Anja Reusch commited on
Commit
2ddcf16
1 Parent(s): df11351

support for fast tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +1 -1
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/s8252120/.cache/huggingface/transformers/828a43aa4b9d07e2b7d3be7c6bc10a3ae6e16e8d9c3a0c557783639de9eaeb1b.670e237d152dd53ef77575d4f4a6cd34158db03128fe4f63437ce0d5992bac74", "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}