datascience-service
commited on
Commit
•
46c9192
1
Parent(s):
8edb4f6
Upload 7 files
Browse files- config.json +65 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-nom",
|
15 |
+
"10": "I-date_naissance",
|
16 |
+
"11": "B-nom_d_usage",
|
17 |
+
"12": "I-nom_d_usage",
|
18 |
+
"13": "B-adresse",
|
19 |
+
"14": "I-adresse",
|
20 |
+
"2": "I-nom",
|
21 |
+
"3": "B-prenom",
|
22 |
+
"4": "I-prenom",
|
23 |
+
"5": "B-sexe",
|
24 |
+
"6": "I-sexe",
|
25 |
+
"7": "B-lieu_naissance",
|
26 |
+
"8": "I-lieu_naissance",
|
27 |
+
"9": "B-date_naissance"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"B-adresse": "13",
|
33 |
+
"B-date_naissance": "9",
|
34 |
+
"B-lieu_naissance": "7",
|
35 |
+
"B-nom": "1",
|
36 |
+
"B-nom_d_usage": "11",
|
37 |
+
"B-prenom": "3",
|
38 |
+
"B-sexe": "5",
|
39 |
+
"I-adresse": "14",
|
40 |
+
"I-date_naissance": "10",
|
41 |
+
"I-lieu_naissance": "8",
|
42 |
+
"I-nom": "2",
|
43 |
+
"I-nom_d_usage": "12",
|
44 |
+
"I-prenom": "4",
|
45 |
+
"I-sexe": "6",
|
46 |
+
"O": "0"
|
47 |
+
},
|
48 |
+
"layer_norm_eps": 1e-12,
|
49 |
+
"max_position_embeddings": 512,
|
50 |
+
"model_type": "bert",
|
51 |
+
"num_attention_heads": 12,
|
52 |
+
"num_hidden_layers": 12,
|
53 |
+
"pad_token_id": 0,
|
54 |
+
"pooler_fc_size": 768,
|
55 |
+
"pooler_num_attention_heads": 12,
|
56 |
+
"pooler_num_fc_layers": 3,
|
57 |
+
"pooler_size_per_head": 128,
|
58 |
+
"pooler_type": "first_token_transform",
|
59 |
+
"position_embedding_type": "absolute",
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.41.2",
|
62 |
+
"type_vocab_size": 2,
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 119547
|
65 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f61ed114c82c1f2fc722c8843ff22801bec8e9f61f8a9ed2eb4c0c6975d1c75d
|
3 |
+
size 709120892
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 512,
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_to_multiple_of": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"pad_token_type_id": 0,
|
53 |
+
"padding_side": "right",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "BertTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "[UNK]"
|
62 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90eadeb63d5aea503358f55c28f7941c9f503d5204cffef71ec3938418ac1ee3
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|