Downloads · 30 days
113
7% of all-time downloads
tiny-roberta-indonesia
akahana/tiny-roberta-indonesia
tiny-roberta-indonesia is a feature extraction model from akahana. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as mit.
All-time downloads
1.6K
Public
Parameters
828K
10 MB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.h53.3 MB · 32%
Parameter types
How the weights are stored.
F32828K · 100%
Try a prompt
Datasets
Model card
From the Hugging Face model README
Indonesian tiny-RoBERTa
How to Use
As Masked Language Model
from transformers import pipeline
pretrained_name = "akahana/tiny-roberta-indonesia"
fill_mask = pipeline(
"fill-mask",
model=pretrained_name,
tokenizer=pretrained_name
)
fill_mask("ikiryo adalah <mask> hantu dalam mitologi jepang.")
Feature Extraction in PyTorch
from transformers import RobertaModel, RobertaTokenizerFast
pretrained_name = "akahana/tiny-roberta-indonesia"
model = RobertaModel.from_pretrained(pretrained_name)
tokenizer = RobertaTokenizerFast.from_pretrained(pretrained_name)
prompt = "ikiryo adalah <mask> hantu dalam mitologi jepang."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)
- Task
- Feature Extraction
- Library
- transformers
- Type
- roberta
- License
- mit
- Languages
- id
- Created
- Mar 2, 2022
- Updated
- Sep 19, 2023