Upload tokenizer

Files changed (4) hide show

README.md CHANGED Viewed

@@ -1,8 +1,8 @@
 ---
 license: mit
-base_model: prajjwal1/bert-small
 tags:
 - generated_from_trainer
 model-index:
 - name: art-bert-base-cased
   results: []

 ---
 license: mit
 tags:
 - generated_from_trainer
+base_model: prajjwal1/bert-small
 model-index:
 - name: art-bert-base-cased
   results: []

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -43,11 +43,9 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_lower_case": false,
   "mask_token": "[MASK]",
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

vocab.txt CHANGED Viewed

The diff for this file is too large to render. See raw diff