Upload tokenizer
Browse files- .gitattributes +1 -0
- added_tokens.json +540 -0
- merges.txt +0 -0
- special_tokens_map.json +39 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|sound_0000|>": 151668,
|
| 21 |
+
"<|sound_0001|>": 151669,
|
| 22 |
+
"<|sound_0002|>": 151670,
|
| 23 |
+
"<|sound_0003|>": 151671,
|
| 24 |
+
"<|sound_0004|>": 151672,
|
| 25 |
+
"<|sound_0005|>": 151673,
|
| 26 |
+
"<|sound_0006|>": 151674,
|
| 27 |
+
"<|sound_0007|>": 151675,
|
| 28 |
+
"<|sound_0008|>": 151676,
|
| 29 |
+
"<|sound_0009|>": 151677,
|
| 30 |
+
"<|sound_0010|>": 151678,
|
| 31 |
+
"<|sound_0011|>": 151679,
|
| 32 |
+
"<|sound_0012|>": 151680,
|
| 33 |
+
"<|sound_0013|>": 151681,
|
| 34 |
+
"<|sound_0014|>": 151682,
|
| 35 |
+
"<|sound_0015|>": 151683,
|
| 36 |
+
"<|sound_0016|>": 151684,
|
| 37 |
+
"<|sound_0017|>": 151685,
|
| 38 |
+
"<|sound_0018|>": 151686,
|
| 39 |
+
"<|sound_0019|>": 151687,
|
| 40 |
+
"<|sound_0020|>": 151688,
|
| 41 |
+
"<|sound_0021|>": 151689,
|
| 42 |
+
"<|sound_0022|>": 151690,
|
| 43 |
+
"<|sound_0023|>": 151691,
|
| 44 |
+
"<|sound_0024|>": 151692,
|
| 45 |
+
"<|sound_0025|>": 151693,
|
| 46 |
+
"<|sound_0026|>": 151694,
|
| 47 |
+
"<|sound_0027|>": 151695,
|
| 48 |
+
"<|sound_0028|>": 151696,
|
| 49 |
+
"<|sound_0029|>": 151697,
|
| 50 |
+
"<|sound_0030|>": 151698,
|
| 51 |
+
"<|sound_0031|>": 151699,
|
| 52 |
+
"<|sound_0032|>": 151700,
|
| 53 |
+
"<|sound_0033|>": 151701,
|
| 54 |
+
"<|sound_0034|>": 151702,
|
| 55 |
+
"<|sound_0035|>": 151703,
|
| 56 |
+
"<|sound_0036|>": 151704,
|
| 57 |
+
"<|sound_0037|>": 151705,
|
| 58 |
+
"<|sound_0038|>": 151706,
|
| 59 |
+
"<|sound_0039|>": 151707,
|
| 60 |
+
"<|sound_0040|>": 151708,
|
| 61 |
+
"<|sound_0041|>": 151709,
|
| 62 |
+
"<|sound_0042|>": 151710,
|
| 63 |
+
"<|sound_0043|>": 151711,
|
| 64 |
+
"<|sound_0044|>": 151712,
|
| 65 |
+
"<|sound_0045|>": 151713,
|
| 66 |
+
"<|sound_0046|>": 151714,
|
| 67 |
+
"<|sound_0047|>": 151715,
|
| 68 |
+
"<|sound_0048|>": 151716,
|
| 69 |
+
"<|sound_0049|>": 151717,
|
| 70 |
+
"<|sound_0050|>": 151718,
|
| 71 |
+
"<|sound_0051|>": 151719,
|
| 72 |
+
"<|sound_0052|>": 151720,
|
| 73 |
+
"<|sound_0053|>": 151721,
|
| 74 |
+
"<|sound_0054|>": 151722,
|
| 75 |
+
"<|sound_0055|>": 151723,
|
| 76 |
+
"<|sound_0056|>": 151724,
|
| 77 |
+
"<|sound_0057|>": 151725,
|
| 78 |
+
"<|sound_0058|>": 151726,
|
| 79 |
+
"<|sound_0059|>": 151727,
|
| 80 |
+
"<|sound_0060|>": 151728,
|
| 81 |
+
"<|sound_0061|>": 151729,
|
| 82 |
+
"<|sound_0062|>": 151730,
|
| 83 |
+
"<|sound_0063|>": 151731,
|
| 84 |
+
"<|sound_0064|>": 151732,
|
| 85 |
+
"<|sound_0065|>": 151733,
|
| 86 |
+
"<|sound_0066|>": 151734,
|
| 87 |
+
"<|sound_0067|>": 151735,
|
| 88 |
+
"<|sound_0068|>": 151736,
|
| 89 |
+
"<|sound_0069|>": 151737,
|
| 90 |
+
"<|sound_0070|>": 151738,
|
| 91 |
+
"<|sound_0071|>": 151739,
|
| 92 |
+
"<|sound_0072|>": 151740,
|
| 93 |
+
"<|sound_0073|>": 151741,
|
| 94 |
+
"<|sound_0074|>": 151742,
|
| 95 |
+
"<|sound_0075|>": 151743,
|
| 96 |
+
"<|sound_0076|>": 151744,
|
| 97 |
+
"<|sound_0077|>": 151745,
|
| 98 |
+
"<|sound_0078|>": 151746,
|
| 99 |
+
"<|sound_0079|>": 151747,
|
| 100 |
+
"<|sound_0080|>": 151748,
|
| 101 |
+
"<|sound_0081|>": 151749,
|
| 102 |
+
"<|sound_0082|>": 151750,
|
| 103 |
+
"<|sound_0083|>": 151751,
|
| 104 |
+
"<|sound_0084|>": 151752,
|
| 105 |
+
"<|sound_0085|>": 151753,
|
| 106 |
+
"<|sound_0086|>": 151754,
|
| 107 |
+
"<|sound_0087|>": 151755,
|
| 108 |
+
"<|sound_0088|>": 151756,
|
| 109 |
+
"<|sound_0089|>": 151757,
|
| 110 |
+
"<|sound_0090|>": 151758,
|
| 111 |
+
"<|sound_0091|>": 151759,
|
| 112 |
+
"<|sound_0092|>": 151760,
|
| 113 |
+
"<|sound_0093|>": 151761,
|
| 114 |
+
"<|sound_0094|>": 151762,
|
| 115 |
+
"<|sound_0095|>": 151763,
|
| 116 |
+
"<|sound_0096|>": 151764,
|
| 117 |
+
"<|sound_0097|>": 151765,
|
| 118 |
+
"<|sound_0098|>": 151766,
|
| 119 |
+
"<|sound_0099|>": 151767,
|
| 120 |
+
"<|sound_0100|>": 151768,
|
| 121 |
+
"<|sound_0101|>": 151769,
|
| 122 |
+
"<|sound_0102|>": 151770,
|
| 123 |
+
"<|sound_0103|>": 151771,
|
| 124 |
+
"<|sound_0104|>": 151772,
|
| 125 |
+
"<|sound_0105|>": 151773,
|
| 126 |
+
"<|sound_0106|>": 151774,
|
| 127 |
+
"<|sound_0107|>": 151775,
|
| 128 |
+
"<|sound_0108|>": 151776,
|
| 129 |
+
"<|sound_0109|>": 151777,
|
| 130 |
+
"<|sound_0110|>": 151778,
|
| 131 |
+
"<|sound_0111|>": 151779,
|
| 132 |
+
"<|sound_0112|>": 151780,
|
| 133 |
+
"<|sound_0113|>": 151781,
|
| 134 |
+
"<|sound_0114|>": 151782,
|
| 135 |
+
"<|sound_0115|>": 151783,
|
| 136 |
+
"<|sound_0116|>": 151784,
|
| 137 |
+
"<|sound_0117|>": 151785,
|
| 138 |
+
"<|sound_0118|>": 151786,
|
| 139 |
+
"<|sound_0119|>": 151787,
|
| 140 |
+
"<|sound_0120|>": 151788,
|
| 141 |
+
"<|sound_0121|>": 151789,
|
| 142 |
+
"<|sound_0122|>": 151790,
|
| 143 |
+
"<|sound_0123|>": 151791,
|
| 144 |
+
"<|sound_0124|>": 151792,
|
| 145 |
+
"<|sound_0125|>": 151793,
|
| 146 |
+
"<|sound_0126|>": 151794,
|
| 147 |
+
"<|sound_0127|>": 151795,
|
| 148 |
+
"<|sound_0128|>": 151796,
|
| 149 |
+
"<|sound_0129|>": 151797,
|
| 150 |
+
"<|sound_0130|>": 151798,
|
| 151 |
+
"<|sound_0131|>": 151799,
|
| 152 |
+
"<|sound_0132|>": 151800,
|
| 153 |
+
"<|sound_0133|>": 151801,
|
| 154 |
+
"<|sound_0134|>": 151802,
|
| 155 |
+
"<|sound_0135|>": 151803,
|
| 156 |
+
"<|sound_0136|>": 151804,
|
| 157 |
+
"<|sound_0137|>": 151805,
|
| 158 |
+
"<|sound_0138|>": 151806,
|
| 159 |
+
"<|sound_0139|>": 151807,
|
| 160 |
+
"<|sound_0140|>": 151808,
|
| 161 |
+
"<|sound_0141|>": 151809,
|
| 162 |
+
"<|sound_0142|>": 151810,
|
| 163 |
+
"<|sound_0143|>": 151811,
|
| 164 |
+
"<|sound_0144|>": 151812,
|
| 165 |
+
"<|sound_0145|>": 151813,
|
| 166 |
+
"<|sound_0146|>": 151814,
|
| 167 |
+
"<|sound_0147|>": 151815,
|
| 168 |
+
"<|sound_0148|>": 151816,
|
| 169 |
+
"<|sound_0149|>": 151817,
|
| 170 |
+
"<|sound_0150|>": 151818,
|
| 171 |
+
"<|sound_0151|>": 151819,
|
| 172 |
+
"<|sound_0152|>": 151820,
|
| 173 |
+
"<|sound_0153|>": 151821,
|
| 174 |
+
"<|sound_0154|>": 151822,
|
| 175 |
+
"<|sound_0155|>": 151823,
|
| 176 |
+
"<|sound_0156|>": 151824,
|
| 177 |
+
"<|sound_0157|>": 151825,
|
| 178 |
+
"<|sound_0158|>": 151826,
|
| 179 |
+
"<|sound_0159|>": 151827,
|
| 180 |
+
"<|sound_0160|>": 151828,
|
| 181 |
+
"<|sound_0161|>": 151829,
|
| 182 |
+
"<|sound_0162|>": 151830,
|
| 183 |
+
"<|sound_0163|>": 151831,
|
| 184 |
+
"<|sound_0164|>": 151832,
|
| 185 |
+
"<|sound_0165|>": 151833,
|
| 186 |
+
"<|sound_0166|>": 151834,
|
| 187 |
+
"<|sound_0167|>": 151835,
|
| 188 |
+
"<|sound_0168|>": 151836,
|
| 189 |
+
"<|sound_0169|>": 151837,
|
| 190 |
+
"<|sound_0170|>": 151838,
|
| 191 |
+
"<|sound_0171|>": 151839,
|
| 192 |
+
"<|sound_0172|>": 151840,
|
| 193 |
+
"<|sound_0173|>": 151841,
|
| 194 |
+
"<|sound_0174|>": 151842,
|
| 195 |
+
"<|sound_0175|>": 151843,
|
| 196 |
+
"<|sound_0176|>": 151844,
|
| 197 |
+
"<|sound_0177|>": 151845,
|
| 198 |
+
"<|sound_0178|>": 151846,
|
| 199 |
+
"<|sound_0179|>": 151847,
|
| 200 |
+
"<|sound_0180|>": 151848,
|
| 201 |
+
"<|sound_0181|>": 151849,
|
| 202 |
+
"<|sound_0182|>": 151850,
|
| 203 |
+
"<|sound_0183|>": 151851,
|
| 204 |
+
"<|sound_0184|>": 151852,
|
| 205 |
+
"<|sound_0185|>": 151853,
|
| 206 |
+
"<|sound_0186|>": 151854,
|
| 207 |
+
"<|sound_0187|>": 151855,
|
| 208 |
+
"<|sound_0188|>": 151856,
|
| 209 |
+
"<|sound_0189|>": 151857,
|
| 210 |
+
"<|sound_0190|>": 151858,
|
| 211 |
+
"<|sound_0191|>": 151859,
|
| 212 |
+
"<|sound_0192|>": 151860,
|
| 213 |
+
"<|sound_0193|>": 151861,
|
| 214 |
+
"<|sound_0194|>": 151862,
|
| 215 |
+
"<|sound_0195|>": 151863,
|
| 216 |
+
"<|sound_0196|>": 151864,
|
| 217 |
+
"<|sound_0197|>": 151865,
|
| 218 |
+
"<|sound_0198|>": 151866,
|
| 219 |
+
"<|sound_0199|>": 151867,
|
| 220 |
+
"<|sound_0200|>": 151868,
|
| 221 |
+
"<|sound_0201|>": 151869,
|
| 222 |
+
"<|sound_0202|>": 151870,
|
| 223 |
+
"<|sound_0203|>": 151871,
|
| 224 |
+
"<|sound_0204|>": 151872,
|
| 225 |
+
"<|sound_0205|>": 151873,
|
| 226 |
+
"<|sound_0206|>": 151874,
|
| 227 |
+
"<|sound_0207|>": 151875,
|
| 228 |
+
"<|sound_0208|>": 151876,
|
| 229 |
+
"<|sound_0209|>": 151877,
|
| 230 |
+
"<|sound_0210|>": 151878,
|
| 231 |
+
"<|sound_0211|>": 151879,
|
| 232 |
+
"<|sound_0212|>": 151880,
|
| 233 |
+
"<|sound_0213|>": 151881,
|
| 234 |
+
"<|sound_0214|>": 151882,
|
| 235 |
+
"<|sound_0215|>": 151883,
|
| 236 |
+
"<|sound_0216|>": 151884,
|
| 237 |
+
"<|sound_0217|>": 151885,
|
| 238 |
+
"<|sound_0218|>": 151886,
|
| 239 |
+
"<|sound_0219|>": 151887,
|
| 240 |
+
"<|sound_0220|>": 151888,
|
| 241 |
+
"<|sound_0221|>": 151889,
|
| 242 |
+
"<|sound_0222|>": 151890,
|
| 243 |
+
"<|sound_0223|>": 151891,
|
| 244 |
+
"<|sound_0224|>": 151892,
|
| 245 |
+
"<|sound_0225|>": 151893,
|
| 246 |
+
"<|sound_0226|>": 151894,
|
| 247 |
+
"<|sound_0227|>": 151895,
|
| 248 |
+
"<|sound_0228|>": 151896,
|
| 249 |
+
"<|sound_0229|>": 151897,
|
| 250 |
+
"<|sound_0230|>": 151898,
|
| 251 |
+
"<|sound_0231|>": 151899,
|
| 252 |
+
"<|sound_0232|>": 151900,
|
| 253 |
+
"<|sound_0233|>": 151901,
|
| 254 |
+
"<|sound_0234|>": 151902,
|
| 255 |
+
"<|sound_0235|>": 151903,
|
| 256 |
+
"<|sound_0236|>": 151904,
|
| 257 |
+
"<|sound_0237|>": 151905,
|
| 258 |
+
"<|sound_0238|>": 151906,
|
| 259 |
+
"<|sound_0239|>": 151907,
|
| 260 |
+
"<|sound_0240|>": 151908,
|
| 261 |
+
"<|sound_0241|>": 151909,
|
| 262 |
+
"<|sound_0242|>": 151910,
|
| 263 |
+
"<|sound_0243|>": 151911,
|
| 264 |
+
"<|sound_0244|>": 151912,
|
| 265 |
+
"<|sound_0245|>": 151913,
|
| 266 |
+
"<|sound_0246|>": 151914,
|
| 267 |
+
"<|sound_0247|>": 151915,
|
| 268 |
+
"<|sound_0248|>": 151916,
|
| 269 |
+
"<|sound_0249|>": 151917,
|
| 270 |
+
"<|sound_0250|>": 151918,
|
| 271 |
+
"<|sound_0251|>": 151919,
|
| 272 |
+
"<|sound_0252|>": 151920,
|
| 273 |
+
"<|sound_0253|>": 151921,
|
| 274 |
+
"<|sound_0254|>": 151922,
|
| 275 |
+
"<|sound_0255|>": 151923,
|
| 276 |
+
"<|sound_0256|>": 151924,
|
| 277 |
+
"<|sound_0257|>": 151925,
|
| 278 |
+
"<|sound_0258|>": 151926,
|
| 279 |
+
"<|sound_0259|>": 151927,
|
| 280 |
+
"<|sound_0260|>": 151928,
|
| 281 |
+
"<|sound_0261|>": 151929,
|
| 282 |
+
"<|sound_0262|>": 151930,
|
| 283 |
+
"<|sound_0263|>": 151931,
|
| 284 |
+
"<|sound_0264|>": 151932,
|
| 285 |
+
"<|sound_0265|>": 151933,
|
| 286 |
+
"<|sound_0266|>": 151934,
|
| 287 |
+
"<|sound_0267|>": 151935,
|
| 288 |
+
"<|sound_0268|>": 151936,
|
| 289 |
+
"<|sound_0269|>": 151937,
|
| 290 |
+
"<|sound_0270|>": 151938,
|
| 291 |
+
"<|sound_0271|>": 151939,
|
| 292 |
+
"<|sound_0272|>": 151940,
|
| 293 |
+
"<|sound_0273|>": 151941,
|
| 294 |
+
"<|sound_0274|>": 151942,
|
| 295 |
+
"<|sound_0275|>": 151943,
|
| 296 |
+
"<|sound_0276|>": 151944,
|
| 297 |
+
"<|sound_0277|>": 151945,
|
| 298 |
+
"<|sound_0278|>": 151946,
|
| 299 |
+
"<|sound_0279|>": 151947,
|
| 300 |
+
"<|sound_0280|>": 151948,
|
| 301 |
+
"<|sound_0281|>": 151949,
|
| 302 |
+
"<|sound_0282|>": 151950,
|
| 303 |
+
"<|sound_0283|>": 151951,
|
| 304 |
+
"<|sound_0284|>": 151952,
|
| 305 |
+
"<|sound_0285|>": 151953,
|
| 306 |
+
"<|sound_0286|>": 151954,
|
| 307 |
+
"<|sound_0287|>": 151955,
|
| 308 |
+
"<|sound_0288|>": 151956,
|
| 309 |
+
"<|sound_0289|>": 151957,
|
| 310 |
+
"<|sound_0290|>": 151958,
|
| 311 |
+
"<|sound_0291|>": 151959,
|
| 312 |
+
"<|sound_0292|>": 151960,
|
| 313 |
+
"<|sound_0293|>": 151961,
|
| 314 |
+
"<|sound_0294|>": 151962,
|
| 315 |
+
"<|sound_0295|>": 151963,
|
| 316 |
+
"<|sound_0296|>": 151964,
|
| 317 |
+
"<|sound_0297|>": 151965,
|
| 318 |
+
"<|sound_0298|>": 151966,
|
| 319 |
+
"<|sound_0299|>": 151967,
|
| 320 |
+
"<|sound_0300|>": 151968,
|
| 321 |
+
"<|sound_0301|>": 151969,
|
| 322 |
+
"<|sound_0302|>": 151970,
|
| 323 |
+
"<|sound_0303|>": 151971,
|
| 324 |
+
"<|sound_0304|>": 151972,
|
| 325 |
+
"<|sound_0305|>": 151973,
|
| 326 |
+
"<|sound_0306|>": 151974,
|
| 327 |
+
"<|sound_0307|>": 151975,
|
| 328 |
+
"<|sound_0308|>": 151976,
|
| 329 |
+
"<|sound_0309|>": 151977,
|
| 330 |
+
"<|sound_0310|>": 151978,
|
| 331 |
+
"<|sound_0311|>": 151979,
|
| 332 |
+
"<|sound_0312|>": 151980,
|
| 333 |
+
"<|sound_0313|>": 151981,
|
| 334 |
+
"<|sound_0314|>": 151982,
|
| 335 |
+
"<|sound_0315|>": 151983,
|
| 336 |
+
"<|sound_0316|>": 151984,
|
| 337 |
+
"<|sound_0317|>": 151985,
|
| 338 |
+
"<|sound_0318|>": 151986,
|
| 339 |
+
"<|sound_0319|>": 151987,
|
| 340 |
+
"<|sound_0320|>": 151988,
|
| 341 |
+
"<|sound_0321|>": 151989,
|
| 342 |
+
"<|sound_0322|>": 151990,
|
| 343 |
+
"<|sound_0323|>": 151991,
|
| 344 |
+
"<|sound_0324|>": 151992,
|
| 345 |
+
"<|sound_0325|>": 151993,
|
| 346 |
+
"<|sound_0326|>": 151994,
|
| 347 |
+
"<|sound_0327|>": 151995,
|
| 348 |
+
"<|sound_0328|>": 151996,
|
| 349 |
+
"<|sound_0329|>": 151997,
|
| 350 |
+
"<|sound_0330|>": 151998,
|
| 351 |
+
"<|sound_0331|>": 151999,
|
| 352 |
+
"<|sound_0332|>": 152000,
|
| 353 |
+
"<|sound_0333|>": 152001,
|
| 354 |
+
"<|sound_0334|>": 152002,
|
| 355 |
+
"<|sound_0335|>": 152003,
|
| 356 |
+
"<|sound_0336|>": 152004,
|
| 357 |
+
"<|sound_0337|>": 152005,
|
| 358 |
+
"<|sound_0338|>": 152006,
|
| 359 |
+
"<|sound_0339|>": 152007,
|
| 360 |
+
"<|sound_0340|>": 152008,
|
| 361 |
+
"<|sound_0341|>": 152009,
|
| 362 |
+
"<|sound_0342|>": 152010,
|
| 363 |
+
"<|sound_0343|>": 152011,
|
| 364 |
+
"<|sound_0344|>": 152012,
|
| 365 |
+
"<|sound_0345|>": 152013,
|
| 366 |
+
"<|sound_0346|>": 152014,
|
| 367 |
+
"<|sound_0347|>": 152015,
|
| 368 |
+
"<|sound_0348|>": 152016,
|
| 369 |
+
"<|sound_0349|>": 152017,
|
| 370 |
+
"<|sound_0350|>": 152018,
|
| 371 |
+
"<|sound_0351|>": 152019,
|
| 372 |
+
"<|sound_0352|>": 152020,
|
| 373 |
+
"<|sound_0353|>": 152021,
|
| 374 |
+
"<|sound_0354|>": 152022,
|
| 375 |
+
"<|sound_0355|>": 152023,
|
| 376 |
+
"<|sound_0356|>": 152024,
|
| 377 |
+
"<|sound_0357|>": 152025,
|
| 378 |
+
"<|sound_0358|>": 152026,
|
| 379 |
+
"<|sound_0359|>": 152027,
|
| 380 |
+
"<|sound_0360|>": 152028,
|
| 381 |
+
"<|sound_0361|>": 152029,
|
| 382 |
+
"<|sound_0362|>": 152030,
|
| 383 |
+
"<|sound_0363|>": 152031,
|
| 384 |
+
"<|sound_0364|>": 152032,
|
| 385 |
+
"<|sound_0365|>": 152033,
|
| 386 |
+
"<|sound_0366|>": 152034,
|
| 387 |
+
"<|sound_0367|>": 152035,
|
| 388 |
+
"<|sound_0368|>": 152036,
|
| 389 |
+
"<|sound_0369|>": 152037,
|
| 390 |
+
"<|sound_0370|>": 152038,
|
| 391 |
+
"<|sound_0371|>": 152039,
|
| 392 |
+
"<|sound_0372|>": 152040,
|
| 393 |
+
"<|sound_0373|>": 152041,
|
| 394 |
+
"<|sound_0374|>": 152042,
|
| 395 |
+
"<|sound_0375|>": 152043,
|
| 396 |
+
"<|sound_0376|>": 152044,
|
| 397 |
+
"<|sound_0377|>": 152045,
|
| 398 |
+
"<|sound_0378|>": 152046,
|
| 399 |
+
"<|sound_0379|>": 152047,
|
| 400 |
+
"<|sound_0380|>": 152048,
|
| 401 |
+
"<|sound_0381|>": 152049,
|
| 402 |
+
"<|sound_0382|>": 152050,
|
| 403 |
+
"<|sound_0383|>": 152051,
|
| 404 |
+
"<|sound_0384|>": 152052,
|
| 405 |
+
"<|sound_0385|>": 152053,
|
| 406 |
+
"<|sound_0386|>": 152054,
|
| 407 |
+
"<|sound_0387|>": 152055,
|
| 408 |
+
"<|sound_0388|>": 152056,
|
| 409 |
+
"<|sound_0389|>": 152057,
|
| 410 |
+
"<|sound_0390|>": 152058,
|
| 411 |
+
"<|sound_0391|>": 152059,
|
| 412 |
+
"<|sound_0392|>": 152060,
|
| 413 |
+
"<|sound_0393|>": 152061,
|
| 414 |
+
"<|sound_0394|>": 152062,
|
| 415 |
+
"<|sound_0395|>": 152063,
|
| 416 |
+
"<|sound_0396|>": 152064,
|
| 417 |
+
"<|sound_0397|>": 152065,
|
| 418 |
+
"<|sound_0398|>": 152066,
|
| 419 |
+
"<|sound_0399|>": 152067,
|
| 420 |
+
"<|sound_0400|>": 152068,
|
| 421 |
+
"<|sound_0401|>": 152069,
|
| 422 |
+
"<|sound_0402|>": 152070,
|
| 423 |
+
"<|sound_0403|>": 152071,
|
| 424 |
+
"<|sound_0404|>": 152072,
|
| 425 |
+
"<|sound_0405|>": 152073,
|
| 426 |
+
"<|sound_0406|>": 152074,
|
| 427 |
+
"<|sound_0407|>": 152075,
|
| 428 |
+
"<|sound_0408|>": 152076,
|
| 429 |
+
"<|sound_0409|>": 152077,
|
| 430 |
+
"<|sound_0410|>": 152078,
|
| 431 |
+
"<|sound_0411|>": 152079,
|
| 432 |
+
"<|sound_0412|>": 152080,
|
| 433 |
+
"<|sound_0413|>": 152081,
|
| 434 |
+
"<|sound_0414|>": 152082,
|
| 435 |
+
"<|sound_0415|>": 152083,
|
| 436 |
+
"<|sound_0416|>": 152084,
|
| 437 |
+
"<|sound_0417|>": 152085,
|
| 438 |
+
"<|sound_0418|>": 152086,
|
| 439 |
+
"<|sound_0419|>": 152087,
|
| 440 |
+
"<|sound_0420|>": 152088,
|
| 441 |
+
"<|sound_0421|>": 152089,
|
| 442 |
+
"<|sound_0422|>": 152090,
|
| 443 |
+
"<|sound_0423|>": 152091,
|
| 444 |
+
"<|sound_0424|>": 152092,
|
| 445 |
+
"<|sound_0425|>": 152093,
|
| 446 |
+
"<|sound_0426|>": 152094,
|
| 447 |
+
"<|sound_0427|>": 152095,
|
| 448 |
+
"<|sound_0428|>": 152096,
|
| 449 |
+
"<|sound_0429|>": 152097,
|
| 450 |
+
"<|sound_0430|>": 152098,
|
| 451 |
+
"<|sound_0431|>": 152099,
|
| 452 |
+
"<|sound_0432|>": 152100,
|
| 453 |
+
"<|sound_0433|>": 152101,
|
| 454 |
+
"<|sound_0434|>": 152102,
|
| 455 |
+
"<|sound_0435|>": 152103,
|
| 456 |
+
"<|sound_0436|>": 152104,
|
| 457 |
+
"<|sound_0437|>": 152105,
|
| 458 |
+
"<|sound_0438|>": 152106,
|
| 459 |
+
"<|sound_0439|>": 152107,
|
| 460 |
+
"<|sound_0440|>": 152108,
|
| 461 |
+
"<|sound_0441|>": 152109,
|
| 462 |
+
"<|sound_0442|>": 152110,
|
| 463 |
+
"<|sound_0443|>": 152111,
|
| 464 |
+
"<|sound_0444|>": 152112,
|
| 465 |
+
"<|sound_0445|>": 152113,
|
| 466 |
+
"<|sound_0446|>": 152114,
|
| 467 |
+
"<|sound_0447|>": 152115,
|
| 468 |
+
"<|sound_0448|>": 152116,
|
| 469 |
+
"<|sound_0449|>": 152117,
|
| 470 |
+
"<|sound_0450|>": 152118,
|
| 471 |
+
"<|sound_0451|>": 152119,
|
| 472 |
+
"<|sound_0452|>": 152120,
|
| 473 |
+
"<|sound_0453|>": 152121,
|
| 474 |
+
"<|sound_0454|>": 152122,
|
| 475 |
+
"<|sound_0455|>": 152123,
|
| 476 |
+
"<|sound_0456|>": 152124,
|
| 477 |
+
"<|sound_0457|>": 152125,
|
| 478 |
+
"<|sound_0458|>": 152126,
|
| 479 |
+
"<|sound_0459|>": 152127,
|
| 480 |
+
"<|sound_0460|>": 152128,
|
| 481 |
+
"<|sound_0461|>": 152129,
|
| 482 |
+
"<|sound_0462|>": 152130,
|
| 483 |
+
"<|sound_0463|>": 152131,
|
| 484 |
+
"<|sound_0464|>": 152132,
|
| 485 |
+
"<|sound_0465|>": 152133,
|
| 486 |
+
"<|sound_0466|>": 152134,
|
| 487 |
+
"<|sound_0467|>": 152135,
|
| 488 |
+
"<|sound_0468|>": 152136,
|
| 489 |
+
"<|sound_0469|>": 152137,
|
| 490 |
+
"<|sound_0470|>": 152138,
|
| 491 |
+
"<|sound_0471|>": 152139,
|
| 492 |
+
"<|sound_0472|>": 152140,
|
| 493 |
+
"<|sound_0473|>": 152141,
|
| 494 |
+
"<|sound_0474|>": 152142,
|
| 495 |
+
"<|sound_0475|>": 152143,
|
| 496 |
+
"<|sound_0476|>": 152144,
|
| 497 |
+
"<|sound_0477|>": 152145,
|
| 498 |
+
"<|sound_0478|>": 152146,
|
| 499 |
+
"<|sound_0479|>": 152147,
|
| 500 |
+
"<|sound_0480|>": 152148,
|
| 501 |
+
"<|sound_0481|>": 152149,
|
| 502 |
+
"<|sound_0482|>": 152150,
|
| 503 |
+
"<|sound_0483|>": 152151,
|
| 504 |
+
"<|sound_0484|>": 152152,
|
| 505 |
+
"<|sound_0485|>": 152153,
|
| 506 |
+
"<|sound_0486|>": 152154,
|
| 507 |
+
"<|sound_0487|>": 152155,
|
| 508 |
+
"<|sound_0488|>": 152156,
|
| 509 |
+
"<|sound_0489|>": 152157,
|
| 510 |
+
"<|sound_0490|>": 152158,
|
| 511 |
+
"<|sound_0491|>": 152159,
|
| 512 |
+
"<|sound_0492|>": 152160,
|
| 513 |
+
"<|sound_0493|>": 152161,
|
| 514 |
+
"<|sound_0494|>": 152162,
|
| 515 |
+
"<|sound_0495|>": 152163,
|
| 516 |
+
"<|sound_0496|>": 152164,
|
| 517 |
+
"<|sound_0497|>": 152165,
|
| 518 |
+
"<|sound_0498|>": 152166,
|
| 519 |
+
"<|sound_0499|>": 152167,
|
| 520 |
+
"<|sound_0500|>": 152168,
|
| 521 |
+
"<|sound_0501|>": 152169,
|
| 522 |
+
"<|sound_0502|>": 152170,
|
| 523 |
+
"<|sound_0503|>": 152171,
|
| 524 |
+
"<|sound_0504|>": 152172,
|
| 525 |
+
"<|sound_0505|>": 152173,
|
| 526 |
+
"<|sound_0506|>": 152174,
|
| 527 |
+
"<|sound_0507|>": 152175,
|
| 528 |
+
"<|sound_0508|>": 152176,
|
| 529 |
+
"<|sound_0509|>": 152177,
|
| 530 |
+
"<|sound_0510|>": 152178,
|
| 531 |
+
"<|sound_0511|>": 152179,
|
| 532 |
+
"<|sound_0512|>": 152180,
|
| 533 |
+
"<|sound_end|>": 151666,
|
| 534 |
+
"<|sound_start|>": 151665,
|
| 535 |
+
"<|text_to_sementic|>": 151667,
|
| 536 |
+
"<|video_pad|>": 151656,
|
| 537 |
+
"<|vision_end|>": 151653,
|
| 538 |
+
"<|vision_pad|>": 151654,
|
| 539 |
+
"<|vision_start|>": 151652
|
| 540 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|sound_start|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|sound_end|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|text_to_sementic|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"eos_token": {
|
| 26 |
+
"content": "<|im_end|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"pad_token": {
|
| 33 |
+
"content": "<|endoftext|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f649ce2d043c0d297c9234ff917770b4d816a97cf66bead316b30efbb0bbcef
|
| 3 |
+
size 11520458
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|