cl-tohoku commited on
Commit
65243d6
1 Parent(s): f58f6fc

Add model files

Browse files
Files changed (6) hide show
  1. config.json +19 -0
  2. flax_model.msgpack +3 -0
  3. pytorch_model.bin +3 -0
  4. tf_model.h5 +3 -0
  5. tokenizer_config.json +10 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 3072,
11
+ "layer_norm_eps": 1e-12,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "bert",
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 12,
16
+ "pad_token_id": 0,
17
+ "type_vocab_size": 2,
18
+ "vocab_size": 32768
19
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dce0b8b350432362a184b9f8bb90ffb0f2ff0c394ab43b915e318926f4e7569
3
+ size 447341816
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e172862e0674054d65e0ba40d67df2a4687982f589db44aa27091c386e5450a4
3
+ size 447406217
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71920d0dc0174d0a0ce32b934fe65f15320b2d53aa7e671718b33065748cb712
3
+ size 549871840
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "BertJapaneseTokenizer",
3
+ "model_max_length": 512,
4
+ "do_lower_case": false,
5
+ "word_tokenizer_type": "mecab",
6
+ "subword_tokenizer_type": "wordpiece",
7
+ "mecab_kwargs": {
8
+ "mecab_dic": "unidic_lite"
9
+ }
10
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff