Instructions to use VMware/bert-tiny-mrqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VMware/bert-tiny-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-tiny-mrqa")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("VMware/bert-tiny-mrqa") model = AutoModelForQuestionAnswering.from_pretrained("VMware/bert-tiny-mrqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from VMware/bert-tiny-mrqa: direct link, hf CLI and curl.
- Browser
- Download file 17.5 MB
-
https://huggingface.co/VMware/bert-tiny-mrqa/resolve/main/model.safetensors
- Command line
-
hf download hf://VMware/bert-tiny-mrqa/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/VMware/bert-tiny-mrqa/resolve/main/model.safetensors
17.5 MB
- Xet hash:
- 60fca14f5ec56be85487110c264cb47e1ce7d2aa64878617e81afc3d86b5c38f
- Size of remote file:
- 17.5 MB
- SHA256:
- f4d0e75437c331f0ad3cc94fcf186b51dea7195d36083f290025a5d06d499f87
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.