T5 Kazakh Qa

🚀 T5 Kazakh QA Model

A fine - tuned model for Kazakh question - answering tasks based on the google/mt5 - large architecture.

🚀 Quick Start

This model is designed to handle question - answering tasks in the Kazakh language. It's fine - tuned on a Kazakh version of the Stanford Question Answering Dataset (SQuAD).

✨ Features

• Based on the google/mt5 - large model.
• Fine - tuned on 30,000 samples of the Kazakh SQuAD dataset.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import T5Tokenizer, T5TokenizerFast
from transformers import T5ForConditionalGeneration
import sentencepiece

tokenizer = T5Tokenizer.from_pretrained("Kyrmasch/t5-kazakh-qa")
model = T5ForConditionalGeneration.from_pretrained("Kyrmasch/t5-kazakh-qa")

context = "Қазақстан Еуразия құрлығының орталығында орналасқан және аумақтың көлемі бойынша (жер шарының бетінде 2%) әлемде тоғызыншы орынға ие. Қазақстан аумағы бүкіл Батыс Еуропадан үлкен."
question = "Қазақстан жер көлемі жөнінен дүние жүзінде нешінші орында?"

encoded = tokenizer.encode_plus(context, question, max_length=128, pad_to_max_length=True, truncation=True, return_tensors="pt")
input_ids = encoded["input_ids"].to('cpu')
attention_mask = encoded["attention_mask"].to('cpu')
output = model.generate(input_ids=input_ids, attention_mask=attention_mask, max_length=128)
answer = ''.join([tokenizer.decode(ids, skip_special_tokens=True) for ids in output])

📚 Documentation

Model Details

Model Description

This model is based on the google/mt5 - large model. The model was fine - tuned on a Kazakh language version of the Stanford Question Answering Dataset (SQuAD) using 30,000 samples.

📄 License

The model is licensed under the Apache 2.0 license.