Hugging Face's logo

thisiskeithkwan
/
stanford-deidentifier-base-onnx

Transformers
ONNX
bert
Model card Files
xet
 Community
thisiskeithkwan commited on
Commit
41584d1
·
verified ·
1 Parent(s): 6772061

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. config.json +46 -0
  2. onnx/config.json +46 -0
  3. onnx/model.onnx +3 -0
  4. onnx/model_quantized.onnx +3 -0
  5. onnx/ort_config.json +33 -0
  6. onnx/special_tokens_map.json +37 -0
  7. onnx/tokenizer.json +0 -0
  8. onnx/tokenizer_config.json +57 -0
  9. onnx/vocab.txt +0 -0
  10. ort_config.json +33 -0
  11. special_tokens_map.json +7 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +57 -0
  14. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "StanfordAIMI/stanford-deidentifier-base",
3
+ "architectures": [
4
+ "AutoModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "eos_token_ids": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "VENDOR",
15
+ "2": "DATE",
16
+ "3": "HCW",
17
+ "4": "HOSPITAL",
18
+ "5": "ID",
19
+ "6": "PATIENT",
20
+ "7": "PHONE"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "DATE": 2,
26
+ "HCW": 3,
27
+ "HOSPITAL": 4,
28
+ "ID": 5,
29
+ "O": 0,
30
+ "PATIENT": 6,
31
+ "PHONE": 7,
32
+ "VENDOR": 1
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "max_position_embeddings": 512,
36
+ "model_type": "bert",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "output_past": true,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "transformers_version": "4.41.2",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 30522
46
+ }
onnx/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/tmpqkvayh6m",
3
+ "architectures": [
4
+ "AutoModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "eos_token_ids": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "VENDOR",
15
+ "2": "DATE",
16
+ "3": "HCW",
17
+ "4": "HOSPITAL",
18
+ "5": "ID",
19
+ "6": "PATIENT",
20
+ "7": "PHONE"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "DATE": 2,
26
+ "HCW": 3,
27
+ "HOSPITAL": 4,
28
+ "ID": 5,
29
+ "O": 0,
30
+ "PATIENT": 6,
31
+ "PHONE": 7,
32
+ "VENDOR": 1
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "max_position_embeddings": 512,
36
+ "model_type": "bert",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "output_past": true,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "transformers_version": "4.41.2",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 30522
46
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee3841e8a2b4478d7db3d134f4ab0a5cb563868d0d6eddf52871d56e756b032
3
+ size 435893038
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf92b67cc121053b2472fc2a17b495442d248d58f300a9f5cb592627f58e263
3
+ size 109818828
onnx/ort_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "quantization": {
6
+ "activations_dtype": "QUInt8",
7
+ "activations_symmetric": false,
8
+ "format": "QOperator",
9
+ "is_static": false,
10
+ "mode": "IntegerOps",
11
+ "nodes_to_exclude": [],
12
+ "nodes_to_quantize": [],
13
+ "operators_to_quantize": [
14
+ "Conv",
15
+ "MatMul",
16
+ "Attention",
17
+ "LSTM",
18
+ "Gather",
19
+ "Transpose",
20
+ "EmbedLayerNormalization"
21
+ ],
22
+ "per_channel": false,
23
+ "qdq_add_pair_to_weight": false,
24
+ "qdq_dedicated_pair": false,
25
+ "qdq_op_type_per_channel_support_to_axis": {
26
+ "MatMul": 1
27
+ },
28
+ "reduce_range": false,
29
+ "weights_dtype": "QUInt8",
30
+ "weights_symmetric": true
31
+ },
32
+ "use_external_data_format": false
33
+ }
onnx/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
onnx/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
onnx/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
ort_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "quantization": {
6
+ "activations_dtype": "QUInt8",
7
+ "activations_symmetric": false,
8
+ "format": "QOperator",
9
+ "is_static": false,
10
+ "mode": "IntegerOps",
11
+ "nodes_to_exclude": [],
12
+ "nodes_to_quantize": [],
13
+ "operators_to_quantize": [
14
+ "Conv",
15
+ "MatMul",
16
+ "Attention",
17
+ "LSTM",
18
+ "Gather",
19
+ "Transpose",
20
+ "EmbedLayerNormalization"
21
+ ],
22
+ "per_channel": false,
23
+ "qdq_add_pair_to_weight": false,
24
+ "qdq_dedicated_pair": false,
25
+ "qdq_op_type_per_channel_support_to_axis": {
26
+ "MatMul": 1
27
+ },
28
+ "reduce_range": false,
29
+ "weights_dtype": "QUInt8",
30
+ "weights_symmetric": true
31
+ },
32
+ "use_external_data_format": false
33
+ }
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff