Instructions to use Marzu39/bertturk-Cased-128k-QA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Marzu39/bertturk-Cased-128k-QA with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Marzu39/bertturk-Cased-128k-QA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Marzu39/bertturk-Cased-128k-QA") model = AutoModelForQuestionAnswering.from_pretrained("Marzu39/bertturk-Cased-128k-QA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Turkish SQuAD Model: Question Answering
I fine-tuned Turkish-Bert-Model for Question-Answering problem with THQuAD;
BERTürk-Cased128k: https://huggingface.co/dbmdz/bert-base-turkish-128k-cased
THQuAD Dataset: https://github.com/okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset
- Downloads last month
- 6