briverse commited on
Commit
3407780
1 Parent(s): 5cfc19f

add model, tokenizer

Browse files
Files changed (4) hide show
  1. config.json +20 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer.json +0 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForPreTraining"
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": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "electra",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "type_vocab_size": 2,
19
+ "vocab_size": 64000
20
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414b424c257fe14605b8ef035d8938a6702dda697520b226b791e5a0e582416d
3
+ size 540862295
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff