added the tokenizer
Browse files- README.md +16 -16
- tokenizer.json +0 -0
- tokenizer_config.json +46 -7
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,4 +1,20 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
model-index:
|
| 3 |
- name: Sociovestix/lenu_SE
|
| 4 |
results:
|
|
@@ -20,22 +36,6 @@ model-index:
|
|
| 20 |
name: f1 macro
|
| 21 |
args:
|
| 22 |
average: macro
|
| 23 |
-
widget:
|
| 24 |
-
- text: "Cathill Industries AB"
|
| 25 |
-
- text: "Gunnar Lingås Stiftelse"
|
| 26 |
-
- text: "Föreningen Hjärtlung Alvesta"
|
| 27 |
-
- text: "Picsous Fastigheter Norrtälje KB"
|
| 28 |
-
- text: "Vreta klosters församling"
|
| 29 |
-
- text: "Alvengren & Söner Handelsbolag"
|
| 30 |
-
- text: "Svenska Förläggareföreningen ek. för."
|
| 31 |
-
- text: "Länsförsäkringar Jämtland"
|
| 32 |
-
- text: "Hälsinglands Sparbank"
|
| 33 |
-
- text: "Dalarnas Försäkringsbolag"
|
| 34 |
-
- text: "Södra Dalarnas Sparbank AB"
|
| 35 |
-
- text: "Bostadsrättsföreningen Bryggan"
|
| 36 |
-
- text: "Garantimyndigheten, Riksgäldskontoret"
|
| 37 |
-
- text: "Edsbergs Häradsallmänning"
|
| 38 |
-
- text: "Bostadsrättsföreningen Vik 7"
|
| 39 |
---
|
| 40 |
|
| 41 |
# LENU - Legal Entity Name Understanding for Sweden
|
|
|
|
| 1 |
---
|
| 2 |
+
widget:
|
| 3 |
+
- text: Cathill Industries AB
|
| 4 |
+
- text: Gunnar Lingås Stiftelse
|
| 5 |
+
- text: Föreningen Hjärtlung Alvesta
|
| 6 |
+
- text: Picsous Fastigheter Norrtälje KB
|
| 7 |
+
- text: Vreta klosters församling
|
| 8 |
+
- text: Alvengren & Söner Handelsbolag
|
| 9 |
+
- text: Svenska Förläggareföreningen ek. för.
|
| 10 |
+
- text: Länsförsäkringar Jämtland
|
| 11 |
+
- text: Hälsinglands Sparbank
|
| 12 |
+
- text: Dalarnas Försäkringsbolag
|
| 13 |
+
- text: Södra Dalarnas Sparbank AB
|
| 14 |
+
- text: Bostadsrättsföreningen Bryggan
|
| 15 |
+
- text: Garantimyndigheten, Riksgäldskontoret
|
| 16 |
+
- text: Edsbergs Häradsallmänning
|
| 17 |
+
- text: Bostadsrättsföreningen Vik 7
|
| 18 |
model-index:
|
| 19 |
- name: Sociovestix/lenu_SE
|
| 20 |
results:
|
|
|
|
| 36 |
name: f1 macro
|
| 37 |
args:
|
| 38 |
average: macro
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
---
|
| 40 |
|
| 41 |
# LENU - Legal Entity Name Understanding for Sweden
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,15 +1,54 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
-
"
|
| 4 |
-
"do_lower_case": false,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
-
"model_max_length":
|
| 7 |
-
"name_or_path": "KB/bert-base-swedish-cased",
|
| 8 |
-
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
-
"
|
| 12 |
-
"strip_accents": false,
|
| 13 |
"tokenize_chinese_chars": true,
|
| 14 |
"tokenizer_class": "BertTokenizer",
|
| 15 |
"unk_token": "[UNK]"
|
|
|
|
| 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",
|
| 54 |
"unk_token": "[UNK]"
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|