hiroshi-matsuda-rit commited on
Commit
2b4c5ad
1 Parent(s): 00fa913

add model files

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForPreTraining"
4
+ ],
5
+ "model_type": "electra",
6
+ "model_name": "base",
7
+ "vocab_size": 30112,
8
+ "embedding_size": 768,
9
+ "hidden_size": 768,
10
+ "num_hidden_layers": 12,
11
+ "num_attention_heads": 12,
12
+ "intermediate_size": 3072,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "attention_probs_dropout_prob": 0.1,
16
+ "max_position_embeddings": 512,
17
+ "type_vocab_size": 2,
18
+ "initializer_range": 0.02,
19
+ "layer_norm_eps": 1e-12,
20
+ "summary_type": "first",
21
+ "summary_use_proj": true,
22
+ "summary_activation": "gelu",
23
+ "summary_last_dropout": 0.1,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute"
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4412201f4146092b562f92ec0ea5be3ad697cd0c83c4817a5ea411375900cd9
3
+ size 436755117
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "word_tokenizer_type": "sudachipy",
4
+ "word_form_type": "surface",
5
+ "subword_tokenizer_type": "wordpiece",
6
+ "model_max_length": 512,
7
+ "sudachipy_kwargs": {"split_mode":"A","dict_type":"core"}
8
+ }
9
+
vocab.txt ADDED
The diff for this file is too large to render. See raw diff