Instructions to use SparseCL/GTE-SparseCL-hotpotqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SparseCL/GTE-SparseCL-hotpotqa with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import NewModelForCL model = NewModelForCL.from_pretrained("SparseCL/GTE-SparseCL-hotpotqa", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-2772/optimizer.pt from SparseCL/GTE-SparseCL-hotpotqa: direct link, hf CLI and curl.
- Browser
- Download file 3.47 GB
-
https://huggingface.co/SparseCL/GTE-SparseCL-hotpotqa/resolve/main/checkpoint-2772/optimizer.pt
- Command line
-
hf download hf://SparseCL/GTE-SparseCL-hotpotqa/checkpoint-2772/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/SparseCL/GTE-SparseCL-hotpotqa/resolve/main/checkpoint-2772/optimizer.pt
3.47 GB
- Xet hash:
- 5522166c4d81b6a15688809cf3072e5e7d4c151b766f6a8080c936d861ba1fdb
- Size of remote file:
- 3.47 GB
- SHA256:
- 8fc8459de21242dc97b82414338c2a2e9027e067e90c6ffe25158f3df32502c4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.