[](https://discord.com/servers/agora-999382051935506503)
## TTL
Pytorch Implementation of the paper: "Learning to (Learn at Test Time): RNNs with Expressive Hidden States"
## Install
```bash
$ pip install ttl-torch
```
## Usage
```python
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
```bibtex
@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},
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/kyegomez/TTL",
"name": "ttl-torch",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "artificial intelligence, deep learning, optimizers, Prompt Engineering",
"author": "Kye Gomez",
"author_email": "kye@apac.ai",
"download_url": "https://files.pythonhosted.org/packages/77/bd/219c1dfbc0ccacb13b1ea8d873169b3c16db87d2a91478f778895d9f2758/ttl_torch-0.0.4.tar.gz",
"platform": null,
"description": "[](https://discord.com/servers/agora-999382051935506503)\n\n## TTL\nPytorch Implementation of the paper: \"Learning to (Learn at Test Time): RNNs with Expressive Hidden States\"\n\n\n\n\n## Install\n```bash\n$ pip install ttl-torch\n\n```\n\n## Usage\n```python\n\nimport torch\nfrom ttl_torch.ttl_linear import TTLinear\n\n\ninput_dim, output_dim = 10, 10 # Dimensions for the linear model\nttt_layer = TTLinear(input_dim, output_dim)\n\n# Generate some example data\nexample_data = [\n torch.randn(1, input_dim, output_dim) for _ in range(5)\n]\n\n# Forward pass through the TTT layer\noutput_data = ttt_layer(example_data)\n\nfor i, output in enumerate(output_data):\n print(f\"Output at step {i}: {output}\")\n\n```\n\n\n# License\nMIT\n\n\n## Citation\n```bibtex\n@misc{sun2024learninglearntesttime,\n title={Learning to (Learn at Test Time): RNNs with Expressive Hidden States}, \n 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},\n year={2024},\n eprint={2407.04620},\n archivePrefix={arXiv},\n primaryClass={cs.LG},\n url={https://arxiv.org/abs/2407.04620}, \n}\n\n```",
"bugtrack_url": null,
"license": "MIT",
"summary": "Paper - Pytorch",
"version": "0.0.4",
"project_urls": {
"Documentation": "https://github.com/kyegomez/TTL",
"Homepage": "https://github.com/kyegomez/TTL",
"Repository": "https://github.com/kyegomez/TTL"
},
"split_keywords": [
"artificial intelligence",
" deep learning",
" optimizers",
" prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c5418cbc155a1b3f15c7c267c0016647635278dab89d657c62320c2edb1f61e2",
"md5": "45cf530d0c7e4227f6d15c04eae750ad",
"sha256": "b20a8a18131b9f05ce64a8ddd6ee68e65f1adbde5d0b19b14e3deabfa53c5d10"
},
"downloads": -1,
"filename": "ttl_torch-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "45cf530d0c7e4227f6d15c04eae750ad",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 5554,
"upload_time": "2024-07-13T07:09:36",
"upload_time_iso_8601": "2024-07-13T07:09:36.921090Z",
"url": "https://files.pythonhosted.org/packages/c5/41/8cbc155a1b3f15c7c267c0016647635278dab89d657c62320c2edb1f61e2/ttl_torch-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "77bd219c1dfbc0ccacb13b1ea8d873169b3c16db87d2a91478f778895d9f2758",
"md5": "4b7e4d2199e08a20b7ef2ac700c9ad43",
"sha256": "5e81f4187d9514efb4b78289c688988461dd8da793ca01ef3422abc9c12a366b"
},
"downloads": -1,
"filename": "ttl_torch-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "4b7e4d2199e08a20b7ef2ac700c9ad43",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 4819,
"upload_time": "2024-07-13T07:09:38",
"upload_time_iso_8601": "2024-07-13T07:09:38.796876Z",
"url": "https://files.pythonhosted.org/packages/77/bd/219c1dfbc0ccacb13b1ea8d873169b3c16db87d2a91478f778895d9f2758/ttl_torch-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-13 07:09:38",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kyegomez",
"github_project": "TTL",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "ttl-torch"
}
JSON
