asahi417 commited on
Commit
a666984
1 Parent(s): cc9b876

add tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +1 -1
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +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/baseline_2021/roberta_large/model_mwzvua/epoch_10", "special_tokens_map_file": "cner_output/model/baseline_2021/roberta_large/model_mwzvua/epoch_10/special_tokens_map.json", "tokenizer_class": "RobertaTokenizer"}
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cner_output/model/baseline_2021/roberta_large/best_model", "tokenizer_class": "RobertaTokenizer"}