Instructions to use huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingface/prunebert-base-uncased-6-finepruned-w-distil-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="huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad") model = AutoModelForQuestionAnswering.from_pretrained("huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad: direct link, hf CLI and curl.
- Browser
- Download file 438 MB
-
https://huggingface.co/huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad/resolve/d7618f051b277b1a8f74cac04242d173de60c176/pytorch_model.bin
- Command line
-
hf download hf://huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad@d7618f051b277b1a8f74cac04242d173de60c176/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/huggingface/prunebert-base-uncased-6-finepruned-w-distil-squad/resolve/d7618f051b277b1a8f74cac04242d173de60c176/pytorch_model.bin
438 MB
- Xet hash:
- 304679a2ac9706dc99c2a3dd256e398288b2b4b64f61e17b164287a63f7ad0f4
- Size of remote file:
- 438 MB
- SHA256:
- 351eba4bea36fa3d9b494ed920070c263083827ca76eeb4e4b12c51c17a8e6eb
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.