Instructions to use dewdev/question_and_answer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dewdev/question_and_answer 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="dewdev/question_and_answer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("dewdev/question_and_answer") model = AutoModelForQuestionAnswering.from_pretrained("dewdev/question_and_answer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from dewdev/question_and_answer: direct link, hf CLI and curl.
- Browser
- Download file 669 kB
-
https://huggingface.co/dewdev/question_and_answer/resolve/main/tokenizer.json
- Command line
-
hf download hf://dewdev/question_and_answer/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/dewdev/question_and_answer/resolve/main/tokenizer.json
669 kB
File too large to display, you can check the raw version instead.