selimonder commited on
Commit
b9625b4
1 Parent(s): ac9735c

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|extratoken_100|>": 50356, "<|extratoken_86|>": 50342, "<|extratoken_55|>": 50311, "<|extratoken_63|>": 50319, "<|extratoken_84|>": 50340, "<|extratoken_71|>": 50327, "<|extratoken_136|>": 50392, "<|extratoken_1|>": 50257, "<|extratoken_32|>": 50288, "<|extratoken_18|>": 50274, "<|extratoken_74|>": 50330, "<|extratoken_65|>": 50321, "<|extratoken_108|>": 50364, "<|extratoken_48|>": 50304, "<|extratoken_22|>": 50278, "<|extratoken_133|>": 50389, "<|extratoken_82|>": 50338, "<|extratoken_112|>": 50368, "<|extratoken_129|>": 50385, "<|extratoken_31|>": 50287, "<|extratoken_6|>": 50262, "<|extratoken_78|>": 50334, "<|extratoken_23|>": 50279, "<|extratoken_14|>": 50270, "<|extratoken_27|>": 50283, "<|extratoken_29|>": 50285, "<|extratoken_69|>": 50325, "<|extratoken_49|>": 50305, "<|extratoken_54|>": 50310, "<|extratoken_119|>": 50375, "<|extratoken_13|>": 50269, "<|extratoken_5|>": 50261, "<|extratoken_39|>": 50295, "<|extratoken_52|>": 50308, "<|extratoken_118|>": 50374, "<|extratoken_139|>": 50395, "<|extratoken_72|>": 50328, "<|extratoken_38|>": 50294, "<|extratoken_59|>": 50315, "<|extratoken_89|>": 50345, "<|extratoken_67|>": 50323, "<|extratoken_2|>": 50258, "<|extratoken_80|>": 50336, "<|extratoken_120|>": 50376, "<|extratoken_56|>": 50312, "<|extratoken_17|>": 50273, "<|extratoken_35|>": 50291, "<|extratoken_92|>": 50348, "<|extratoken_46|>": 50302, "<|extratoken_109|>": 50365, "<|extratoken_26|>": 50282, "<|extratoken_107|>": 50363, "<|extratoken_70|>": 50326, "<|extratoken_40|>": 50296, "<|extratoken_99|>": 50355, "<|extratoken_66|>": 50322, "<|extratoken_20|>": 50276, "<|extratoken_45|>": 50301, "<|extratoken_143|>": 50399, "<|extratoken_114|>": 50370, "<|extratoken_128|>": 50384, "<|extratoken_24|>": 50280, "<|extratoken_57|>": 50313, "<|extratoken_43|>": 50299, "<|extratoken_53|>": 50309, "<|extratoken_81|>": 50337, "<|extratoken_68|>": 50324, "<|extratoken_73|>": 50329, "<|extratoken_25|>": 50281, "<|extratoken_95|>": 50351, "<|extratoken_64|>": 50320, "<|extratoken_137|>": 50393, "<|extratoken_121|>": 50377, "<|extratoken_113|>": 50369, "<|extratoken_134|>": 50390, "<|extratoken_116|>": 50372, "<|extratoken_37|>": 50293, "<|extratoken_115|>": 50371, "<|extratoken_117|>": 50373, "<|extratoken_62|>": 50318, "<|extratoken_51|>": 50307, "<|extratoken_93|>": 50349, "<|extratoken_88|>": 50344, "<|extratoken_94|>": 50350, "<|extratoken_9|>": 50265, "<|extratoken_130|>": 50386, "<|extratoken_50|>": 50306, "<|extratoken_79|>": 50335, "<|extratoken_15|>": 50271, "<|extratoken_76|>": 50332, "<|extratoken_97|>": 50353, "<|extratoken_28|>": 50284, "<|extratoken_3|>": 50259, "<|extratoken_98|>": 50354, "<|extratoken_91|>": 50347, "<|extratoken_60|>": 50316, "<|extratoken_41|>": 50297, "<|extratoken_12|>": 50268, "<|extratoken_110|>": 50366, "<|extratoken_4|>": 50260, "<|extratoken_140|>": 50396, "<|extratoken_96|>": 50352, "<|extratoken_123|>": 50379, "<|extratoken_125|>": 50381, "<|extratoken_61|>": 50317, "<|extratoken_103|>": 50359, "<|extratoken_19|>": 50275, "<|extratoken_106|>": 50362, "<|extratoken_122|>": 50378, "<|extratoken_33|>": 50289, "<|extratoken_104|>": 50360, "<|extratoken_127|>": 50383, "<|extratoken_75|>": 50331, "<|extratoken_47|>": 50303, "<|extratoken_142|>": 50398, "<|extratoken_34|>": 50290, "<|extratoken_101|>": 50357, "<|extratoken_141|>": 50397, "<|extratoken_124|>": 50380, "<|extratoken_85|>": 50341, "<|extratoken_58|>": 50314, "<|extratoken_90|>": 50346, "<|extratoken_44|>": 50300, "<|extratoken_10|>": 50266, "<|extratoken_102|>": 50358, "<|extratoken_77|>": 50333, "<|extratoken_36|>": 50292, "<|extratoken_21|>": 50277, "<|extratoken_8|>": 50264, "<|extratoken_7|>": 50263, "<|extratoken_138|>": 50394, "<|extratoken_87|>": 50343, "<|extratoken_126|>": 50382, "<|extratoken_105|>": 50361, "<|extratoken_83|>": 50339, "<|extratoken_16|>": 50272, "<|extratoken_132|>": 50388, "<|extratoken_42|>": 50298, "<|extratoken_111|>": 50367, "<|extratoken_135|>": 50391, "<|extratoken_30|>": 50286, "<|extratoken_11|>": 50267, "<|extratoken_131|>": 50387}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-j-6B", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff