Instructions to use Marzu39/bert-base-turkish-128k-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Marzu39/bert-base-turkish-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/bert-base-turkish-128k-qa")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Marzu39/bert-base-turkish-128k-qa") model = AutoModelForQuestionAnswering.from_pretrained("Marzu39/bert-base-turkish-128k-qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download nbest_predictions_test.json from Marzu39/bert-base-turkish-128k-qa: direct link, hf CLI and curl.
- Browser
- Download file 560 kB
-
https://huggingface.co/Marzu39/bert-base-turkish-128k-qa/resolve/main/nbest_predictions_test.json
- Command line
-
hf download hf://Marzu39/bert-base-turkish-128k-qa/nbest_predictions_test.json
-
curl -L -o nbest_predictions_test.json https://huggingface.co/Marzu39/bert-base-turkish-128k-qa/resolve/main/nbest_predictions_test.json
560 kB
File too large to display, you can check the raw version instead.