add tokenizer

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask_2>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"]}

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
-size 1915455
+oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
+size 1912529

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": "[MASK]", "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token_sent": null, "offset": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/b548e984b09823ed5cea0e622c0ec194a7e07b3c5d2e6b48a7cde84bd179cc7c.4eda581f816a0a941629106f0338c957910ce4839ecf7e3e743bb79523bf7249", "name_or_path": "google/bigbird-pegasus-large-arxiv", "model_max_length": 4096, "tokenizer_file": "/scratch/work/truongl3/hf_home/transformers/114304786763b6699cb6410cf9157c5467c015572ef969732a328a71f49b2e87.5d90d0c694dc11b42f74927efea80a49f2123fc4d91d2f05048d03acbd34673b", "tokenizer_class": "PegasusTokenizer"}
+{"eos_token": "</s>", "unk_token": "<unk>", "mask_token": "<mask_2>", "pad_token": "<pad>", "mask_token_sent": "<mask_1>", "offset": 103, "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "full_tokenizer_file": null, "tokenizer_file": "/scratch/work/truongl3/hf_home/transformers/249fc759c5fa315dca06897d79493c1d27d999d4876ebb798d07d9d7a2ebbb29.b11a22b825f5f3714fac8c470a8602bd6f8fbce86cb56e588c571016e963bd4e", "name_or_path": "google/pegasus-xsum", "tokenizer_class": "PegasusTokenizer"}