Hugging Face's logo

andrews3596
/
deid_roberta_i2b2_quantized

ONNX
English
roberta
deidentification
medical notes
ehr
phi
Model card Files
xet
Community
andrews3596 commited on
Commit
666c9e3
·
verified ·
1 Parent(s): d6dae23

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +123 -0
  2. merges.txt +0 -0
  3. onnx/model_quantized.onnx +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +63 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "obi/deid_roberta_i2b2",
4
+ "architectures": [
5
+ "RobertaForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "finetuning_task": "ner",
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "id2label": {
16
+ "0": "B-AGE",
17
+ "1": "B-DATE",
18
+ "2": "B-EMAIL",
19
+ "3": "B-HOSP",
20
+ "4": "B-ID",
21
+ "5": "B-LOC",
22
+ "6": "B-OTHERPHI",
23
+ "7": "B-PATIENT",
24
+ "8": "B-PATORG",
25
+ "9": "B-PHONE",
26
+ "10": "B-STAFF",
27
+ "11": "I-AGE",
28
+ "12": "I-DATE",
29
+ "13": "I-EMAIL",
30
+ "14": "I-HOSP",
31
+ "15": "I-ID",
32
+ "16": "I-LOC",
33
+ "17": "I-OTHERPHI",
34
+ "18": "I-PATIENT",
35
+ "19": "I-PATORG",
36
+ "20": "I-PHONE",
37
+ "21": "I-STAFF",
38
+ "22": "L-AGE",
39
+ "23": "L-DATE",
40
+ "24": "L-EMAIL",
41
+ "25": "L-HOSP",
42
+ "26": "L-ID",
43
+ "27": "L-LOC",
44
+ "28": "L-OTHERPHI",
45
+ "29": "L-PATIENT",
46
+ "30": "L-PATORG",
47
+ "31": "L-PHONE",
48
+ "32": "L-STAFF",
49
+ "33": "O",
50
+ "34": "U-AGE",
51
+ "35": "U-DATE",
52
+ "36": "U-EMAIL",
53
+ "37": "U-HOSP",
54
+ "38": "U-ID",
55
+ "39": "U-LOC",
56
+ "40": "U-OTHERPHI",
57
+ "41": "U-PATIENT",
58
+ "42": "U-PATORG",
59
+ "43": "U-PHONE",
60
+ "44": "U-STAFF"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 4096,
64
+ "label2id": {
65
+ "B-AGE": 0,
66
+ "B-DATE": 1,
67
+ "B-EMAIL": 2,
68
+ "B-HOSP": 3,
69
+ "B-ID": 4,
70
+ "B-LOC": 5,
71
+ "B-OTHERPHI": 6,
72
+ "B-PATIENT": 7,
73
+ "B-PATORG": 8,
74
+ "B-PHONE": 9,
75
+ "B-STAFF": 10,
76
+ "I-AGE": 11,
77
+ "I-DATE": 12,
78
+ "I-EMAIL": 13,
79
+ "I-HOSP": 14,
80
+ "I-ID": 15,
81
+ "I-LOC": 16,
82
+ "I-OTHERPHI": 17,
83
+ "I-PATIENT": 18,
84
+ "I-PATORG": 19,
85
+ "I-PHONE": 20,
86
+ "I-STAFF": 21,
87
+ "L-AGE": 22,
88
+ "L-DATE": 23,
89
+ "L-EMAIL": 24,
90
+ "L-HOSP": 25,
91
+ "L-ID": 26,
92
+ "L-LOC": 27,
93
+ "L-OTHERPHI": 28,
94
+ "L-PATIENT": 29,
95
+ "L-PATORG": 30,
96
+ "L-PHONE": 31,
97
+ "L-STAFF": 32,
98
+ "O": 33,
99
+ "U-AGE": 34,
100
+ "U-DATE": 35,
101
+ "U-EMAIL": 36,
102
+ "U-HOSP": 37,
103
+ "U-ID": 38,
104
+ "U-LOC": 39,
105
+ "U-OTHERPHI": 40,
106
+ "U-PATIENT": 41,
107
+ "U-PATORG": 42,
108
+ "U-PHONE": 43,
109
+ "U-STAFF": 44
110
+ },
111
+ "layer_norm_eps": 1e-05,
112
+ "max_position_embeddings": 514,
113
+ "model_type": "roberta",
114
+ "num_attention_heads": 16,
115
+ "num_hidden_layers": 24,
116
+ "pad_token_id": 1,
117
+ "position_embedding_type": "absolute",
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.49.0",
120
+ "type_vocab_size": 1,
121
+ "use_cache": true,
122
+ "vocab_size": 50265
123
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6849223731355d23fcba1a7658934490dee984d8f313ab68d263fa2f1e93bcca
3
+ size 357256503
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "do_lower_case": false,
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "extra_special_tokens": {},
52
+ "mask_token": "<mask>",
53
+ "max_length": 512,
54
+ "model_max_length": 512,
55
+ "pad_token": "<pad>",
56
+ "sep_token": "</s>",
57
+ "stride": 0,
58
+ "tokenizer_class": "RobertaTokenizer",
59
+ "trim_offsets": true,
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "<unk>"
63
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff