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}, 
}

Metadata

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)

Source distribution for ttl-torch 0.0.4
File	Size	Uploaded
ttl_torch-0.0.4.tar.gz	4.8 kB	Jul 13, 2024	Details

Built distribution (wheel)

Table of built distributions (wheels) for ttl-torch 0.0.4
File	Interpreter	ABI	Platform	Reset
ttl_torch-0.0.4-py3-none-any.whl 5.6 kB Jul 13, 2024	Python 3	none	any	Details

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	Jul 13, 2024
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	Jul 13, 2024
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.8.3 CPython/3.12.4 Darwin/22.6.0`