geidiprime

Name	geidiprime JSON
Version	0.0.1 JSON
	download
home_page	https://github.com/kyegomez/GiediPrime
Summary	Paper - Pytorch
upload_time	2023-11-30 07:37:03
maintainer
docs_url	None
author	Kye Gomez
requires_python	>=3.9,<4.0
license	MIT
keywords	artificial intelligence deep learning optimizers prompt engineering
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            [![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)

# GeidiPrime
This is an extremely experimental Transformer architecture with Macaron like FFNs with local attention. Perhap's we can add the visual expert from Zeta and make it multi-modal!


# Install

## Usage
```python
import torch
from geidi_prime.model import GeidiPrimeTransformer

model = GeidiPrimeTransformer(
    dim=4096,
    depth=6,
    heads=8,
    num_tokens=20000,
)

x = torch.randint(0, 20000, (1, 4096))

out = model(x)
print(out.shape)

```



# License
MIT




            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/kyegomez/GiediPrime",
    "name": "geidiprime",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.9,<4.0",
    "maintainer_email": "",
    "keywords": "artificial intelligence,deep learning,optimizers,Prompt Engineering",
    "author": "Kye Gomez",
    "author_email": "kye@apac.ai",
    "download_url": "https://files.pythonhosted.org/packages/2e/7c/8782659bc7836803167a41fd12964ba0610c4dc7ae2a2861b7e8a337dee8/geidiprime-0.0.1.tar.gz",
    "platform": null,
    "description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# GeidiPrime\nThis is an extremely experimental Transformer architecture with Macaron like FFNs with local attention. Perhap's we can add the visual expert from Zeta and make it multi-modal!\n\n\n# Install\n\n## Usage\n```python\nimport torch\nfrom geidi_prime.model import GeidiPrimeTransformer\n\nmodel = GeidiPrimeTransformer(\n    dim=4096,\n    depth=6,\n    heads=8,\n    num_tokens=20000,\n)\n\nx = torch.randint(0, 20000, (1, 4096))\n\nout = model(x)\nprint(out.shape)\n\n```\n\n\n\n# License\nMIT\n\n\n\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "Paper - Pytorch",
    "version": "0.0.1",
    "project_urls": {
        "Documentation": "https://github.com/kyegomez/GiediPrime",
        "Homepage": "https://github.com/kyegomez/GiediPrime",
        "Repository": "https://github.com/kyegomez/GiediPrime"
    },
    "split_keywords": [
        "artificial intelligence",
        "deep learning",
        "optimizers",
        "prompt engineering"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "ff07c467733196302abf72c910fff56e5cf7927fbad9da34dd7aa432f31e7146",
                "md5": "c1ce47a00a657655b6c22ab718a920ff",
                "sha256": "9a71e972687727f5c544e8fd7a88c48cba4fa69f297040d4e64043b1dc57c0df"
            },
            "downloads": -1,
            "filename": "geidiprime-0.0.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "c1ce47a00a657655b6c22ab718a920ff",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.9,<4.0",
            "size": 3783,
            "upload_time": "2023-11-30T07:37:00",
            "upload_time_iso_8601": "2023-11-30T07:37:00.918080Z",
            "url": "https://files.pythonhosted.org/packages/ff/07/c467733196302abf72c910fff56e5cf7927fbad9da34dd7aa432f31e7146/geidiprime-0.0.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "2e7c8782659bc7836803167a41fd12964ba0610c4dc7ae2a2861b7e8a337dee8",
                "md5": "8088a1df2b17c51f26e08ca6c81216c0",
                "sha256": "17627fb93375e8057383acd3495e15941e2d30c2550589b6a2b33b8ac026a98e"
            },
            "downloads": -1,
            "filename": "geidiprime-0.0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "8088a1df2b17c51f26e08ca6c81216c0",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.9,<4.0",
            "size": 3888,
            "upload_time": "2023-11-30T07:37:03",
            "upload_time_iso_8601": "2023-11-30T07:37:03.127348Z",
            "url": "https://files.pythonhosted.org/packages/2e/7c/8782659bc7836803167a41fd12964ba0610c4dc7ae2a2861b7e8a337dee8/geidiprime-0.0.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-11-30 07:37:03",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "kyegomez",
    "github_project": "GiediPrime",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [],
    "lcname": "geidiprime"
}