Maltehb commited on
Commit
3203af4
1 Parent(s): 283fdb4
Files changed (2) hide show
  1. config.json +21 -14
  2. pytorch_model.bin +3 -0
config.json CHANGED
@@ -1,19 +1,26 @@
1
  {
2
- "intermediate_size": 3072,
3
- "pooler_type": "first_token_transform",
4
- "initializer_range": 0.02,
 
 
 
 
5
  "hidden_dropout_prob": 0.1,
 
 
 
 
 
 
 
6
  "num_hidden_layers": 12,
7
- "vocab_size": 32000,
8
- "pooler_size_per_head": 128,
9
- "attention_probs_dropout_prob": 0.1,
10
  "pooler_num_attention_heads": 12,
11
- "type_vocab_size": 2,
12
- "num_attention_heads": 12,
13
- "max_position_embeddings": 512,
14
- "hidden_size": 768,
15
- "directionality": "bidi",
16
  "pooler_num_fc_layers": 3,
17
- "hidden_act": "gelu",
18
- "pooler_fc_size": 768
19
- }
 
 
 
1
  {
2
+ "architectures": [
3
+ "BertForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "directionality": "bidi",
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
  "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_fc_size": 768,
 
20
  "pooler_num_attention_heads": 12,
 
 
 
 
 
21
  "pooler_num_fc_layers": 3,
22
+ "pooler_size_per_head": 128,
23
+ "pooler_type": "first_token_transform",
24
+ "type_vocab_size": 2,
25
+ "vocab_size": 32000
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3ef03a7c364daa00db6855a4c97711effbda850bc8f18886d803caa7faa114
3
+ size 445061189