How to use deepset/roberta-base-squad2 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="deepset/roberta-base-squad2")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2") model = AutoModelForQuestionAnswering.from_pretrained("deepset/roberta-base-squad2", device_map="auto")
https://huggingface.co/deepset/roberta-base-squad2/resolve/main/vocab.json
hf download hf://deepset/roberta-base-squad2/vocab.json
curl -L -o vocab.json https://huggingface.co/deepset/roberta-base-squad2/resolve/main/vocab.json
