Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,16 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
SinBerto is a small language model trained on a small news corpus. SinBerto is trained on Sinhala Language which is a low resource language compared to other languages.
|
| 4 |
|
| 5 |
-
Model Specifications.
|
| 6 |
|
| 7 |
vocab_size=52_000,
|
| 8 |
max_position_embeddings=514,
|
|
@@ -11,10 +19,16 @@ num_hidden_layers=6,
|
|
| 11 |
type_vocab_size=1
|
| 12 |
|
| 13 |
|
| 14 |
-
How to from the Transformers Library
|
| 15 |
|
| 16 |
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
| 17 |
|
| 18 |
tokenizer = AutoTokenizer.from_pretrained("Kalindu/SinBerto")
|
| 19 |
|
| 20 |
-
model = AutoModelForMaskedLM.from_pretrained("Kalindu/SinBerto")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: si
|
| 3 |
+
tags:
|
| 4 |
+
- SinhalaBERTo
|
| 5 |
+
- Sinhala
|
| 6 |
+
- roberta
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
### Overview
|
| 10 |
|
| 11 |
SinBerto is a small language model trained on a small news corpus. SinBerto is trained on Sinhala Language which is a low resource language compared to other languages.
|
| 12 |
|
| 13 |
+
### Model Specifications.
|
| 14 |
|
| 15 |
vocab_size=52_000,
|
| 16 |
max_position_embeddings=514,
|
|
|
|
| 19 |
type_vocab_size=1
|
| 20 |
|
| 21 |
|
| 22 |
+
### How to from the Transformers Library
|
| 23 |
|
| 24 |
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
| 25 |
|
| 26 |
tokenizer = AutoTokenizer.from_pretrained("Kalindu/SinBerto")
|
| 27 |
|
| 28 |
+
model = AutoModelForMaskedLM.from_pretrained("Kalindu/SinBerto")
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
### OR Clone the model repo
|
| 32 |
+
|
| 33 |
+
git lfs install
|
| 34 |
+
git clone https://huggingface.co/Kalindu/SinBerto
|