add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<reserved-1>": 50266, "<reserved-5>": 50270, "<reserved-6>": 50271, "<reserved-8>": 50273, "<reserved-7>": 50272, "<reserved-0>": 50265, "<reserved-4>": 50269, "<reserved-9>": 50274, "<reserved-3>": 50268, "<reserved-2>": 50267}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<reserved-0>", "<reserved-1>", "<reserved-2>", "<reserved-3>", "<reserved-4>", "<reserved-5>", "<reserved-6>", "<reserved-7>", "<reserved-8>", "<reserved-9>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}