TTL
Pytorch Implementation of the paper: "Learning to (Learn at Test Time): RNNs with Expressive Hidden States"
Install
$ pip install ttl-torch
Usage
import torch
from ttl_torch.ttl_linear import TTLinear
input_dim, output_dim = 10, 10 # Dimensions for the linear model
ttt_layer = TTLinear(input_dim, output_dim)
# Generate some example data
example_data = [
torch.randn(1, input_dim, output_dim) for _ in range(5)
]
# Forward pass through the TTT layer
output_data = ttt_layer(example_data)
for i, output in enumerate(output_data):
print(f"Output at step {i}: {output}")
License
MIT
Citation
@misc{sun2024learninglearntesttime,
title={Learning to (Learn at Test Time): RNNs with Expressive Hidden States},
author={Yu Sun and Xinhao Li and Karan Dalal and Jiarui Xu and Arjun Vikram and Genghan Zhang and Yann Dubois and Xinlei Chen and Xiaolong Wang and Sanmi Koyejo and Tatsunori Hashimoto and Carlos Guestrin},
year={2024},
eprint={2407.04620},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2407.04620},
}
1 maintainer
Metadata
1 maintainer
Release files for ttl-torch 0.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ttl_torch-0.0.4.tar.gz | 4.8 kB | Without provenance | Details for ttl_torch-0.0.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ttl_torch-0.0.4-py3-none-any.whl | Python 3 | none | any | Details for ttl_torch-0.0.4-py3-none-any.whl |
Total release size: 10.4 kB
Release files / ttl_torch-0.0.4.tar.gz
| Download URL | ttl_torch-0.0.4.tar.gz |
|---|---|
| Size | 4.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5e81f4187d9514efb4b78289c688988461dd8da793ca01ef3422abc9c12a366b
|
|
BLAKE2b-256 checksum How to use checksums |
77bd219c1dfbc0ccacb13b1ea8d873169b3c16db87d2a91478f778895d9f2758
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.12.4 Darwin/22.6.0
|
Release files / ttl_torch-0.0.4-py3-none-any.whl
| Download URL | ttl_torch-0.0.4-py3-none-any.whl |
|---|---|
| Size | 5.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b20a8a18131b9f05ce64a8ddd6ee68e65f1adbde5d0b19b14e3deabfa53c5d10
|
|
BLAKE2b-256 checksum How to use checksums |
c5418cbc155a1b3f15c7c267c0016647635278dab89d657c62320c2edb1f61e2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.12.4 Darwin/22.6.0
|
Security for ttl-torch 0.0.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
