added the tokenizer
Browse files- README.md +19 -19
- tokenizer.json +0 -0
- tokenizer_config.json +44 -5
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,4 +1,23 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
model-index:
|
| 3 |
- name: Sociovestix/lenu_IE
|
| 4 |
results:
|
|
@@ -20,25 +39,6 @@ model-index:
|
|
| 20 |
name: f1 macro
|
| 21 |
args:
|
| 22 |
average: macro
|
| 23 |
-
widget:
|
| 24 |
-
- text: "CRH Group Services Ltd Share Participation Scheme"
|
| 25 |
-
- text: "SCF Ajoneuvohallinto IX Limited"
|
| 26 |
-
- text: "BSSF II Origination Designated Activity Company"
|
| 27 |
-
- text: "New Vision Strategies ICAV"
|
| 28 |
-
- text: "GPB EUROBOND FINANCE PUBLIC LIMITED COMPANY"
|
| 29 |
-
- text: "IPF MANAGEMENT UNLIMITED COMPANY"
|
| 30 |
-
- text: "Castlerea and District Credit Union Limited"
|
| 31 |
-
- text: "IRPF Fernbank Limited Partnership"
|
| 32 |
-
- text: "Disabled Drivers Association of Ireland"
|
| 33 |
-
- text: "The Pat Brophy Family Partnership"
|
| 34 |
-
- text: "PRIMA ICG SENIOR DEBT PARTNERS IRELAND DESIGNATED ACTIVITY COMPANY"
|
| 35 |
-
- text: "East Coast Catering (Ireland) Unlimited"
|
| 36 |
-
- text: "Marist Brothers In Ireland-Tallaght"
|
| 37 |
-
- text: "Forestay Capital II, ILP"
|
| 38 |
-
- text: "DONOVAN'S PHARMACY LIMITED"
|
| 39 |
-
- text: "AXIS Specialty Europe SE"
|
| 40 |
-
- text: "Ballycora Investments UC"
|
| 41 |
-
- text: "Lakeland Dairies Co-Operative Society Ltd"
|
| 42 |
---
|
| 43 |
|
| 44 |
# LENU - Legal Entity Name Understanding for Ireland
|
|
|
|
| 1 |
---
|
| 2 |
+
widget:
|
| 3 |
+
- text: CRH Group Services Ltd Share Participation Scheme
|
| 4 |
+
- text: SCF Ajoneuvohallinto IX Limited
|
| 5 |
+
- text: BSSF II Origination Designated Activity Company
|
| 6 |
+
- text: New Vision Strategies ICAV
|
| 7 |
+
- text: GPB EUROBOND FINANCE PUBLIC LIMITED COMPANY
|
| 8 |
+
- text: IPF MANAGEMENT UNLIMITED COMPANY
|
| 9 |
+
- text: Castlerea and District Credit Union Limited
|
| 10 |
+
- text: IRPF Fernbank Limited Partnership
|
| 11 |
+
- text: Disabled Drivers Association of Ireland
|
| 12 |
+
- text: The Pat Brophy Family Partnership
|
| 13 |
+
- text: PRIMA ICG SENIOR DEBT PARTNERS IRELAND DESIGNATED ACTIVITY COMPANY
|
| 14 |
+
- text: East Coast Catering (Ireland) Unlimited
|
| 15 |
+
- text: Marist Brothers In Ireland-Tallaght
|
| 16 |
+
- text: Forestay Capital II, ILP
|
| 17 |
+
- text: DONOVAN'S PHARMACY LIMITED
|
| 18 |
+
- text: AXIS Specialty Europe SE
|
| 19 |
+
- text: Ballycora Investments UC
|
| 20 |
+
- text: Lakeland Dairies Co-Operative Society Ltd
|
| 21 |
model-index:
|
| 22 |
- name: Sociovestix/lenu_IE
|
| 23 |
results:
|
|
|
|
| 39 |
name: f1 macro
|
| 40 |
args:
|
| 41 |
average: macro
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
---
|
| 43 |
|
| 44 |
# LENU - Legal Entity Name Understanding for Ireland
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,14 +1,53 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
-
"do_basic_tokenize": true,
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
-
"model_max_length":
|
| 7 |
-
"name_or_path": "yiyanghkust/finbert-pretrain",
|
| 8 |
-
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
-
"special_tokens_map_file": null,
|
| 12 |
"strip_accents": null,
|
| 13 |
"tokenize_chinese_chars": true,
|
| 14 |
"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",
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|