pamessina commited on
Commit
b5dbccc
1 Parent(s): cdcf103

First version of the CXRFE model and tokenizer.

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedVLP-CXR-BERT-specialized",
3
+ "architectures": [
4
+ "CXRBertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.25,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/BiomedVLP-CXR-BERT-specialized--configuration_cxrbert.CXRBertConfig",
9
+ "AutoModel": "microsoft/BiomedVLP-CXR-BERT-specialized--modeling_cxrbert.CXRBertModel"
10
+ },
11
+ "classifier_dropout": null,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.25,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "cxr-bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "projection_size": 128,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.41.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 30522
31
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.41.2"
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2bb712f853a2abae9e8e6a5068b714bb1d0b7a3819cf3b66857a31c6c73cc4
3
+ size 438542360
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "auto_map": {
45
+ "AutoTokenizer": [
46
+ "microsoft/BiomedVLP-CXR-BERT-specialized--configuration_cxrbert.CXRBertTokenizer",
47
+ null
48
+ ]
49
+ },
50
+ "clean_up_tokenization_spaces": true,
51
+ "cls_token": "[CLS]",
52
+ "do_basic_tokenize": true,
53
+ "do_lower_case": true,
54
+ "mask_token": "[MASK]",
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "never_split": null,
57
+ "pad_token": "[PAD]",
58
+ "sep_token": "[SEP]",
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "CXRBertTokenizer",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff