Taizo Kaneko commited on
Commit
91162ba
1 Parent(s): a32d3c8

commit files to HF hub

Browse files
config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CustomModel"
4
+ ],
5
+ "torch_dtype": "float32",
6
+ "transformers_version": "4.24.0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7cd4bf2443889b8e5d536b36a92637dd5f4df0306037eba6443382e92f7af0e
3
+ size 747
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "do_subword_tokenize": true,
5
+ "do_word_tokenize": true,
6
+ "jumanpp_kwargs": null,
7
+ "mask_token": "[MASK]",
8
+ "mecab_kwargs": null,
9
+ "model_max_length": 512,
10
+ "name_or_path": "cl-tohoku/bert-base-japanese",
11
+ "never_split": null,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "special_tokens_map_file": null,
15
+ "subword_tokenizer_type": "wordpiece",
16
+ "sudachi_kwargs": null,
17
+ "tokenizer_class": "BertJapaneseTokenizer",
18
+ "unk_token": "[UNK]",
19
+ "word_tokenizer_type": "mecab"
20
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff