First version of model files.
Browse files- added_tokens.json +1 -0
- config.json +106 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"</a1>": 28898, "</a2>": 28900, "</e>": 28896, "<neg>": 28902, "<cr>": 28901, "<a1>": 28897, "<e>": 28895, "<a2>": 28899}
|
config.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": null,
|
24 |
+
"forced_bos_token_id": null,
|
25 |
+
"forced_eos_token_id": null,
|
26 |
+
"hidden_act": "gelu",
|
27 |
+
"hidden_dropout_prob": 0.1,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"is_decoder": false,
|
36 |
+
"is_encoder_decoder": false,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"length_penalty": 1.0,
|
43 |
+
"max_length": 20,
|
44 |
+
"max_position_embeddings": 512,
|
45 |
+
"min_length": 0,
|
46 |
+
"model_type": "bert",
|
47 |
+
"no_repeat_ngram_size": 0,
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_beam_groups": 1,
|
50 |
+
"num_beams": 1,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"num_return_sequences": 1,
|
53 |
+
"output_attentions": false,
|
54 |
+
"output_hidden_states": false,
|
55 |
+
"output_scores": false,
|
56 |
+
"pad_token_id": 0,
|
57 |
+
"position_embedding_type": "absolute",
|
58 |
+
"prefix": null,
|
59 |
+
"problem_type": null,
|
60 |
+
"pruned_heads": {},
|
61 |
+
"remove_invalid_values": false,
|
62 |
+
"repetition_penalty": 1.0,
|
63 |
+
"return_dict": true,
|
64 |
+
"return_dict_in_generate": false,
|
65 |
+
"sep_token_id": null,
|
66 |
+
"task_specific_params": null,
|
67 |
+
"temperature": 1.0,
|
68 |
+
"tie_encoder_decoder": false,
|
69 |
+
"tie_word_embeddings": true,
|
70 |
+
"tokenizer_class": null,
|
71 |
+
"top_k": 50,
|
72 |
+
"top_p": 1.0,
|
73 |
+
"torch_dtype": null,
|
74 |
+
"torchscript": false,
|
75 |
+
"transformers_version": "4.15.0",
|
76 |
+
"type_vocab_size": 2,
|
77 |
+
"use_bfloat16": false,
|
78 |
+
"use_cache": true,
|
79 |
+
"vocab_size": 28903
|
80 |
+
},
|
81 |
+
"encoder_name": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
|
82 |
+
"finetuning_task": [
|
83 |
+
"event"
|
84 |
+
],
|
85 |
+
"hidden_dropout_prob": 0.1,
|
86 |
+
"hidden_size": 768,
|
87 |
+
"layer": 12,
|
88 |
+
"model_type": "cnlpt",
|
89 |
+
"num_labels_list": [
|
90 |
+
9
|
91 |
+
],
|
92 |
+
"num_rel_attention_heads": 12,
|
93 |
+
"num_tokens": -1,
|
94 |
+
"rel_attention_head_dims": 64,
|
95 |
+
"relations": [
|
96 |
+
false
|
97 |
+
],
|
98 |
+
"tagger": [
|
99 |
+
true
|
100 |
+
],
|
101 |
+
"tokens": false,
|
102 |
+
"torch_dtype": "float32",
|
103 |
+
"transformers_version": "4.15.0",
|
104 |
+
"use_prior_tasks": false,
|
105 |
+
"vocab_size": 28903
|
106 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b0b88fc250ba56bcafd249ca875d4ea6d104f94ed3cac70c3d1a8bc06a598c8
|
3 |
+
size 435401957
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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, "add_prefix_space": true, "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"], "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|