botryan96 commited on
Commit
ab36e5e
1 Parent(s): b8f755c

1st Trial Version of GeoBERT

Browse files
Files changed (6) hide show
  1. config.json +46 -0
  2. special_tokens_map.json +7 -0
  3. tf_model.h5 +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +15 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-GeoTime",
14
+ "2": "I-GeoTime",
15
+ "3": "B-GeoLoc",
16
+ "4": "I-GeoLoc",
17
+ "5": "B-GeoMeth",
18
+ "6": "I-GeoMeth",
19
+ "7": "B-GeoPetro",
20
+ "8": "I-GeoPetro"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-GeoLoc": "3",
26
+ "B-GeoMeth": "5",
27
+ "B-GeoPetro": "7",
28
+ "B-GeoTime": "1",
29
+ "I-GeoLoc": "4",
30
+ "I-GeoMeth": "6",
31
+ "I-GeoPetro": "8",
32
+ "I-GeoTime": "2",
33
+ "O": "0"
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "transformers_version": "4.22.1",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 31090
46
+ }
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
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631320bbcb8fae6a88b5d6e3d75d706eef659e2f8b1ff5b3aefd8cd88fb68c76
3
+ size 437612588
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
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "allenai/scibert_scivocab_uncased",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff