dl-ru commited on
Commit
af83e18
1 Parent(s): 50cb47f

Initial version

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-Predicate",
16
+ "2": "B-Object",
17
+ "3": "B-Experiencer",
18
+ "4": "B-Cause",
19
+ "5": "B-Deliberative",
20
+ "6": "B-Causator",
21
+ "7": "B-ContrSubject",
22
+ "8": "B-Benefactive"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 600,
26
+ "label2id": {
27
+ "B-Benefactive": 8,
28
+ "B-Causator": 6,
29
+ "B-Cause": 4,
30
+ "B-ContrSubject": 7,
31
+ "B-Deliberative": 5,
32
+ "B-Experiencer": 3,
33
+ "B-Object": 2,
34
+ "B-Predicate": 1,
35
+ "O": 0
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 2048,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 3,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.28.1",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 83828
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d5d622327ba18f19f245a759afaf9fa01ea382a842a386bae4f296051b909d
3
+ size 116429721
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 2048,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ec9be7bb9b916e9543582095c1fc47800e8d257596cccab91bfb0890df81fe
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff