Masatoshi Suzuki commited on
Commit
c89b4e4
1 Parent(s): bc6c8c8

First commit of the bert-base-japanese-v2 model and tokenizer.

Browse files

Files changed (5) hide show
  1. config.json +13 -0
  2. pytorch_model.bin +3 -0
  3. tf_model.h5 +3 -0
  4. tokenizer_config.json +8 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "hidden_act": "gelu",
4
+ "hidden_dropout_prob": 0.1,
5
+ "hidden_size": 768,
6
+ "initializer_range": 0.02,
7
+ "intermediate_size": 3072,
8
+ "max_position_embeddings": 512,
9
+ "num_attention_heads": 12,
10
+ "num_hidden_layers": 12,
11
+ "type_vocab_size": 2,
12
+ "vocab_size": 32768
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02b2a7a5f3606da4e15397e73ae81ac18ad8582331209b0880380f1a8c3da9d
3
+ size 447423557
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e324891530e4d92f6e93545b56670f144ea0108740a3dc7a7ce40986e68522b6
3
+ size 549869424
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "word_tokenizer_type": "mecab",
4
+ "subword_tokenizer_type": "wordpiece",
5
+ "mecab_kwargs": {
6
+ "mecab_dic": "unidic_lite"
7
+ }
8
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff