gpt4o

Name	gpt4o JSON
Version	0.0.1 JSON
	download
home_page	https://github.com/kyegomez/gpt4o
Summary	gpt4o - Pytorch
upload_time	2024-05-14 20:17:36
maintainer	None
docs_url	None
author	Kye Gomez
requires_python	<4.0,>=3.10
license	MIT
keywords	artificial intelligence deep learning optimizers prompt engineering
VCS
bugtrack_url
requirements	torch zetascale einops tiktoken
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

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

# GPT4o
Community Open Source Implementation of GPT4o in PyTorch


## Install


# Architecture
- TikToken Tokenzier: We know fursure the tokenizer. [Which is here](https://github.com/openai/tiktoken)
- Model understands Images and Audio Natively. There are 2 approaches, process them natively or use encoders for each. I think here they're using encoders like whisper and vit for simplicity and brevity.
- Using DALLE3 as the output head to generate images
- Tokens to denote when to generate an image or audio
- Whisper output head for the audio outputs
- 

# License
MIT

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/kyegomez/gpt4o",
    "name": "gpt4o",
    "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/69/5d/8423537f2ee1002c75f4150881f4290966f33d94dcca67bc82a3ecbc763f/gpt4o-0.0.1.tar.gz",
    "platform": null,
    "description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# GPT4o\nCommunity Open Source Implementation of GPT4o in PyTorch\n\n\n## Install\n\n\n# Architecture\n- TikToken Tokenzier: We know fursure the tokenizer. [Which is here](https://github.com/openai/tiktoken)\n- Model understands Images and Audio Natively. There are 2 approaches, process them natively or use encoders for each. I think here they're using encoders like whisper and vit for simplicity and brevity.\n- Using DALLE3 as the output head to generate images\n- Tokens to denote when to generate an image or audio\n- Whisper output head for the audio outputs\n- \n\n# License\nMIT\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "gpt4o - Pytorch",
    "version": "0.0.1",
    "project_urls": {
        "Documentation": "https://github.com/kyegomez/gpt4o",
        "Homepage": "https://github.com/kyegomez/gpt4o",
        "Repository": "https://github.com/kyegomez/gpt4o"
    },
    "split_keywords": [
        "artificial intelligence",
        " deep learning",
        " optimizers",
        " prompt engineering"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "1a027e8b342cd05e28f3a689b712c08fd632781b3d6447cf843b9b3841526d9b",
                "md5": "a878039532607f456bfba4c79ddc40c2",
                "sha256": "39467fd746688ec553d1740be9ffce1eacdd6b0678ebfecec1ec1f17c7c2faa4"
            },
            "downloads": -1,
            "filename": "gpt4o-0.0.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "a878039532607f456bfba4c79ddc40c2",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<4.0,>=3.10",
            "size": 3067,
            "upload_time": "2024-05-14T20:17:34",
            "upload_time_iso_8601": "2024-05-14T20:17:34.678470Z",
            "url": "https://files.pythonhosted.org/packages/1a/02/7e8b342cd05e28f3a689b712c08fd632781b3d6447cf843b9b3841526d9b/gpt4o-0.0.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "695d8423537f2ee1002c75f4150881f4290966f33d94dcca67bc82a3ecbc763f",
                "md5": "f215dbab16534abef634348d40f3dd13",
                "sha256": "54fb69e976de3d0cee675098d1ca3e2c0f254eaec5405354d0cb14f425ddcbed"
            },
            "downloads": -1,
            "filename": "gpt4o-0.0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "f215dbab16534abef634348d40f3dd13",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<4.0,>=3.10",
            "size": 3060,
            "upload_time": "2024-05-14T20:17:36",
            "upload_time_iso_8601": "2024-05-14T20:17:36.415363Z",
            "url": "https://files.pythonhosted.org/packages/69/5d/8423537f2ee1002c75f4150881f4290966f33d94dcca67bc82a3ecbc763f/gpt4o-0.0.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-05-14 20:17:36",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "kyegomez",
    "github_project": "gpt4o",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [
        {
            "name": "torch",
            "specs": []
        },
        {
            "name": "zetascale",
            "specs": []
        },
        {
            "name": "einops",
            "specs": []
        },
        {
            "name": "tiktoken",
            "specs": []
        }
    ],
    "lcname": "gpt4o"
}