How to use ToluClassics/extractive_reader_nq 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="ToluClassics/extractive_reader_nq")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("ToluClassics/extractive_reader_nq") model = AutoModelForQuestionAnswering.from_pretrained("ToluClassics/extractive_reader_nq", device_map="auto")
https://huggingface.co/ToluClassics/extractive_reader_nq/resolve/refs%2Fpr%2F1/eval_null_odds.json
hf download hf://ToluClassics/extractive_reader_nq@refs/pr/1/eval_null_odds.json
curl -L -o eval_null_odds.json https://huggingface.co/ToluClassics/extractive_reader_nq/resolve/refs%2Fpr%2F1/eval_null_odds.json
