Ransaka commited on
Commit
75ee7b9
·
1 Parent(s): c932e51

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -1,26 +1,26 @@
1
  ---
2
  tags:
3
- - generated_from_trainer
4
  model-index:
5
- - name: Sinhala-BERT
6
  results: []
7
  widget:
8
  - text: "අපි තමයි [MASK] කරේ."
9
- - text: "මට හෙට එන්න වෙන්නේ [MASK]"
10
  - text: "අපි ගෙදර [MASK]."
11
- - text: "සිංහල සහ [MASK] අලුත් අවුරුද්ද "
 
 
 
12
  ---
13
 
14
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
- should probably proofread and complete it, then remove this comment. -->
16
-
17
  # SinhalaBERT
18
 
19
- This model is trained on various Sinhala corpus extracted from News and articles.
20
 
21
  ## Model description
22
 
23
- Trained on MLM tasks, Please use [MASK] token to indicate masked token.
24
 
25
  ### Training hyperparameters
26
 
@@ -38,4 +38,4 @@ The following hyperparameters were used during training:
38
  - Transformers 4.26.1
39
  - Pytorch 1.13.0
40
  - Datasets 2.1.0
41
- - Tokenizers 0.13.2
 
1
  ---
2
  tags:
3
+ - MLM
4
  model-index:
5
+ - name: SinhalaBERT
6
  results: []
7
  widget:
8
  - text: "අපි තමයි [MASK] කරේ."
9
+ - text: "මට හෙට එන්න වෙන්නේ [MASK]."
10
  - text: "අපි ගෙදර [MASK]."
11
+ - text: 'සිංහල සහ [MASK] අලුත් අවුරුද්ද.'
12
+ license: mit
13
+ language:
14
+ - si
15
  ---
16
 
 
 
 
17
  # SinhalaBERT
18
 
19
+ This model is trained on various Sinhala corpus extracted from News and articles.
20
 
21
  ## Model description
22
 
23
+ Trained on MLM tasks, Please use [MASK] token to indicate masked token. The model comprises a total of 85 million parameters
24
 
25
  ### Training hyperparameters
26
 
 
38
  - Transformers 4.26.1
39
  - Pytorch 1.13.0
40
  - Datasets 2.1.0
41
+ - Tokenizers 0.13.2