beomi commited on
Commit
a6f029f
1 Parent(s): 3de5c62

Add 848.4k KcELECTRA-base

Browse files
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForPreTraining"
4
+ ],
5
+ "num_hidden_layers": 12,
6
+ "hidden_size": 768,
7
+ "intermediate_size": 3072,
8
+ "num_attention_heads": 12,
9
+ "embedding_size": 768,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "type_vocab_size": 2,
18
+ "vocab_size": 50135,
19
+ "pad_token_id": 0,
20
+ "tokenizer_class": "BertTokenizer"
21
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb914aabf4627728d6494d8acda390a2f26200850a519f4bb55f1297c0ec86a
3
+ size 498271049
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "[UNK]",
3
+ "sep_token": "[SEP]",
4
+ "pad_token": "[PAD]",
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "do_basic_tokenize": true,
4
+ "never_split": null,
5
+ "unk_token": "[UNK]",
6
+ "sep_token": "[SEP]",
7
+ "pad_token": "[PAD]",
8
+ "cls_token": "[CLS]",
9
+ "mask_token": "[MASK]",
10
+ "tokenize_chinese_chars": true,
11
+ "strip_accents": null,
12
+ "model_max_length": 512
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff