linjieccc commited on
Commit
5ff47b9
1 Parent(s): 7158ec9

Upload with huggingface_hub

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_tokenize_postprocess": true, "sep_token": "[SEP]", "cls_token": "[CLS]", "unk_token": "[UNK]", "pad_token": "[PAD]", "mask_token": "[MASK]", "do_lower_case": true, "model_max_length": 514, "tokenizer_class": "ErnieLayoutTokenizer", "special_tokens_map_file": "/root/.paddlenlp/models/__internal_testing__/tiny-random-uie-x/special_tokens_map.json"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff