Downloads · 30 days
47
5% of all-time downloads
sinhala-roberta-oscar
keshan/sinhala-roberta-oscar
sinhala-roberta-oscar is a fill-mask model from keshan. Use it when you need the model to fill a missing word. It is set up for transformers.
This is a slightly smaller model trained on OSCAR Sinhala dedup dataset. As Sinhala is one of those low resource languages, there are only a handful of models been trained. So, this would be a great place to start tra…
All-time downloads
1K
Public
Repo size
6.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 50%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jul 14, 2021
- SHA
- 655873a1
Try a prompt
Datasets
Model card
From the Hugging Face model README
Overview
This is a slightly smaller model trained on OSCAR Sinhala dedup dataset. As Sinhala is one of those low resource languages, there are only a handful of models been trained. So, this would be a great place to start training for more downstream tasks.
Model Specification
The model chosen for training is Roberta with the following specifications:
- vocab_size=50265
- max_position_embeddings=514
- num_attention_heads=12
- num_hidden_layers=12
- type_vocab_size=1
How to Use
You can use this model directly with a pipeline for masked language modeling:
from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
model = AutoModelWithLMHead.from_pretrained("keshan/sinhala-roberta-oscar")
tokenizer = AutoTokenizer.from_pretrained("keshan/sinhala-roberta-oscar")
fill_mask = pipeline('fill-mask', model=model, tokenizer=tokenizer)
fill_mask("මම ගෙදර <mask>.")
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Languages
- si
- Created
- Mar 2, 2022
- Updated
- Jul 14, 2021