|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- tr |
|
|
library_name: transformers |
|
|
pipeline_tag: feature-extraction |
|
|
--- |
|
|
|
|
|
# TyRoberta Model |
|
|
|
|
|
This repository provides a pretrained Roberta model for Turkish by Trendyol, named TyRoberta. The model is useful for various natural language understanding tasks, such as text classification, named entity recognition, and more. |
|
|
|
|
|
|
|
|
## How to use |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, RobertaModel |
|
|
|
|
|
# Load the tokenizer and model |
|
|
tokenizer = AutoTokenizer.from_pretrained("Trendyol/tyroberta") |
|
|
model = RobertaModel.from_pretrained("Trendyol/tyroberta") |
|
|
|
|
|
# Define a sample text |
|
|
text = "Filenin Sultanları ilk maçını 29 Temmuz'da Hollanda'ya karşı oynayacak." |
|
|
|
|
|
# Tokenize and encode the input text |
|
|
encoded_input = tokenizer(text, return_tensors='pt') |
|
|
|
|
|
# Get the model's output |
|
|
output = model(**encoded_input) |
|
|
|
|
|
print(output) |
|
|
|
|
|
``` |
