mambabyte

Name	mambabyte JSON
Version	0.0.2 JSON
	download
home_page	https://github.com/kyegomez/MambaByte
Summary	MambaByte - Pytorch
upload_time	2024-01-26 01:45:18
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)


# MambaByte
Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta. Note this will be a higher performance implementation of Mamba with parallel scan 


## Installation

```bash
pip install mambabyte
```

# Usage
```python
import torch 
from mambabyte import MambaConfig, Mamba

x = torch.randn(2, 3, 4)
config = MambaConfig(
    dim = 4,
    depth = 3,
    dt_rank = 2,
    d_state = 2,
    expand_factor = 2,
    d_conv = 3,
    dt_min = 0.001,
    dt_max = 0.1,
    dt_init = "random",
    dt_scale = 1.0,
    bias = False,
    conv_bias = True,
    pscan = True
)

model = Mamba(config)

out = model(x)

print(out)

```


# License
MIT

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/kyegomez/MambaByte",
    "name": "mambabyte",
    "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/7d/2e/a060a4da585b800439adeadf3d692a0d5d61a1b59ae823f8d6a850461da4/mambabyte-0.0.2.tar.gz",
    "platform": null,
    "description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n\n# MambaByte\nImplementation of MambaByte in \"MambaByte: Token-free Selective State Space Model\" in Pytorch and Zeta. Note this will be a higher performance implementation of Mamba with parallel scan \n\n\n## Installation\n\n```bash\npip install mambabyte\n```\n\n# Usage\n```python\nimport torch \nfrom mambabyte import MambaConfig, Mamba\n\nx = torch.randn(2, 3, 4)\nconfig = MambaConfig(\n    dim = 4,\n    depth = 3,\n    dt_rank = 2,\n    d_state = 2,\n    expand_factor = 2,\n    d_conv = 3,\n    dt_min = 0.001,\n    dt_max = 0.1,\n    dt_init = \"random\",\n    dt_scale = 1.0,\n    bias = False,\n    conv_bias = True,\n    pscan = True\n)\n\nmodel = Mamba(config)\n\nout = model(x)\n\nprint(out)\n\n```\n\n\n# License\nMIT\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "MambaByte - Pytorch",
    "version": "0.0.2",
    "project_urls": {
        "Documentation": "https://github.com/kyegomez/MambaByte",
        "Homepage": "https://github.com/kyegomez/MambaByte",
        "Repository": "https://github.com/kyegomez/MambaByte"
    },
    "split_keywords": [
        "artificial intelligence",
        "deep learning",
        "optimizers",
        "prompt engineering"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "06a7a79de0f8b0e09fc430f168a222946d50f5d7842b07655d7865b67dd22272",
                "md5": "c787007ccbb1294eee1f8e716dc24dd5",
                "sha256": "1545a1276449a9d5cb3a0f3ee65779a6b6a48e701699e734a95822d22c9f59cb"
            },
            "downloads": -1,
            "filename": "mambabyte-0.0.2-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "c787007ccbb1294eee1f8e716dc24dd5",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6,<4.0",
            "size": 6937,
            "upload_time": "2024-01-26T01:45:16",
            "upload_time_iso_8601": "2024-01-26T01:45:16.594781Z",
            "url": "https://files.pythonhosted.org/packages/06/a7/a79de0f8b0e09fc430f168a222946d50f5d7842b07655d7865b67dd22272/mambabyte-0.0.2-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "7d2ea060a4da585b800439adeadf3d692a0d5d61a1b59ae823f8d6a850461da4",
                "md5": "97966bbbb548de331358c0c8d4e4fdcf",
                "sha256": "47a27a4b659d8ec3b145bbac8fb1d67001faceaac29b78fa8e983ff46ff5b0d3"
            },
            "downloads": -1,
            "filename": "mambabyte-0.0.2.tar.gz",
            "has_sig": false,
            "md5_digest": "97966bbbb548de331358c0c8d4e4fdcf",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6,<4.0",
            "size": 7041,
            "upload_time": "2024-01-26T01:45:18",
            "upload_time_iso_8601": "2024-01-26T01:45:18.228223Z",
            "url": "https://files.pythonhosted.org/packages/7d/2e/a060a4da585b800439adeadf3d692a0d5d61a1b59ae823f8d6a850461da4/mambabyte-0.0.2.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-01-26 01:45:18",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "kyegomez",
    "github_project": "MambaByte",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [],
    "lcname": "mambabyte"
}