diff --git "a/tokenizer.json" "b/tokenizer.json" new file mode 100644--- /dev/null +++ "b/tokenizer.json" @@ -0,0 +1,129482 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32000, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32001, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32002, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32003, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32004, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32005, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32006, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32007, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32008, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32009, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32010, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32011, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32012, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32013, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32014, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32015, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32016, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32017, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32018, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32019, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32020, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32021, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32022, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32023, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32024, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32025, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32026, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32027, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32028, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32029, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32030, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32031, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32032, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32033, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32034, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32035, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32036, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32037, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32038, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32039, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32040, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32041, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32042, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32043, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32044, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32045, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32046, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32047, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32048, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32049, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32050, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32051, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32052, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32053, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32054, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32055, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32056, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32057, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32058, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32059, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32060, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32061, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32062, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32063, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32064, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32065, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32066, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32067, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32068, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32069, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32070, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32071, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32072, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32073, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32074, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32075, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32076, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32077, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32078, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32079, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32080, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32081, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32082, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32083, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32084, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32085, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32086, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32087, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32088, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32089, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32090, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32091, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32092, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32093, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32094, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32095, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32096, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32097, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32098, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32099, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32100, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32101, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32102, + "content": "