Instructions to use distilbert/distilbert-base-uncased-distilled-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use distilbert/distilbert-base-uncased-distilled-squad 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="distilbert/distilbert-base-uncased-distilled-squad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("distilbert/distilbert-base-uncased-distilled-squad") model = AutoModelForQuestionAnswering.from_pretrained("distilbert/distilbert-base-uncased-distilled-squad", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from distilbert/distilbert-base-uncased-distilled-squad: direct link, hf CLI and curl.
- Browser
- Download file 28 Bytes
-
https://huggingface.co/distilbert/distilbert-base-uncased-distilled-squad/resolve/refs%2Fpr%2F2/tokenizer_config.json
- Command line
-
hf download hf://distilbert/distilbert-base-uncased-distilled-squad@refs/pr/2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/distilbert/distilbert-base-uncased-distilled-squad/resolve/refs%2Fpr%2F2/tokenizer_config.json
28 Bytes
| { | |
| "do_lower_case": true | |
| } | |