add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<pad>": 50259, "<s>": 50257, "</s>": 50258}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<|endoftext|>", "pad_token": "<pad>", "additional_special_tokens": ["<s>", "</s>", "<pad>"]}

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"}