Mike commited on
Commit
ac414c8
1 Parent(s): 87bcc59

add knowledge extraciton model

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jjzha/jobbert-base-cased",
3
+ "adapters": {
4
+ "adapters": {},
5
+ "config_map": {},
6
+ "fusion_config_map": {},
7
+ "fusions": {}
8
+ },
9
+ "architectures": [
10
+ "BertForTokenClassification"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "classifier_dropout": null,
14
+ "gradient_checkpointing": false,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "B",
20
+ "1": "I",
21
+ "2": "O"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B": 0,
27
+ "I": 1,
28
+ "O": 2
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "output_hidden_states": true,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.26.1",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 28996
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbdc7e9654dcde1d789ff9deaf35fa676c749c6b88fc4197020947166522dc5
3
+ size 430984049
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "jjzha/jobbert-base-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff