add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"], "lang2id": null, "id2lang": null, "do_lowercase_and_remove_accent": true, "do_lowercase": false, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "flaubert/flaubert_small_cased", "tokenizer_class": "FlaubertTokenizer"}