add tokenizer

merges.txt

@@ -0,0 +1 @@
+#version: 0.2 - Trained by `huggingface/tokenizers`

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1 @@
+{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":0,"special":true,"content":"<|endoftext|>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":null,"pre_tokenizer":{"type":"ByteLevel","add_prefix_space":false,"trim_offsets":true},"post_processor":{"type":"ByteLevel","add_prefix_space":true,"trim_offsets":false},"decoder":{"type":"ByteLevel","add_prefix_space":true,"trim_offsets":true},"model":{"type":"BPE","dropout":null,"unk_token":null,"continuing_subword_prefix":"","end_of_word_suffix":"","fuse_unk":false,"vocab":{"<|endoftext|>":0},"merges":[]}}

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"}

vocab.json

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