added the tokenizer
Browse files- README.md +10 -10
- tokenizer_config.json +43 -2
README.md
CHANGED
@@ -1,4 +1,14 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
model-index:
|
3 |
- name: Sociovestix/lenu_ES
|
4 |
results:
|
@@ -20,16 +30,6 @@ model-index:
|
|
20 |
name: f1 macro
|
21 |
args:
|
22 |
average: macro
|
23 |
-
widget:
|
24 |
-
- text: "HIERBAS TUNEL SL"
|
25 |
-
- text: "BIOQUIM SA"
|
26 |
-
- text: "PATRIMONI MUNICIPAL DE TERRASSA S.L.(SOCIEDAD UNIPERSONAL)"
|
27 |
-
- text: "BBVA CREDITO EUROPA, FI"
|
28 |
-
- text: "HERENCIA YACENTE DE DOÑA M TERESA PENINA RIBAS"
|
29 |
-
- text: "FUNDACIO CATALANA PER A LA RECERCA I LA INNOVACIO"
|
30 |
-
- text: "KUTXABANK RENTA FIJA FP"
|
31 |
-
- text: "DAMAS DE LA ASUNCION"
|
32 |
-
- text: "CUDOS I SLP"
|
33 |
---
|
34 |
|
35 |
# LENU - Legal Entity Name Understanding for Spain
|
|
|
1 |
---
|
2 |
+
widget:
|
3 |
+
- text: HIERBAS TUNEL SL
|
4 |
+
- text: BIOQUIM SA
|
5 |
+
- text: PATRIMONI MUNICIPAL DE TERRASSA S.L.(SOCIEDAD UNIPERSONAL)
|
6 |
+
- text: BBVA CREDITO EUROPA, FI
|
7 |
+
- text: HERENCIA YACENTE DE DOÑA M TERESA PENINA RIBAS
|
8 |
+
- text: FUNDACIO CATALANA PER A LA RECERCA I LA INNOVACIO
|
9 |
+
- text: KUTXABANK RENTA FIJA FP
|
10 |
+
- text: DAMAS DE LA ASUNCION
|
11 |
+
- text: CUDOS I SLP
|
12 |
model-index:
|
13 |
- name: Sociovestix/lenu_ES
|
14 |
results:
|
|
|
30 |
name: f1 macro
|
31 |
args:
|
32 |
average: macro
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
---
|
34 |
|
35 |
# LENU - Legal Entity Name Understanding for Spain
|
tokenizer_config.json
CHANGED
@@ -1,12 +1,53 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_lower_case": true,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
-
"name_or_path": "bert-base-multilingual-uncased",
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
-
"special_tokens_map_file": null,
|
10 |
"strip_accents": null,
|
11 |
"tokenize_chinese_chars": true,
|
12 |
"tokenizer_class": "BertTokenizer",
|
|
|
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": true,
|
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": "BertTokenizer",
|