stack-attention-pytorch

Stack Attention (wip)

For following a line of research that augments attention with a differentiable stack, beginning with DuSell et al. at ETH Zurich

Citations

@misc{dusell2024stackattentionimprovingability,
    title   = {Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns}, 
    author  = {Brian DuSell and David Chiang},
    year    = {2024},
    eprint  = {2310.01749},
    archivePrefix = {arXiv},
    primaryClass = {cs.CL},
    url     = {https://arxiv.org/abs/2310.01749}, 
}

@misc{zhang2025stacktranslargelanguagemodel,
    title    = {StackTrans: From Large Language Model to Large Pushdown Automata Model}, 
    author   = {Kechi Zhang and Ge Li and Jia Li and Huangzhao Zhang and Yihong Dong and Jia Li and Jingjing Xu and Zhi Jin},
    year     = {2025},
    eprint   = {2507.15343},
    archivePrefix = {arXiv},
    primaryClass = {cs.SE},
    url      = {https://arxiv.org/abs/2507.15343}, 
}

Release files for stack-attention-pytorch 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for stack-attention-pytorch 0.0.1
File	Size	Uploaded
stack_attention_pytorch-0.0.1.tar.gz	4.2 kB	Sep 19, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for stack-attention-pytorch 0.0.1
File	Interpreter	ABI	Platform	Reset
stack_attention_pytorch-0.0.1-py3-none-any.whl 3.6 kB Sep 19, 2026	Python 3	none	any	Details

Total release size: 7.8 kB

Release files / stack_attention_pytorch-0.0.1.tar.gz

Download URL	stack_attention_pytorch-0.0.1.tar.gz
Size	4.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`fbcec74aa13e943c726809ac8c27047b3cd2fa0b6d6fc5691e8013c44777e814`
BLAKE2b-256 checksum How to use checksums	`6343e9e4fb124c54a3511caee38485aac75bd0ba761818dbf52118d44dbedafd`
Upload date	Sep 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.17`

Release files / stack_attention_pytorch-0.0.1-py3-none-any.whl

Download URL	stack_attention_pytorch-0.0.1-py3-none-any.whl
Size	3.6 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`724b66f1d5a0e86340825e552da4125917f2844bf108cc1783ad24aec7c5aaa7`
BLAKE2b-256 checksum How to use checksums	`0bfd34a3224bf04e42c4744f26ba48e7a2a537cabcc556ff27e672bd353bf6eb`
Upload date	Sep 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.17`