Instructions to use t-tech/flex-sae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use t-tech/flex-sae with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("t-tech/flex-sae", version=1) - Notebooks
- Google Colab
- Kaggle
Download NOTICE from t-tech/flex-sae: direct link, hf CLI and curl.
- Browser
- Download file 796 Bytes
-
https://huggingface.co/t-tech/flex-sae/resolve/main/NOTICE
- Command line
-
hf download hf://t-tech/flex-sae/NOTICE
-
curl -L -o NOTICE https://huggingface.co/t-tech/flex-sae/resolve/main/NOTICE
796 Bytes
| Flex SAE Kernels | |
| Copyright (c) 2025 T-Tech | |
| This project is distributed under the Apache License, Version 2.0. The following | |
| third-party component is redistributed under its original terms: | |
| - Portions of `torch-ext/flex_sae/topk_kernels.py` are adapted from the Facebook | |
| Research project "memory" (https://github.com/facebookresearch/memory). | |
| That source is licensed under the Creative Commons Attribution-NonCommercial | |
| 4.0 International License (CC BY-NC 4.0). Any use of the adapted code must | |
| comply with the non-commercial requirements described at | |
| https://creativecommons.org/licenses/by-nc/4.0/. | |
| Where the Apache 2.0 license and CC BY-NC 4.0 differ, the more restrictive | |
| requirements apply to the adapted code. All other files are provided under the | |
| Apache License, Version 2.0. | |