Hugging Face's logo

Spaces:
publichealthsurveillance
/
PHS-BERT
Runtime error

App Files Community
Chan Lee commited on
Commit
028b2fe
•
1 Parent(s): 330fe92

M

Browse files
Files changed (30) hide show
  1. cv/bert/config.json +24 -0
  2. cv/bert/special_tokens_map.json +1 -0
  3. cv/bert/tf_model.preproc +0 -0
  4. cv/bert/tokenizer_config.json +1 -0
  5. cv/bert/vocab.txt +0 -0
  6. cv/mentalbert/config.json +25 -0
  7. cv/mentalbert/special_tokens_map.json +1 -0
  8. cv/mentalbert/tf_model.preproc +0 -0
  9. cv/mentalbert/tokenizer_config.json +1 -0
  10. cv/mentalbert/vocab.txt +0 -0
  11. cv/phsbert/config.json +25 -0
  12. cv/phsbert/special_tokens_map.json +1 -0
  13. cv/phsbert/tf_model.preproc +0 -0
  14. cv/phsbert/tokenizer_config.json +1 -0
  15. cv/phsbert/vocab.txt +0 -0
  16. sc/bert/config.json +38 -0
  17. sc/bert/special_tokens_map.json +1 -0
  18. sc/bert/tf_model.preproc +0 -0
  19. sc/bert/tokenizer_config.json +1 -0
  20. sc/bert/vocab.txt +0 -0
  21. sc/mentalbert/config.json +39 -0
  22. sc/mentalbert/special_tokens_map.json +1 -0
  23. sc/mentalbert/tf_model.preproc +0 -0
  24. sc/mentalbert/tokenizer_config.json +1 -0
  25. sc/mentalbert/vocab.txt +0 -0
  26. sc/phsbert/config.json +39 -0
  27. sc/phsbert/special_tokens_map.json +1 -0
  28. sc/phsbert/tf_model.preproc +0 -0
  29. sc/phsbert/tokenizer_config.json +1 -0
  30. sc/phsbert/vocab.txt +0 -0
cv/bert/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
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
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.3.3",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
cv/bert/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
cv/bert/tf_model.preproc ADDED
Binary file (2.22 kB). View file
 
cv/bert/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
cv/bert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
cv/mentalbert/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mental/mental-bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
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
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.3.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
cv/mentalbert/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
cv/mentalbert/tf_model.preproc ADDED
Binary file (2.28 kB). View file
 
cv/mentalbert/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "mental/mental-bert-base-uncased", "tokenizer_class": "BertTokenizer"}
cv/mentalbert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
cv/phsbert/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "publichealthsurveillance/PHS-BERT",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "total_flos": 2232610412725615392,
21
+ "transformers_version": "4.3.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
cv/phsbert/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
cv/phsbert/tf_model.preproc ADDED
Binary file (2.29 kB). View file
 
cv/phsbert/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "publichealthsurveillance/PHS-BERT", "do_basic_tokenize": true, "never_split": null}
cv/phsbert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
sc/bert/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "transformers_version": "4.3.3",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
sc/bert/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
sc/bert/tf_model.preproc ADDED
Binary file (2.29 kB). View file
 
sc/bert/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
sc/bert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
sc/mentalbert/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mental/mental-bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.3.3",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30522
39
+ }
sc/mentalbert/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
sc/mentalbert/tf_model.preproc ADDED
Binary file (2.34 kB). View file
 
sc/mentalbert/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "mental/mental-bert-base-uncased", "tokenizer_class": "BertTokenizer"}
sc/mentalbert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
sc/phsbert/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "publichealthsurveillance/PHS-BERT",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 16,
31
+ "num_hidden_layers": 24,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "total_flos": 2232610412725615392,
35
+ "transformers_version": "4.3.3",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30522
39
+ }
sc/phsbert/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
sc/phsbert/tf_model.preproc ADDED
Binary file (2.35 kB). View file
 
sc/phsbert/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "publichealthsurveillance/PHS-BERT", "do_basic_tokenize": true, "never_split": null}
sc/phsbert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff