Instructions to use VMware/bert-base-mrqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VMware/bert-base-mrqa 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="VMware/bert-base-mrqa")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("VMware/bert-base-mrqa") model = AutoModelForQuestionAnswering.from_pretrained("VMware/bert-base-mrqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from VMware/bert-base-mrqa: direct link, hf CLI and curl.
- Browser
- Download file 436 MB
-
https://huggingface.co/VMware/bert-base-mrqa/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://VMware/bert-base-mrqa/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/VMware/bert-base-mrqa/resolve/main/pytorch_model.bin
436 MB
- Xet hash:
- 1743690ed5cb421e8df3fb38dff5f2bd84556225aeb6b12ff5b3514d211199ea
- Size of remote file:
- 436 MB
- SHA256:
- 9b442a079d88b5c02cea285bc50469d13bfdb1d0cfa39a7e33c1301ee8319357
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.