alexbrandsen commited on
Commit
9f04c00
1 Parent(s): 2da877f
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ArcheoBERTje-NER
2
+ A Dutch BERT model for Named Entity Recognition in the Archaeology domain
3
+
4
+ This is the [ArcheoBERTje](https://huggingface.co/alexbrandsen/ArcheoBERTje) model finetuned for NER, targeting the following entities:
5
+
6
+ - Time periods
7
+ - Places
8
+ - Artefacts
9
+ - Contexts
10
+ - Materials
11
+ - Species
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "gradient_checkpointing": false,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "B-ART",
12
+ "1": "I-ART",
13
+ "2": "B-MAT",
14
+ "3": "I-MAT",
15
+ "4": "B-PER",
16
+ "5": "I-PER",
17
+ "6": "B-SPE",
18
+ "7": "I-SPE",
19
+ "8": "B-CON",
20
+ "9": "I-CON",
21
+ "10": "B-LOC",
22
+ "11": "I-LOC",
23
+ "12": "O"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "B-ART": 0,
29
+ "B-CON": 8,
30
+ "B-LOC": 10,
31
+ "B-MAT": 2,
32
+ "B-PER": 4,
33
+ "B-SPE": 6,
34
+ "I-ART": 1,
35
+ "I-CON": 9,
36
+ "I-LOC": 11,
37
+ "I-MAT": 3,
38
+ "I-PER": 5,
39
+ "I-SPE": 7,
40
+ "O": 12
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "max_position_embeddings": 512,
44
+ "model_type": "bert",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 3,
48
+ "type_vocab_size": 2,
49
+ "vocab_size": 30000
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38dfb162155203dc11438f20c0c7becd078083eea798aa49c9c53e6dbe6d01a
3
+ size 436413243
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": "/data/brandsena/BERT_models/bertje_archaeo/special_tokens_map.json", "full_tokenizer_file": null}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3260cdc19d414f6724c3417517c1981e078e066af55923f81668b932c8a096ce
3
+ size 1197
vocab.txt ADDED
The diff for this file is too large to render. See raw diff