add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<|startoftext|>": 50258, "<|unknown|>": 50259, "<|endoftext|>": 50257}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "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, "do_lower_case": false, "max_len": 1024, "special_tokens_map_file": "special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "finetuned/checkpoint-4146", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}