add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50289, "       ": 50281, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50292, "                       ": 50265, "                   ": 50269, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50288, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50290, "                    ": 50268, "\t\t\t\t\t\t\t\t": 50298, "                         ": 50263, "\t\t\t\t\t": 50301, "          ": 50278, "                               ": 50257, "           ": 50277, "\t\t\t\t\t\t\t": 50299, "                              ": 50258, "                ": 50272, "                           ": 50261, "     ": 50283, "                 ": 50271, "                             ": 50259, "      ": 50282, "\t\t\t\t\t\t\t\t\t\t\t\t\t": 50293, "                      ": 50266, "\t\t\t\t\t\t\t\t\t\t": 50296, "    ": 50284, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50287, "                     ": 50267, "\t\t\t\t": 50302, "         ": 50279, "\t\t\t\t\t\t\t\t\t": 50297, "                  ": 50270, "   ": 50285, "\t\t": 50304, "               ": 50273, "  ": 50286, "                          ": 50262, "             ": 50275, "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t": 50291, "\t\t\t\t\t\t\t\t\t\t\t": 50295, "            ": 50276, "                        ": 50264, "        ": 50280, "              ": 50274, "                            ": 50260, "\t\t\t\t\t\t\t\t\t\t\t\t": 50294, "\t\t\t\t\t\t": 50300, "\t\t\t": 50303}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}