oualidlamrini commited on
Commit
e57d9d0
1 Parent(s): 67d0cd5

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-nom",
14
+ "10": "I-date_naissance",
15
+ "11": "B-nom_d_usage",
16
+ "12": "I-nom_d_usage",
17
+ "13": "B-adresse",
18
+ "14": "I-adresse",
19
+ "2": "I-nom",
20
+ "3": "B-prenom",
21
+ "4": "I-prenom",
22
+ "5": "B-sexe",
23
+ "6": "I-sexe",
24
+ "7": "B-lieu_naissance",
25
+ "8": "I-lieu_naissance",
26
+ "9": "B-date_naissance"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "B-adresse": "13",
31
+ "B-date_naissance": "9",
32
+ "B-lieu_naissance": "7",
33
+ "B-nom": "1",
34
+ "B-nom_d_usage": "11",
35
+ "B-prenom": "3",
36
+ "B-sexe": "5",
37
+ "I-adresse": "14",
38
+ "I-date_naissance": "10",
39
+ "I-lieu_naissance": "8",
40
+ "I-nom": "2",
41
+ "I-nom_d_usage": "12",
42
+ "I-prenom": "4",
43
+ "I-sexe": "6",
44
+ "O": "0"
45
+ },
46
+ "max_position_embeddings": 512,
47
+ "model_type": "distilbert",
48
+ "n_heads": 12,
49
+ "n_layers": 6,
50
+ "output_past": true,
51
+ "pad_token_id": 0,
52
+ "qa_dropout": 0.1,
53
+ "seq_classif_dropout": 0.2,
54
+ "sinusoidal_pos_embds": false,
55
+ "tie_weights_": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.41.2",
58
+ "vocab_size": 119547
59
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b45af2cfcbb26a58d83589be899ebd9ed413724aed302077a367a30f3d93361
3
+ size 538994812
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d6212638b7c74b307a54fec3c8a06d8d2353412d93961c789209e78669cdaa
3
+ size 5048
vocab.txt ADDED
The diff for this file is too large to render. See raw diff