full sample tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<UNK>": 50257, "<PAD>": 50259, "<SEP>": 50258}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": {"content": "<UNK>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": "<SEP>", "pad_token": "<PAD>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<UNK>", "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, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "pad_token": "<PAD>", "sep_token": "<SEP>", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}