SDFT - Pytorch (wip)
Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT
Citations
@misc{shenfeld2026selfdistillationenablescontinuallearning,
title = {Self-Distillation Enables Continual Learning},
author = {Idan Shenfeld and Mehul Damani and Jonas Hübotter and Pulkit Agrawal},
year = {2026},
eprint = {2601.19897},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2601.19897},
}
1 maintainer
Metadata
1 maintainer
Release files for sdft-pytorch 0.0.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| sdft_pytorch-0.0.10.tar.gz | 6.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sdft_pytorch-0.0.10-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 11.6 kB
Release files / sdft_pytorch-0.0.10.tar.gz
| Download URL | sdft_pytorch-0.0.10.tar.gz |
|---|---|
| Size | 6.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
183754d512828832ab259514072d575ca3a149ea934d981718a6b5ea7596b353
|
|
BLAKE2b-256 checksum How to use checksums |
0d2139308ccd88109a36442188a59982a5c0b24191f4e8f467916cc430b76f67
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.17
|
Release files / sdft_pytorch-0.0.10-py3-none-any.whl
| Download URL | sdft_pytorch-0.0.10-py3-none-any.whl |
|---|---|
| Size | 5.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
366fbdc23a08e92f3c04e7882e6a8482a6c9b06e5a556e2619350f928cac21ca
|
|
BLAKE2b-256 checksum How to use checksums |
779dbd1a38e4c07733b72d57be7b6652005188eef7b276037c3337138f2b2cc7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.17
|
