patrickvonplaten commited on
Commit
ec054cd
·
1 Parent(s): 9190dde

upload model files

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfd1eae4522281b1b839eab877a791befec7a1663a41c814c77d9c89c748f2d
3
+ size 253154
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token_box": [0, 0, 0, 0], "sep_token_box": [1000, 1000, 1000, 1000], "pad_token_box": [0, 0, 0, 0], "pad_token_label": -100, "only_label_first_subword": true, "sp_model_kwargs": {}, "keep_accents": true, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "./", "tokenizer_file": null, "tokenizer_class": "LayoutXLMTokenizer"}