kosmosg

Name	kosmosg JSON
Version	0.0.4 JSON
	download
home_page	https://github.com/kyegomez/KosmosG
Summary	kosmosg - Pytorch
upload_time	2023-10-25 16:55:52
maintainer
docs_url	None
author	Kye Gomez
requires_python	>=3.6,<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)

# KosmosG
My implementation of the model KosmosG from "KOSMOS-G: Generating Images in Context with Multimodal Large Language Models"

## Installation
`pip install kosmosg`

## Usage
```python
import torch
from kosmosg.main import KosmosG

# usage
img = torch.randn(1, 3, 256, 256)
text = torch.randint(0, 20000, (1, 1024))

model = KosmosG()
output = model(img, text)
print(output)
```

## Architecture
`text, image => KosmosG => text tokens with multi modality understanding`

## License
MIT

## Todo
- Create Aligner in pytorch
- Create Diffusion module
- Integrate these pieces
- Create a training script
            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/kyegomez/KosmosG",
    "name": "kosmosg",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.6,<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/26/7a/7ef1e2efb021c0318b7a0c44eb9f65a1b22a684845885795022b537e4a1e/kosmosg-0.0.4.tar.gz",
    "platform": null,
    "description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# KosmosG\nMy implementation of the model KosmosG from \"KOSMOS-G: Generating Images in Context with Multimodal Large Language Models\"\n\n## Installation\n`pip install kosmosg`\n\n## Usage\n```python\nimport torch\nfrom kosmosg.main import KosmosG\n\n# usage\nimg = torch.randn(1, 3, 256, 256)\ntext = torch.randint(0, 20000, (1, 1024))\n\nmodel = KosmosG()\noutput = model(img, text)\nprint(output)\n```\n\n## Architecture\n`text, image => KosmosG => text tokens with multi modality understanding`\n\n## License\nMIT\n\n## Todo\n- Create Aligner in pytorch\n- Create Diffusion module\n- Integrate these pieces\n- Create a training script",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "kosmosg - Pytorch",
    "version": "0.0.4",
    "project_urls": {
        "Homepage": "https://github.com/kyegomez/KosmosG",
        "Repository": "https://github.com/kyegomez/KosmosG"
    },
    "split_keywords": [
        "artificial intelligence",
        "deep learning",
        "optimizers",
        "prompt engineering"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "8ede5461107f228385baa151c4309d95a7d625f3816c4644a7992ec9b47e4486",
                "md5": "99c09c2d402e87bc36e4e5b251a626ea",
                "sha256": "ae7206b315c6ab15f77fe63d94b26bb72d43216bdfef879f1187beca64731750"
            },
            "downloads": -1,
            "filename": "kosmosg-0.0.4-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "99c09c2d402e87bc36e4e5b251a626ea",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6,<4.0",
            "size": 4800,
            "upload_time": "2023-10-25T16:55:51",
            "upload_time_iso_8601": "2023-10-25T16:55:51.244095Z",
            "url": "https://files.pythonhosted.org/packages/8e/de/5461107f228385baa151c4309d95a7d625f3816c4644a7992ec9b47e4486/kosmosg-0.0.4-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "267a7ef1e2efb021c0318b7a0c44eb9f65a1b22a684845885795022b537e4a1e",
                "md5": "5a9caa3691519dd5b381384ebd4aab1e",
                "sha256": "2721a5d38684c47e2452717c44e5cdf039ea73de67a941da1ca2e13d861631b1"
            },
            "downloads": -1,
            "filename": "kosmosg-0.0.4.tar.gz",
            "has_sig": false,
            "md5_digest": "5a9caa3691519dd5b381384ebd4aab1e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6,<4.0",
            "size": 4665,
            "upload_time": "2023-10-25T16:55:52",
            "upload_time_iso_8601": "2023-10-25T16:55:52.372087Z",
            "url": "https://files.pythonhosted.org/packages/26/7a/7ef1e2efb021c0318b7a0c44eb9f65a1b22a684845885795022b537e4a1e/kosmosg-0.0.4.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-10-25 16:55:52",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "kyegomez",
    "github_project": "KosmosG",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [],
    "lcname": "kosmosg"
}