mcollardanuy commited on
Commit
f320835
1 Parent(s): 00d9b48

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "khosseini/bert_1760_1900",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-BUILDING",
15
+ "1": "B-FICTION",
16
+ "2": "B-LOC",
17
+ "3": "B-OTHER",
18
+ "4": "B-STREET",
19
+ "5": "I-BUILDING",
20
+ "6": "I-LOC",
21
+ "7": "I-STREET",
22
+ "8": "O"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-BUILDING": 0,
28
+ "B-FICTION": 1,
29
+ "B-LOC": 2,
30
+ "B-OTHER": 3,
31
+ "B-STREET": 4,
32
+ "I-BUILDING": 5,
33
+ "I-LOC": 6,
34
+ "I-STREET": 7,
35
+ "O": 8
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "output_past": true,
43
+ "pad_token_id": 0,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.29.2",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b52c97de8d86ff801dd85bed53b171793768e222a266bf81b26535e2289549a9
3
+ size 435663597
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
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124891a293c78501fea4c9eef40fa38eb14a1d1f0beb529d9fde726945b7c2d3
3
+ size 3899
vocab.txt ADDED
The diff for this file is too large to render. See raw diff