Ukrainian Qa

🚀 Ukrainian-QA

This model is a fine - tuned version for question - answering tasks in Ukrainian, leveraging pre - trained models and specific datasets to provide accurate answers.

🚀 Quick Start

This model is a fine - tuned version of [ukr - models/xlm - roberta - base - uk](https://huggingface.co/ukr - models/xlm - roberta - base - uk) on the [UA - SQuAD](https://github.com/fido - ai/ua - datasets/tree/main/ua_datasets/src/question_answering) dataset.

Link to training scripts - [https://github.com/robinhad/ukrainian - qa](https://github.com/robinhad/ukrainian - qa)
It achieves the following results on the evaluation set:

• Loss: 1.4778

✨ Features

This model is a fine - tuned version of a pre - trained model, which can be used for question - answering tasks in Ukrainian. It has been trained on a specific dataset and can provide answers based on given contexts.

💻 Usage Examples

Basic Usage

from transformers import pipeline, AutoTokenizer, AutoModelForQuestionAnswering
model_name = "robinhad/ukrainian-qa"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForQuestionAnswering.from_pretrained(model_name)

qa_model = pipeline("question-answering", model=model.to("cpu"), tokenizer=tokenizer)
question = "Де ти живеш?"
context = "Мене звати Сара і я живу у Лондоні"
qa_model(question = question, context = context)

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0
• Datasets 2.2.2
• Tokenizers 0.12.1

📄 License

This model is released under the MIT license.