Instructions to use abdoelsayed/AraDPR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdoelsayed/AraDPR 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="abdoelsayed/AraDPR")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("abdoelsayed/AraDPR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Preprocessing steps required to used AraDPR
#2
by NajlaSS - opened
What are the preprocessing steps need to be performed before using AraDPR? such as, normalization, tokenization ... etc
or it directly use the Arabic text without any need for preprocessing steps?
we used arabert tokenizer
we didn't do any preprocessing steps