torchxlstm


Nametorchxlstm JSON
Version 0.0.3 PyPI version JSON
download
home_pageNone
SummaryA pure pytorch implementation of xLSTM.
upload_time2024-05-28 12:41:50
maintainerNone
docs_urlNone
authorNone
requires_python>=3
licenseNone
keywords xlstm lstm torch pytorch
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # xLSTM

A pure pytorch implementation of the [XLSTM paper](https://arxiv.org/abs/2405.04517).

## TODO
- Ensure correct with paper
- Create some usage examples
- Implement paralleization
- CUDA?
- Allow for different initializations according to: https://pytorch.org/docs/stable/nn.init.html
- Allow for flattening of x for greater shape conformity
- Allow for batching
- Add tests
    - https://github.com/catid/audio_prediction/tree/master
    - other classic RNN/LSTM tasks

## References
- https://arxiv.org/abs/2405.04517
- https://discuss.pytorch.org/t/causal-convolution/3456/3
- https://pytorch.org/docs/stable/generated/torch.nn.RNN.html
- https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "torchxlstm",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3",
    "maintainer_email": "Akaash Dash <akaash.dash@gmail.com>",
    "keywords": "xlstm, lstm, torch, pytorch",
    "author": null,
    "author_email": "Akaash Dash <akaash.dash@gmail.com>",
    "download_url": "https://files.pythonhosted.org/packages/58/40/28a31a2c02dbc4379043b675d13f901bb8f90c95ef710e5394534ac69b4e/torchxlstm-0.0.3.tar.gz",
    "platform": null,
    "description": "# xLSTM\n\nA pure pytorch implementation of the [XLSTM paper](https://arxiv.org/abs/2405.04517).\n\n## TODO\n- Ensure correct with paper\n- Create some usage examples\n- Implement paralleization\n- CUDA?\n- Allow for different initializations according to: https://pytorch.org/docs/stable/nn.init.html\n- Allow for flattening of x for greater shape conformity\n- Allow for batching\n- Add tests\n    - https://github.com/catid/audio_prediction/tree/master\n    - other classic RNN/LSTM tasks\n\n## References\n- https://arxiv.org/abs/2405.04517\n- https://discuss.pytorch.org/t/causal-convolution/3456/3\n- https://pytorch.org/docs/stable/generated/torch.nn.RNN.html\n- https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html\n",
    "bugtrack_url": null,
    "license": null,
    "summary": "A pure pytorch implementation of xLSTM.",
    "version": "0.0.3",
    "project_urls": {
        "Homepage": "https://github.com/akaashdash/xlstm",
        "Source": "https://github.com/akaashdash/xlstm/"
    },
    "split_keywords": [
        "xlstm",
        " lstm",
        " torch",
        " pytorch"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "096137204fd3e7830676ff8fdb3b8edf172a4ae73a997da08c36fb5f0e7fe595",
                "md5": "a1aa454da85371798aa9b7eb4950ec80",
                "sha256": "984abe69a05a5ca621aa0fc6dc8a286490de4fd7b917facca60b6e6bd1ab2139"
            },
            "downloads": -1,
            "filename": "torchxlstm-0.0.3-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "a1aa454da85371798aa9b7eb4950ec80",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3",
            "size": 4635,
            "upload_time": "2024-05-28T12:41:49",
            "upload_time_iso_8601": "2024-05-28T12:41:49.059697Z",
            "url": "https://files.pythonhosted.org/packages/09/61/37204fd3e7830676ff8fdb3b8edf172a4ae73a997da08c36fb5f0e7fe595/torchxlstm-0.0.3-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "584028a31a2c02dbc4379043b675d13f901bb8f90c95ef710e5394534ac69b4e",
                "md5": "ee6f873f9ee630a0febbfe31979ebd16",
                "sha256": "23050af2559a0b20d8542bf6a6ab219c7aee1b13523b2e3c47a90ff8099725fe"
            },
            "downloads": -1,
            "filename": "torchxlstm-0.0.3.tar.gz",
            "has_sig": false,
            "md5_digest": "ee6f873f9ee630a0febbfe31979ebd16",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3",
            "size": 4312,
            "upload_time": "2024-05-28T12:41:50",
            "upload_time_iso_8601": "2024-05-28T12:41:50.172989Z",
            "url": "https://files.pythonhosted.org/packages/58/40/28a31a2c02dbc4379043b675d13f901bb8f90c95ef710e5394534ac69b4e/torchxlstm-0.0.3.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-05-28 12:41:50",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "akaashdash",
    "github_project": "xlstm",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "torchxlstm"
}
        
Elapsed time: 4.36849s