Instructions to use nmysore/attention-manifolds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nmysore/attention-manifolds with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nmysore/attention-manifolds", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trained/layer_024.pt from nmysore/attention-manifolds: direct link, hf CLI and curl.
- Browser
- Download file 298 kB
-
https://huggingface.co/nmysore/attention-manifolds/resolve/main/trained/layer_024.pt
- Command line
-
hf download hf://nmysore/attention-manifolds/trained/layer_024.pt
-
curl -L -o layer_024.pt https://huggingface.co/nmysore/attention-manifolds/resolve/main/trained/layer_024.pt
298 kB
- Xet hash:
- 28f265c4b71d8758a2c9a0b41860676cfe41325e8fa3b66f4d891cf9bff4259b
- Size of remote file:
- 298 kB
- SHA256:
- 95e720e11236eb09717b822fdc27992d213aa08e561dfdce809ce43cc0048b8f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.