add tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +0 -0
tokenizer_config.json +1 -1

tokenizer.json ADDED Viewed

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

tokenizer_config.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"do_lower_case": true, "~~do_basic_tokenize": true, "never_split": null, "~~unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "./AraBertMo_base_V9/~~bert-ar-vocab~~.~~txt~~", "tokenizer_class": "BertTokenizer"}

+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "name_or_path": "Ebtihal/AraBertMo_base_V9", "special_tokens_map_file": "/root/.cache/huggingface/transformers/67234162e6c9fe5503fd7a006a6074dd88141f38a08b350164ebffc7658b22bb.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_class": "BertTokenizer"}