Augmentations and undup

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5258683127030c253dbd6c9e9c32221bdf8f0732f284dcaca4b80c9619ba82ee
+oid sha256:9802aaa1a432d28ef25b67259e0af14ef4048724715292d3bef2bdd6c7f24576
 size 711504045

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/ilya-gusev/.cache/huggingface/transformers/1f428acdde727eed5de979d6856ce350a470be2a64e134a1fdae04af78a27301.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/rubert-base-cased-conversational", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "special_tokens_map_file": "models/rubertconv/special_tokens_map.json", "name_or_path": "models/rubertconv", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}