change tokenizer configuration

.gitattributes

@@ -6,3 +6,5 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+tf_model.h5 filter=lfs diff=lfs merge=lfs -text

tokenizer_config.json

@@ -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": "[MASK]", "max_len": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/root/workspace/thesis/tokenizer_v2/"}
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]", "max_len": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/root/workspace/thesis/tokenizer_v2/"}