baikal-nlp commited on
Commit
866bfb5
1 Parent(s): 4b7aece

start: 110k

Browse files
Files changed (5) hide show
  1. README.md +14 -0
  2. base-gen.json +26 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer_config.json +4 -0
  5. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ko
3
+ datasets:
4
+ - kowiki
5
+ - news
6
+ ---
7
+
8
+ deeqELECTRA-base
9
+ ---
10
+
11
+ - model: electra-base-generator
12
+ - vocab: bert-wordpiece, 35k
13
+ - version: latest
14
+
base-gen.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "embedding_size": 768,
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
+ "position_embedding_type": "absolute",
19
+ "summary_activation": "gelu",
20
+ "summary_last_dropout": 0.1,
21
+ "summary_type": "first",
22
+ "summary_use_proj": true,
23
+ "transformers_version": "4.6.0.dev0",
24
+ "type_vocab_size": 2,
25
+ "vocab_size": 35000
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc69ae87611a2e581f43abb01bd7e6fece5ecb74a309a8097cb151e133815407
3
+ size 148825700
tokenizer_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "do_lower_case": false
3
+ }
4
+
vocab.txt ADDED
The diff for this file is too large to render. See raw diff