Question Answering
Transformers
PyTorch
Safetensors
Icelandic
English
multilingual
xlm-roberta
icelandic
qa
Instructions to use vesteinn/XLMr-ENIS-QA-IsQ-EnA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vesteinn/XLMr-ENIS-QA-IsQ-EnA 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="vesteinn/XLMr-ENIS-QA-IsQ-EnA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("vesteinn/XLMr-ENIS-QA-IsQ-EnA") model = AutoModelForQuestionAnswering.from_pretrained("vesteinn/XLMr-ENIS-QA-IsQ-EnA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
XLMr-ENIS-QA-IsQ-EnA
Model description
This is an Icelandic reading comprehension Q&A model.
Intended uses & limitations
This model is part of my MSc thesis about Q&A for Icelandic.
How to use
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("vesteinn/IceBERT-QA")
model = AutoModelForQuestionAnswering.from_pretrained("vesteinn/IceBERT-QA")
Limitations and bias
Training data
Translated English datasets were used along with the Natural Questions in Icelandic dataset.
Training procedure
Eval results
BibTeX entry and citation info
- Downloads last month
- 14