |
-
[
|
| 326702 |
-
"Ġcatch",
|
| 326703 |
-
"ing"
|
| 326704 |
-
],
|
| 326705 |
-
[
|
| 326706 |
-
"ĠÏĮ",
|
| 326707 |
-
"ÏĦαν"
|
| 326708 |
-
],
|
| 326709 |
-
[
|
| 326710 |
-
"7",
|
| 326711 |
-
"37"
|
| 326712 |
-
],
|
| 326713 |
-
[
|
| 326714 |
-
"ĠоÑĤ",
|
| 326715 |
-
"де"
|
| 326716 |
-
],
|
| 326717 |
-
[
|
| 326718 |
-
"Ġë°",
|
| 326719 |
-
"ı"
|
| 326720 |
-
],
|
| 326721 |
-
[
|
| 326722 |
-
"sym",
|
| 326723 |
-
"ptoms"
|
| 326724 |
-
],
|
| 326725 |
-
[
|
| 326726 |
-
"ap",
|
| 326727 |
-
"ac"
|
| 326728 |
-
],
|
| 326729 |
-
[
|
| 326730 |
-
"Ġdép",
|
| 326731 |
-
"ou"
|
| 326732 |
-
],
|
| 326733 |
-
[
|
| 326734 |
-
"οÏį",
|
| 326735 |
-
"μεν"
|
| 326736 |
-
],
|
| 326737 |
-
[
|
| 326738 |
-
"Ġmagn",
|
| 326739 |
-
"ifique"
|
| 326740 |
-
],
|
| 326741 |
-
[
|
| 326742 |
-
"Reg",
|
| 326743 |
-
"ular"
|
| 326744 |
-
],
|
| 326745 |
-
[
|
| 326746 |
-
"r",
|
| 326747 |
-
"als"
|
| 326748 |
-
],
|
| 326749 |
-
[
|
| 326750 |
-
"ir",
|
| 326751 |
-
"ii"
|
| 326752 |
-
],
|
| 326753 |
-
[
|
| 326754 |
-
"Ġ",
|
| 326755 |
-
"ÅĻÃŃ"
|
| 326756 |
-
],
|
| 326757 |
-
[
|
| 326758 |
-
"Ġins",
|
| 326759 |
-
"ulated"
|
| 326760 |
-
],
|
| 326761 |
-
[
|
| 326762 |
-
"Ġins",
|
| 326763 |
-
"ur"
|
| 326764 |
-
],
|
| 326765 |
-
[
|
| 326766 |
-
"Ġupra",
|
| 326767 |
-
"wn"
|
| 326768 |
-
],
|
| 326769 |
-
[
|
| 326770 |
-
"ει",
|
| 326771 |
-
"εÏĤ"
|
| 326772 |
]
|
| 326773 |
]
|
| 326774 |
}
|
|
|
|
| 38 |
"rstrip": false,
|
| 39 |
"normalized": false,
|
| 40 |
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 65510,
|
| 44 |
+
"content": "<|tool_call_start|>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 65511,
|
| 53 |
+
"content": "<|tool_call_end|>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 65512,
|
| 62 |
+
"content": "<|tool_list_start|>",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 65513,
|
| 71 |
+
"content": "<|tool_list_end|>",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 65514,
|
| 80 |
+
"content": "<|source_analysis_start|>",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 65515,
|
| 89 |
+
"content": "<|source_analysis_end|>",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 65516,
|
| 98 |
+
"content": "<|source_start|>",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 65517,
|
| 107 |
+
"content": "<|source_end|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 65518,
|
| 116 |
+
"content": "<|im_start|>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 65519,
|
| 125 |
+
"content": "<|im_end|>",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 65520,
|
| 134 |
+
"content": "<|answer_start|>",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 65521,
|
| 143 |
+
"content": "<|answer_end|>",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 65522,
|
| 152 |
+
"content": "<|text_start|>",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": false,
|
| 157 |
+
"special": true
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 65523,
|
| 161 |
+
"content": "<|text_end|>",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": false,
|
| 166 |
+
"special": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 65524,
|
| 170 |
+
"content": "<|translation_start|>",
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"lstrip": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"special": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 65525,
|
| 179 |
+
"content": "<|translation_end|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": true
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 65526,
|
| 188 |
+
"content": "<|back_translation_start|>",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 65527,
|
| 197 |
+
"content": "<|back_translation_end|>",
|
| 198 |
+
"single_word": false,
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 65528,
|
| 206 |
+
"content": "<|ocr_correction_start|>",
|
| 207 |
+
"single_word": false,
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"normalized": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 65529,
|
| 215 |
+
"content": "<|ocr_correction_end|>",
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"lstrip": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"normalized": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 65530,
|
| 224 |
+
"content": "<|json_scheme_start|>",
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"normalized": false,
|
| 229 |
+
"special": true
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 65531,
|
| 233 |
+
"content": "<|json_scheme_end|>",
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"lstrip": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"special": true
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"id": 65532,
|
| 242 |
+
"content": "<|source_interpretation_start|>",
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"lstrip": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"special": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": 65533,
|
| 251 |
+
"content": "<|source_interpretation_end|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"id": 65534,
|
| 260 |
+
"content": "<|query_start|>",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"id": 65535,
|
| 269 |
+
"content": "<|query_end|>",
|
| 270 |
+
"single_word": false,
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"special": true
|
| 275 |
}
|
| 276 |
],
|
| 277 |
"normalizer": null,
|
|
|
|
| 65819 |
"reste": 65506,
|
| 65820 |
"ĠMonat": 65507,
|
| 65821 |
"å·¥ä½ľ": 65508,
|
| 65822 |
+
"Ġdémocratique": 65509
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65823 |
},
|
| 65824 |
"merges": [
|
| 65825 |
[
|
|
|
|
| 326873 |
[
|
| 326874 |
"Ġdémocra",
|
| 326875 |
"tique"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 326876 |
]
|
| 326877 |
]
|
| 326878 |
}
|
tokenizer_config.json
CHANGED
|
@@ -31,8 +31,244 @@
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"clean_up_tokenization_spaces": true,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
+
},
|
| 35 |
+
"65510": {
|
| 36 |
+
"content": "<|tool_call_start|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"65511": {
|
| 44 |
+
"content": "<|tool_call_end|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"65512": {
|
| 52 |
+
"content": "<|tool_list_start|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"65513": {
|
| 60 |
+
"content": "<|tool_list_end|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"65514": {
|
| 68 |
+
"content": "<|source_analysis_start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"65515": {
|
| 76 |
+
"content": "<|source_analysis_end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"65516": {
|
| 84 |
+
"content": "<|source_start|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"65517": {
|
| 92 |
+
"content": "<|source_end|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"65518": {
|
| 100 |
+
"content": "<|im_start|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"65519": {
|
| 108 |
+
"content": "<|im_end|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"65520": {
|
| 116 |
+
"content": "<|answer_start|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"65521": {
|
| 124 |
+
"content": "<|answer_end|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"65522": {
|
| 132 |
+
"content": "<|text_start|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"65523": {
|
| 140 |
+
"content": "<|text_end|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"65524": {
|
| 148 |
+
"content": "<|translation_start|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"65525": {
|
| 156 |
+
"content": "<|translation_end|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"65526": {
|
| 164 |
+
"content": "<|back_translation_start|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"65527": {
|
| 172 |
+
"content": "<|back_translation_end|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"65528": {
|
| 180 |
+
"content": "<|ocr_correction_start|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"65529": {
|
| 188 |
+
"content": "<|ocr_correction_end|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"65530": {
|
| 196 |
+
"content": "<|json_scheme_start|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"65531": {
|
| 204 |
+
"content": "<|json_scheme_end|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"65532": {
|
| 212 |
+
"content": "<|source_interpretation_start|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"65533": {
|
| 220 |
+
"content": "<|source_interpretation_end|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"65534": {
|
| 228 |
+
"content": "<|query_start|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"65535": {
|
| 236 |
+
"content": "<|query_end|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
}
|
| 243 |
},
|
| 244 |
+
"additional_special_tokens": [
|
| 245 |
+
"<|tool_call_start|>",
|
| 246 |
+
"<|tool_call_end|>",
|
| 247 |
+
"<|tool_list_start|>",
|
| 248 |
+
"<|tool_list_end|>",
|
| 249 |
+
"<|source_analysis_start|>",
|
| 250 |
+
"<|source_analysis_end|>",
|
| 251 |
+
"<|source_start|>",
|
| 252 |
+
"<|source_end|>",
|
| 253 |
+
"<|im_start|>",
|
| 254 |
+
"<|im_end|>",
|
| 255 |
+
"<|answer_start|>",
|
| 256 |
+
"<|answer_end|>",
|
| 257 |
+
"<|text_start|>",
|
| 258 |
+
"<|text_end|>",
|
| 259 |
+
"<|translation_start|>",
|
| 260 |
+
"<|translation_end|>",
|
| 261 |
+
"<|back_translation_start|>",
|
| 262 |
+
"<|back_translation_end|>",
|
| 263 |
+
"<|ocr_correction_start|>",
|
| 264 |
+
"<|ocr_correction_end|>",
|
| 265 |
+
"<|json_scheme_start|>",
|
| 266 |
+
"<|json_scheme_end|>",
|
| 267 |
+
"<|source_interpretation_start|>",
|
| 268 |
+
"<|source_interpretation_end|>",
|
| 269 |
+
"<|query_start|>",
|
| 270 |
+
"<|query_end|>"
|
| 271 |
+
],
|
| 272 |
"clean_up_tokenization_spaces": true,
|
| 273 |
"model_max_length": 1000000000000000019884624838656,
|
| 274 |
"tokenizer_class": "PreTrainedTokenizerFast"
|