singletongue commited on
Commit
2cbf66b
1 Parent(s): f4fd5c8

First commit of the bert-large-japanese 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": 1024,
6
+ "initializer_range": 0.02,
7
+ "intermediate_size": 4096,
8
+ "max_position_embeddings": 512,
9
+ "num_attention_heads": 16,
10
+ "num_hidden_layers": 24,
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:f31f607d5e3220878a6731b958fc235aa502b937b5ede0036801037df3859ec5
3
+ size 1354281605
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2458f77c2f17d16c7664f9db840f704baf83c4b312ead0846b362c54df32d1a
3
+ size 1490975032
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