kiyono commited on
Commit
8e0dd0e
1 Parent(s): f776b3c

initial commit

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.5.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 100002
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a279364774123165dcc515e7840d5f18d6f5ecd26ade26355b4c30653c453a85
3
+ size 652269275
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f486660afe1c3edc98c96ce69928d5dfbb0d04d3cda791687c137382e8667ce
3
+ size 2024878
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "word_tokenizer_type": "mecab",
4
+ "mecab_kwargs": {
5
+ "mecab_dic": "unidic_lite"
6
+ },
7
+ "do_zenkaku": true
8
+ }