[](https://discord.gg/qUtxnK2NMf)
# Jamba
PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"
## install
`$ pip install jamba`
## usage
```python
# Import the torch library, which provides tools for machine learning
import torch
# Import the Jamba model from the jamba.model module
from jamba.model import Jamba
# Create a tensor of random integers between 0 and 100, with shape (1, 100)
# This simulates a batch of tokens that we will pass through the model
x = torch.randint(0, 100, (1, 100))
# Initialize the Jamba model with the specified parameters
# dim: dimensionality of the input data
# depth: number of layers in the model
# num_tokens: number of unique tokens in the input data
# d_state: dimensionality of the hidden state in the model
# d_conv: dimensionality of the convolutional layers in the model
# heads: number of attention heads in the model
# num_experts: number of expert networks in the model
# num_experts_per_token: number of experts used for each token in the input data
model = Jamba(
dim=512,
depth=6,
num_tokens=100,
d_state=256,
d_conv=128,
heads=8,
num_experts=8,
num_experts_per_token=2,
)
# Perform a forward pass through the model with the input data
# This will return the model's predictions for each token in the input data
output = model(x)
# Print the model's predictions
print(output)
```
# License
MIT
Raw data
{
"_id": null,
"home_page": "https://github.com/kyegomez/jamba",
"name": "jamba",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.6",
"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/10/28/5bc6245545c7be050685d887e8e034a70054ce390db81ba197316266d1ec/jamba-0.0.2.tar.gz",
"platform": null,
"description": "[](https://discord.gg/qUtxnK2NMf)\n\n# Jamba\nPyTorch Implementation of Jamba: \"Jamba: A Hybrid Transformer-Mamba Language Model\"\n\n\n## install\n`$ pip install jamba`\n\n## usage\n\n```python\n# Import the torch library, which provides tools for machine learning\nimport torch\n\n# Import the Jamba model from the jamba.model module\nfrom jamba.model import Jamba\n\n# Create a tensor of random integers between 0 and 100, with shape (1, 100)\n# This simulates a batch of tokens that we will pass through the model\nx = torch.randint(0, 100, (1, 100))\n\n# Initialize the Jamba model with the specified parameters\n# dim: dimensionality of the input data\n# depth: number of layers in the model\n# num_tokens: number of unique tokens in the input data\n# d_state: dimensionality of the hidden state in the model\n# d_conv: dimensionality of the convolutional layers in the model\n# heads: number of attention heads in the model\n# num_experts: number of expert networks in the model\n# num_experts_per_token: number of experts used for each token in the input data\nmodel = Jamba(\n dim=512,\n depth=6,\n num_tokens=100,\n d_state=256,\n d_conv=128,\n heads=8,\n num_experts=8,\n num_experts_per_token=2,\n)\n\n# Perform a forward pass through the model with the input data\n# This will return the model's predictions for each token in the input data\noutput = model(x)\n\n# Print the model's predictions\nprint(output)\n\n```\n\n# License\nMIT\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "jamba - Pytorch",
"version": "0.0.2",
"project_urls": {
"Documentation": "https://github.com/kyegomez/jamba",
"Homepage": "https://github.com/kyegomez/jamba",
"Repository": "https://github.com/kyegomez/jamba"
},
"split_keywords": [
"artificial intelligence",
" deep learning",
" optimizers",
" prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d66879333062974aaaed75ecd950821b13f62fbd2852f7ef08076124c4614436",
"md5": "db985a5e6b2446611a0a3e548169fbe9",
"sha256": "d1d918498812a5f748ad18b3d94eccbb4c9ebb0b1e997755837a721f62844eb2"
},
"downloads": -1,
"filename": "jamba-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "db985a5e6b2446611a0a3e548169fbe9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.6",
"size": 8267,
"upload_time": "2024-04-01T18:28:48",
"upload_time_iso_8601": "2024-04-01T18:28:48.925747Z",
"url": "https://files.pythonhosted.org/packages/d6/68/79333062974aaaed75ecd950821b13f62fbd2852f7ef08076124c4614436/jamba-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "10285bc6245545c7be050685d887e8e034a70054ce390db81ba197316266d1ec",
"md5": "09035fdff16940d1e09f77e310a6c8a2",
"sha256": "9fb7d3b5501351f297cae924a8b3efc241c37d949f20858b1241b16162275fa1"
},
"downloads": -1,
"filename": "jamba-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "09035fdff16940d1e09f77e310a6c8a2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.6",
"size": 8664,
"upload_time": "2024-04-01T18:28:50",
"upload_time_iso_8601": "2024-04-01T18:28:50.546022Z",
"url": "https://files.pythonhosted.org/packages/10/28/5bc6245545c7be050685d887e8e034a70054ce390db81ba197316266d1ec/jamba-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-01 18:28:50",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kyegomez",
"github_project": "jamba",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "torch",
"specs": []
},
{
"name": "zetascale",
"specs": []
},
{
"name": "swarms",
"specs": []
}
],
"lcname": "jamba"
}
JSON
