joangines commited on
Commit
8a74bed
1 Parent(s): 03a7e51

add model files

Browse files
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "embedding_size": 128,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 1024,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "electra",
15
+ "num_attention_heads": 4,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "type_vocab_size": 2,
19
+ "vocab_size": 32000,
20
+ "xla_device": false
21
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ca4f44bc82639843930ec6622f8a2aa769a0027b70a94389ab772cfa2634a6
3
+ size 55001623
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, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "tokenize_chinese_chars": false, "model_max_length": 512}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff