tmills commited on
Commit
09cacf6
1 Parent(s): 9965471

First version of model to do end-to-end temporal IE from THYME2. includes all relation types, events with DTR, and timexes with time classes.

Browse files
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
+ "encoder_config": {
6
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.22.2",
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 28903
83
+ },
84
+ "encoder_name": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
85
+ "finetuning_task": [
86
+ "timex",
87
+ "event",
88
+ "tlinkx"
89
+ ],
90
+ "hidden_dropout_prob": 0.1,
91
+ "hidden_size": 768,
92
+ "hier_head_config": null,
93
+ "layer": 10,
94
+ "model_type": "cnlpt",
95
+ "num_labels_list": [
96
+ 9,
97
+ 15,
98
+ 8
99
+ ],
100
+ "num_rel_attention_heads": 256,
101
+ "rel_attention_head_dims": 64,
102
+ "relations": [
103
+ false,
104
+ false,
105
+ true
106
+ ],
107
+ "tagger": [
108
+ true,
109
+ true,
110
+ false
111
+ ],
112
+ "tokens": false,
113
+ "torch_dtype": "float32",
114
+ "transformers_version": "4.22.2",
115
+ "use_prior_tasks": false,
116
+ "vocab_size": 28903
117
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daf34b2db77c26043e923b13458d97555e55d3afcd3ffde55ffef3683555825
3
+ size 538633829
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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "additional_special_tokens": [
4
+ "<e>",
5
+ "</e>",
6
+ "<a1>",
7
+ "</a1>",
8
+ "<a2>",
9
+ "</a2>",
10
+ "<cr>",
11
+ "<neg>"
12
+ ],
13
+ "cls_token": "[CLS]",
14
+ "do_basic_tokenize": true,
15
+ "do_lower_case": true,
16
+ "mask_token": "[MASK]",
17
+ "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
18
+ "never_split": null,
19
+ "pad_token": "[PAD]",
20
+ "sep_token": "[SEP]",
21
+ "special_tokens_map_file": null,
22
+ "strip_accents": null,
23
+ "tokenize_chinese_chars": true,
24
+ "tokenizer_class": "BertTokenizer",
25
+ "unk_token": "[UNK]"
26
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff