Hugging Face's logo

mlml-chip
/
termexists-ssm-cnlpt-0.7.1

Safetensors
cnlpt
Model card Files
xet
Community
tmills commited on
Commit
0b0aac4
·
verified ·
1 Parent(s): 9b40f48

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. added_tokens.json +10 -0
  2. config.json +117 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +17 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +133 -0
  7. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</a1>": 28898,
3
+ "</a2>": 28900,
4
+ "</e>": 28896,
5
+ "<a1>": 28897,
6
+ "<a2>": 28899,
7
+ "<cr>": 28901,
8
+ "<e>": 28895,
9
+ "<neg>": 28902
10
+ }
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CnlpModelForClassification"
4
+ ],
5
+ "character_level": false,
6
+ "cnlpt_version": "0.7.1",
7
+ "encoder_config": {
8
+ "_attn_implementation_autoset": false,
9
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
10
+ "add_cross_attention": false,
11
+ "architectures": [
12
+ "BertForMaskedLM"
13
+ ],
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "classifier_dropout": null,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 512,
50
+ "min_length": 0,
51
+ "model_type": "bert",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 12,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 12,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 0,
62
+ "position_embedding_type": "absolute",
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.46.2",
83
+ "type_vocab_size": 2,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 28903
88
+ },
89
+ "encoder_name": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
90
+ "finetuning_task": [
91
+ "TermExists"
92
+ ],
93
+ "hidden_dropout_prob": 0.1,
94
+ "hidden_size": 768,
95
+ "hier_head_config": null,
96
+ "label_dictionary": {
97
+ "TermExists": [
98
+ "-1",
99
+ "1"
100
+ ]
101
+ },
102
+ "layer": 11,
103
+ "model_type": "cnlpt",
104
+ "num_rel_attention_heads": 12,
105
+ "rel_attention_head_dims": 64,
106
+ "relations": {
107
+ "TermExists": false
108
+ },
109
+ "tagger": {
110
+ "TermExists": false
111
+ },
112
+ "tokens": false,
113
+ "torch_dtype": "float32",
114
+ "transformers_version": "4.46.2",
115
+ "use_prior_tasks": false,
116
+ "vocab_size": 28903
117
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d970de5e09335be155d625da28116836eb647e736d83d7043b25eabde60a8fa3
3
+ size 435348272
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<e>",
4
+ "</e>",
5
+ "<a1>",
6
+ "</a1>",
7
+ "<a2>",
8
+ "</a2>",
9
+ "<cr>",
10
+ "<neg>"
11
+ ],
12
+ "cls_token": "[CLS]",
13
+ "mask_token": "[MASK]",
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "unk_token": "[UNK]"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "28895": {
45
+ "content": "<e>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "28896": {
53
+ "content": "</e>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "28897": {
61
+ "content": "<a1>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "28898": {
69
+ "content": "</a1>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "28899": {
77
+ "content": "<a2>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "28900": {
85
+ "content": "</a2>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "28901": {
93
+ "content": "<cr>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "28902": {
101
+ "content": "<neg>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ }
108
+ },
109
+ "additional_special_tokens": [
110
+ "<e>",
111
+ "</e>",
112
+ "<a1>",
113
+ "</a1>",
114
+ "<a2>",
115
+ "</a2>",
116
+ "<cr>",
117
+ "<neg>"
118
+ ],
119
+ "clean_up_tokenization_spaces": true,
120
+ "cls_token": "[CLS]",
121
+ "do_basic_tokenize": true,
122
+ "do_lower_case": true,
123
+ "mask_token": "[MASK]",
124
+ "model_max_length": 1000000000000000019884624838656,
125
+ "never_split": null,
126
+ "pad_token": "[PAD]",
127
+ "sep_token": "[SEP]",
128
+ "strip_accents": null,
129
+ "tokenize_chinese_chars": true,
130
+ "tokenizer_class": "BertTokenizer",
131
+ "truncation_side": "right",
132
+ "unk_token": "[UNK]"
133
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff