helboukkouri commited on
Commit
3cc3d05
1 Parent(s): 2b3d00d

Add CharacterBERT(medical) model

Browse files
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CharacterBertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "character_embeddings_dim": 16,
7
+ "cnn_activation": "relu",
8
+ "cnn_filters": [
9
+ [
10
+ 1,
11
+ 32
12
+ ],
13
+ [
14
+ 2,
15
+ 32
16
+ ],
17
+ [
18
+ 3,
19
+ 64
20
+ ],
21
+ [
22
+ 4,
23
+ 128
24
+ ],
25
+ [
26
+ 5,
27
+ 256
28
+ ],
29
+ [
30
+ 6,
31
+ 512
32
+ ],
33
+ [
34
+ 7,
35
+ 1024
36
+ ]
37
+ ],
38
+ "hidden_act": "gelu",
39
+ "hidden_dropout_prob": 0.1,
40
+ "hidden_size": 768,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "layer_norm_eps": 1e-12,
44
+ "max_position_embeddings": 512,
45
+ "max_word_length": 50,
46
+ "mlm_vocab_size": 100000,
47
+ "model_type": "character_bert",
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 12,
50
+ "num_highway_layers": 2,
51
+ "tie_word_embeddings": false,
52
+ "type_vocab_size": 2
53
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df985d92f0dfad42742d3f685d7497a2d83e762be3b24e55322cfa5d6b043d03
3
+ size 418464323
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
+ {"max_word_length": 50, "do_lower_case": true, "do_basic_tokenize": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
vocab.txt ADDED
File without changes