Create README.md

README.md

@@ -0,0 +1,36 @@
+---
+language: id
+tags:
+  - roberta-base-indonesia
+license: mit
+datasets:
+  - oscar
+widget:
+  - text: "Budi adalah anak yang pintar karena ia suka <mask>."
+---
+
+## Indonesian RoBERTa Base
+## How to Use
+
+### As Masked Language Model
+```python
+from transformers import pipeline
+pretrained_name = "akahana/roberta-base-indonesia"
+fill_mask = pipeline(
+    "fill-mask",
+    model=pretrained_name,
+    tokenizer=pretrained_name
+)
+fill_mask("Budi adalah anak yang pintar karena ia suka <mask>.")
+```
+
+### Feature Extraction in PyTorch
+```python
+from transformers import RobertaModel, RobertaTokenizerFast
+pretrained_name = "akahana/roberta-base-indonesia"
+model = RobertaModel.from_pretrained(pretrained_name)
+tokenizer = RobertaTokenizerFast.from_pretrained(pretrained_name)
+prompt = "Budi adalah anak yang pintar karena ia suka belajar."
+encoded_input = tokenizer(prompt, return_tensors='pt')
+output = model(**encoded_input)
+```