hiroshi-matsuda-rit commited on
Commit
1690dbf
1 Parent(s): d4a7665

add model files

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "electra-base-ud-japanese-c4-wordpiece-conj-switch-a-discriminator.2",
3
+ "architectures": [
4
+ "ElectraForPreTraining"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 768,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_name": "base",
16
+ "model_type": "electra",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "summary_activation": "gelu",
22
+ "summary_last_dropout": 0.1,
23
+ "summary_type": "first",
24
+ "summary_use_proj": true,
25
+ "transformers_version": "4.6.1",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 30112
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2cc69aacd51a8da3eac133cc9b15473f8434a593da61d49d419f09ba1d8997
3
+ size 434392869
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 @@
 
 
1
+ {"do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "sudachipy", "subword_tokenizer_type": "pos_substitution", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "word_form_type": "surface", "sudachipy_kwargs": null, "use_fast": false, "tokenizer_class": "sudachitra.tokenization_electra_sudachipy.ElectraSudachipyTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff