add tokenizer

Browse files

Files changed (3) hide show

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

added_tokens.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"~~[CLS]~~": ~~50257~~, "[SEP]": 50258, "~~<pad>~~": ~~50259~~, "[~~MASK~~]": ~~50260~~}


1	+ {"<pad>": 50259, "[SEP]": 50258, "[MASK]": 50260, "[CLS]": 50257, "<unk>": 50261}

tokenizer.json ADDED Viewed

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

tokenizer_config.json CHANGED Viewed

@@ -1 +1 @@

- {"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": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "~~/content/drive/MyDrive/ColabModels/GPT2SmallTheseus/pytorch_model/~~special_tokens_map.json", "name_or_path": "/content/~~drive~~/~~MyDrive/ColabModels/GPT2SmallTheseus/pytorch_model/~~", "tokenizer_class": "AlbertTokenizer"}

+ {"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": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "special_tokens_map.json", "name_or_path": "/content/tokenizer/", "tokenizer_class": "AlbertTokenizer"}