Upload folder using huggingface_hub
Browse files- special_tokens_map.json +7 -23
- tokenizer.json +44 -156
- tokenizer_config.json +17 -161
special_tokens_map.json
CHANGED
|
@@ -1,30 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
"<|
|
| 4 |
-
"<|
|
| 5 |
-
"<|tool_list_start|>",
|
| 6 |
-
"<|tool_list_end|>",
|
| 7 |
-
"<|source_analysis_start|>",
|
| 8 |
-
"<|source_analysis_end|>",
|
| 9 |
"<|source_start|>",
|
| 10 |
"<|source_end|>",
|
| 11 |
-
"<|
|
| 12 |
-
"<|
|
|
|
|
|
|
|
| 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 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<|query_start|>",
|
| 4 |
+
"<|query_end|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"<|source_start|>",
|
| 6 |
"<|source_end|>",
|
| 7 |
+
"<|source_id_start|>",
|
| 8 |
+
"<|source_id_end|>",
|
| 9 |
+
"<|source_analysis_start|>",
|
| 10 |
+
"<|source_analysis_end|>",
|
| 11 |
"<|answer_start|>",
|
| 12 |
+
"<|answer_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
]
|
| 14 |
}
|
tokenizer.json
CHANGED
|
@@ -39,153 +39,9 @@
|
|
| 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": "<|
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
|
@@ -194,7 +50,7 @@
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 65527,
|
| 197 |
-
"content": "<|
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
|
@@ -203,7 +59,7 @@
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 65528,
|
| 206 |
-
"content": "<|
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
|
@@ -212,7 +68,7 @@
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 65529,
|
| 215 |
-
"content": "<|
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
|
@@ -221,7 +77,7 @@
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 65530,
|
| 224 |
-
"content": "<|
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
|
@@ -230,7 +86,7 @@
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 65531,
|
| 233 |
-
"content": "<|
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
|
@@ -239,7 +95,7 @@
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 65532,
|
| 242 |
-
"content": "<|
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
|
@@ -248,7 +104,7 @@
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 65533,
|
| 251 |
-
"content": "<|
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
|
@@ -257,7 +113,7 @@
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 65534,
|
| 260 |
-
"content": "<|
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
|
@@ -266,7 +122,7 @@
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 65535,
|
| 269 |
-
"content": "<|
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
|
@@ -65911,7 +65767,23 @@
|
|
| 65911 |
"reste": 65506,
|
| 65912 |
"ĠMonat": 65507,
|
| 65913 |
"å·¥ä½ľ": 65508,
|
| 65914 |
-
"Ġdémocratique": 65509
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65915 |
},
|
| 65916 |
"merges": [
|
| 65917 |
"Ġ Ġ",
|
|
@@ -131176,7 +131048,23 @@
|
|
| 131176 |
"res te",
|
| 131177 |
"ĠMon at",
|
| 131178 |
"å·¥ ä½ľ",
|
| 131179 |
-
"Ġdémocra tique"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131180 |
]
|
| 131181 |
}
|
| 131182 |
}
|
|
|
|
| 39 |
"normalized": false,
|
| 40 |
"special": true
|
| 41 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
{
|
| 43 |
"id": 65526,
|
| 44 |
+
"content": "<|query_start|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 65527,
|
| 53 |
+
"content": "<|query_end|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 65528,
|
| 62 |
+
"content": "<|source_start|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 65529,
|
| 71 |
+
"content": "<|source_end|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 65530,
|
| 80 |
+
"content": "<|source_id_start|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 65531,
|
| 89 |
+
"content": "<|source_id_end|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 65532,
|
| 98 |
+
"content": "<|source_analysis_start|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 65533,
|
| 107 |
+
"content": "<|source_analysis_end|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 65534,
|
| 116 |
+
"content": "<|answer_start|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 65535,
|
| 125 |
+
"content": "<|answer_end|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
|
|
|
| 65767 |
"reste": 65506,
|
| 65768 |
"ĠMonat": 65507,
|
| 65769 |
"å·¥ä½ľ": 65508,
|
| 65770 |
+
"Ġdémocratique": 65509,
|
| 65771 |
+
"Ġsejam": 65510,
|
| 65772 |
+
"ÑĥбеÑĢ": 65511,
|
| 65773 |
+
"Ġaccessoires": 65512,
|
| 65774 |
+
"Ġ709": 65513,
|
| 65775 |
+
"Ġménages": 65514,
|
| 65776 |
+
"Ġprodukty": 65515,
|
| 65777 |
+
"Ġsuum": 65516,
|
| 65778 |
+
"Ġinfluenc": 65517,
|
| 65779 |
+
"Ġcatching": 65518,
|
| 65780 |
+
"ĠÏĮÏĦαν": 65519,
|
| 65781 |
+
"737": 65520,
|
| 65782 |
+
"ĠоÑĤде": 65521,
|
| 65783 |
+
"Ġë°ı": 65522,
|
| 65784 |
+
"symptoms": 65523,
|
| 65785 |
+
"apac": 65524,
|
| 65786 |
+
"Ġdépou": 65525
|
| 65787 |
},
|
| 65788 |
"merges": [
|
| 65789 |
"Ġ Ġ",
|
|
|
|
| 131048 |
"res te",
|
| 131049 |
"ĠMon at",
|
| 131050 |
"å·¥ ä½ľ",
|
| 131051 |
+
"Ġdémocra tique",
|
| 131052 |
+
"Ġse jam",
|
| 131053 |
+
"Ñĥб еÑĢ",
|
| 131054 |
+
"Ġaccess oires",
|
| 131055 |
+
"Ġ7 09",
|
| 131056 |
+
"Ġmén ages",
|
| 131057 |
+
"Ġproduk ty",
|
| 131058 |
+
"Ġsu um",
|
| 131059 |
+
"Ġinflu enc",
|
| 131060 |
+
"Ġcatch ing",
|
| 131061 |
+
"ĠÏĮ ÏĦαν",
|
| 131062 |
+
"7 37",
|
| 131063 |
+
"ĠоÑĤ де",
|
| 131064 |
+
"Ġë° ı",
|
| 131065 |
+
"sym ptoms",
|
| 131066 |
+
"ap ac",
|
| 131067 |
+
"Ġdép ou"
|
| 131068 |
]
|
| 131069 |
}
|
| 131070 |
}
|
tokenizer_config.json
CHANGED
|
@@ -32,136 +32,8 @@
|
|
| 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": "<|
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": false,
|
| 167 |
"rstrip": false,
|
|
@@ -169,7 +41,7 @@
|
|
| 169 |
"special": true
|
| 170 |
},
|
| 171 |
"65527": {
|
| 172 |
-
"content": "<|
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
"rstrip": false,
|
|
@@ -177,7 +49,7 @@
|
|
| 177 |
"special": true
|
| 178 |
},
|
| 179 |
"65528": {
|
| 180 |
-
"content": "<|
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": false,
|
| 183 |
"rstrip": false,
|
|
@@ -185,7 +57,7 @@
|
|
| 185 |
"special": true
|
| 186 |
},
|
| 187 |
"65529": {
|
| 188 |
-
"content": "<|
|
| 189 |
"lstrip": false,
|
| 190 |
"normalized": false,
|
| 191 |
"rstrip": false,
|
|
@@ -193,7 +65,7 @@
|
|
| 193 |
"special": true
|
| 194 |
},
|
| 195 |
"65530": {
|
| 196 |
-
"content": "<|
|
| 197 |
"lstrip": false,
|
| 198 |
"normalized": false,
|
| 199 |
"rstrip": false,
|
|
@@ -201,7 +73,7 @@
|
|
| 201 |
"special": true
|
| 202 |
},
|
| 203 |
"65531": {
|
| 204 |
-
"content": "<|
|
| 205 |
"lstrip": false,
|
| 206 |
"normalized": false,
|
| 207 |
"rstrip": false,
|
|
@@ -209,7 +81,7 @@
|
|
| 209 |
"special": true
|
| 210 |
},
|
| 211 |
"65532": {
|
| 212 |
-
"content": "<|
|
| 213 |
"lstrip": false,
|
| 214 |
"normalized": false,
|
| 215 |
"rstrip": false,
|
|
@@ -217,7 +89,7 @@
|
|
| 217 |
"special": true
|
| 218 |
},
|
| 219 |
"65533": {
|
| 220 |
-
"content": "<|
|
| 221 |
"lstrip": false,
|
| 222 |
"normalized": false,
|
| 223 |
"rstrip": false,
|
|
@@ -225,7 +97,7 @@
|
|
| 225 |
"special": true
|
| 226 |
},
|
| 227 |
"65534": {
|
| 228 |
-
"content": "<|
|
| 229 |
"lstrip": false,
|
| 230 |
"normalized": false,
|
| 231 |
"rstrip": false,
|
|
@@ -233,7 +105,7 @@
|
|
| 233 |
"special": true
|
| 234 |
},
|
| 235 |
"65535": {
|
| 236 |
-
"content": "<|
|
| 237 |
"lstrip": false,
|
| 238 |
"normalized": false,
|
| 239 |
"rstrip": false,
|
|
@@ -242,32 +114,16 @@
|
|
| 242 |
}
|
| 243 |
},
|
| 244 |
"additional_special_tokens": [
|
| 245 |
-
"<|
|
| 246 |
-
"<|
|
| 247 |
-
"<|tool_list_start|>",
|
| 248 |
-
"<|tool_list_end|>",
|
| 249 |
-
"<|source_analysis_start|>",
|
| 250 |
-
"<|source_analysis_end|>",
|
| 251 |
"<|source_start|>",
|
| 252 |
"<|source_end|>",
|
| 253 |
-
"<|
|
| 254 |
-
"<|
|
|
|
|
|
|
|
| 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,
|
|
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
"65526": {
|
| 36 |
+
"content": "<|query_start|>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"65527": {
|
| 44 |
+
"content": "<|query_end|>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
"65528": {
|
| 52 |
+
"content": "<|source_start|>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
| 55 |
"rstrip": false,
|
|
|
|
| 57 |
"special": true
|
| 58 |
},
|
| 59 |
"65529": {
|
| 60 |
+
"content": "<|source_end|>",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": false,
|
| 63 |
"rstrip": false,
|
|
|
|
| 65 |
"special": true
|
| 66 |
},
|
| 67 |
"65530": {
|
| 68 |
+
"content": "<|source_id_start|>",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": false,
|
| 71 |
"rstrip": false,
|
|
|
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
"65531": {
|
| 76 |
+
"content": "<|source_id_end|>",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
| 79 |
"rstrip": false,
|
|
|
|
| 81 |
"special": true
|
| 82 |
},
|
| 83 |
"65532": {
|
| 84 |
+
"content": "<|source_analysis_start|>",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": false,
|
| 87 |
"rstrip": false,
|
|
|
|
| 89 |
"special": true
|
| 90 |
},
|
| 91 |
"65533": {
|
| 92 |
+
"content": "<|source_analysis_end|>",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": false,
|
| 95 |
"rstrip": false,
|
|
|
|
| 97 |
"special": true
|
| 98 |
},
|
| 99 |
"65534": {
|
| 100 |
+
"content": "<|answer_start|>",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
"rstrip": false,
|
|
|
|
| 105 |
"special": true
|
| 106 |
},
|
| 107 |
"65535": {
|
| 108 |
+
"content": "<|answer_end|>",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": false,
|
| 111 |
"rstrip": false,
|
|
|
|
| 114 |
}
|
| 115 |
},
|
| 116 |
"additional_special_tokens": [
|
| 117 |
+
"<|query_start|>",
|
| 118 |
+
"<|query_end|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
"<|source_start|>",
|
| 120 |
"<|source_end|>",
|
| 121 |
+
"<|source_id_start|>",
|
| 122 |
+
"<|source_id_end|>",
|
| 123 |
+
"<|source_analysis_start|>",
|
| 124 |
+
"<|source_analysis_end|>",
|
| 125 |
"<|answer_start|>",
|
| 126 |
+
"<|answer_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
],
|
| 128 |
"clean_up_tokenization_spaces": true,
|
| 129 |
"model_max_length": 1000000000000000019884624838656,
|