add tokenizer

tokenizer_config.json

@@ -1 +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, "name_or_path": "cner_output/model/self_training_2021/roberta_large_continuous/model_ckqpdj/epoch_10", "special_tokens_map_file": "cner_output/model/baseline/roberta_large/best_model/special_tokens_map.json", "tokenizer_class": "RobertaTokenizer"}
+{"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, "name_or_path": "cner_output/model/self_training_2021/roberta_large_continuous/best_model", "special_tokens_map_file": "/home/c.c2042013/.cache/huggingface/transformers/f13c0d4fbb91837912532d8abfe04b839ae0469f26de2112d4d853ab113deb75.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342", "tokenizer_class": "RobertaTokenizer"}