Instructions to use RedHatAI/oBERT-3-downstream-pruned-block4-80-QAT-squadv1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/oBERT-3-downstream-pruned-block4-80-QAT-squadv1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RedHatAI/oBERT-3-downstream-pruned-block4-80-QAT-squadv1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 554854286d48bfddae61f073f7792b719601f12ab7ca539060efeae49f507300
- Size of remote file:
- 181 MB
- SHA256:
- 09a7005ccc2870b0a2fea1c9a9315d506eb960542c01373c97c82f0e0bb913df
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.