Name | llm-sambanova JSON |
Version |
0.1
JSON |
| download |
home_page | None |
Summary | LLM plugin for models hosted by SambaNova |
upload_time | 2024-10-09 00:56:59 |
maintainer | None |
docs_url | None |
author | Nick Mystic |
requires_python | None |
license | MIT |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# llm-sambanova
[![PyPI](https://img.shields.io/pypi/v/llm-sambanova.svg)](https://pypi.org/project/llm-sambanova/)
[![Changelog](https://img.shields.io/github/v/release/simonw/llm-sambanova?include_prereleases&label=changelog)](https://github.com/simonw/llm-sambanova/releases)
[![Tests](https://github.com/simonw/llm-sambanova/workflows/Test/badge.svg)](https://github.com/simonw/llm-sambanova/actions?query=workflow%3ATest)
[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm-sambanova/blob/main/LICENSE)
[LLM](https://llm.datasette.io/) plugin for models hosted by [SambaNova](https://sambanova.ai/)
## Installation
First, [install the LLM command-line utility](https://llm.datasette.io/en/stable/setup.html).
Now install this plugin in the same environment as LLM.
```bash
llm install llm-sambanova
```
## Configuration
You will need an API key from SambaNova. You can [obtain one here](https://sambanova.ai/keys).
You can set that as an environment variable called `OPENROUTER_KEY`, or add it to the `llm` set of saved keys using:
```bash
llm keys set sambanova
```
```
Enter key: <paste key here>
```
## Usage
To list available models, run:
```bash
llm models list
```
You should see a list that looks something like this:
```
SambaNova: sambanova/Meta-Llama-3.2-1B-Instruct
SambaNova: sambanova/Meta-Llama-3.2-3B-Instruct
SambaNova: sambanova/Meta-Llama-3.1-8B-Instruct
SambaNova: sambanova/Meta-Llama-3.1-8B-Instruct-8k
SambaNova: sambanova/Meta-Llama-3.1-70B-Instruct
SambaNova: sambanova/Meta-Llama-3.1-70B-Instruct-8k
SambaNova: sambanova/Meta-Llama-3.1-405B-Instruct
SambaNova: sambanova/Meta-Llama-3.1-405B-Instruct-8k
SambaNova: sambanovacompletion/Meta-Llama-3.2-1B-Instruct
SambaNova: sambanovacompletion/Meta-Llama-3.2-3B-Instruct
SambaNova: sambanovacompletion/Meta-Llama-3.1-8B-Instruct
SambaNova: sambanovacompletion/Meta-Llama-3.1-8B-Instruct-8k
SambaNova: sambanovacompletion/Meta-Llama-3.1-70B-Instruct
SambaNova: sambanovacompletion/Meta-Llama-3.1-70B-Instruct-8k
SambaNova: sambanovacompletion/Meta-Llama-3.1-405B-Instruct
SambaNova: sambanovacompletion/Meta-Llama-3.1-405B-Instruct-8k
...
```
To run a prompt against a model, pass its full model ID to the `-m` option, like this:
```bash
llm -m sambanova/Meta-Llama-3.2-1B-Instruct "Five spooky names for a pet tarantula"
```
You can set a shorter alias for a model using the `llm aliases` command like so:
```bash
llm aliases set 405 sambanova/Meta-Llama-3.1-405B-Instruct
```
Now you can prompt Claude using:
```bash
cat llm_sambanova.py | llm -m 405 -s 'write some pytest tests for this'
```
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-sambanova
python3 -m venv venv
source venv/bin/activate
```
Now install the dependencies and test dependencies:
```bash
pip install -e '.[test]'
```
To run the tests:
```bash
pytest
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llm-sambanova",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "Nick Mystic",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/63/ab/f1bb24e4fdb84ef8b84a2ee1c373aa2721924fef3a2ff05318ffa772f924/llm_sambanova-0.1.tar.gz",
"platform": null,
"description": "# llm-sambanova\n\n[![PyPI](https://img.shields.io/pypi/v/llm-sambanova.svg)](https://pypi.org/project/llm-sambanova/)\n[![Changelog](https://img.shields.io/github/v/release/simonw/llm-sambanova?include_prereleases&label=changelog)](https://github.com/simonw/llm-sambanova/releases)\n[![Tests](https://github.com/simonw/llm-sambanova/workflows/Test/badge.svg)](https://github.com/simonw/llm-sambanova/actions?query=workflow%3ATest)\n[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm-sambanova/blob/main/LICENSE)\n\n[LLM](https://llm.datasette.io/) plugin for models hosted by [SambaNova](https://sambanova.ai/)\n\n## Installation\n\nFirst, [install the LLM command-line utility](https://llm.datasette.io/en/stable/setup.html).\n\nNow install this plugin in the same environment as LLM.\n```bash\nllm install llm-sambanova\n```\n\n## Configuration\n\nYou will need an API key from SambaNova. You can [obtain one here](https://sambanova.ai/keys).\n\nYou can set that as an environment variable called `OPENROUTER_KEY`, or add it to the `llm` set of saved keys using:\n\n```bash\nllm keys set sambanova\n```\n```\nEnter key: <paste key here>\n```\n\n## Usage\n\nTo list available models, run:\n```bash\nllm models list\n```\nYou should see a list that looks something like this:\n```\nSambaNova: sambanova/Meta-Llama-3.2-1B-Instruct\nSambaNova: sambanova/Meta-Llama-3.2-3B-Instruct\nSambaNova: sambanova/Meta-Llama-3.1-8B-Instruct\nSambaNova: sambanova/Meta-Llama-3.1-8B-Instruct-8k\nSambaNova: sambanova/Meta-Llama-3.1-70B-Instruct\nSambaNova: sambanova/Meta-Llama-3.1-70B-Instruct-8k\nSambaNova: sambanova/Meta-Llama-3.1-405B-Instruct\nSambaNova: sambanova/Meta-Llama-3.1-405B-Instruct-8k\nSambaNova: sambanovacompletion/Meta-Llama-3.2-1B-Instruct\nSambaNova: sambanovacompletion/Meta-Llama-3.2-3B-Instruct\nSambaNova: sambanovacompletion/Meta-Llama-3.1-8B-Instruct\nSambaNova: sambanovacompletion/Meta-Llama-3.1-8B-Instruct-8k\nSambaNova: sambanovacompletion/Meta-Llama-3.1-70B-Instruct\nSambaNova: sambanovacompletion/Meta-Llama-3.1-70B-Instruct-8k\nSambaNova: sambanovacompletion/Meta-Llama-3.1-405B-Instruct\nSambaNova: sambanovacompletion/Meta-Llama-3.1-405B-Instruct-8k\n...\n```\nTo run a prompt against a model, pass its full model ID to the `-m` option, like this:\n```bash\nllm -m sambanova/Meta-Llama-3.2-1B-Instruct \"Five spooky names for a pet tarantula\"\n```\nYou can set a shorter alias for a model using the `llm aliases` command like so:\n```bash\nllm aliases set 405 sambanova/Meta-Llama-3.1-405B-Instruct\n```\nNow you can prompt Claude using:\n```bash\ncat llm_sambanova.py | llm -m 405 -s 'write some pytest tests for this'\n```\n## Development\n\nTo set up this plugin locally, first checkout the code. Then create a new virtual environment:\n```bash\ncd llm-sambanova\npython3 -m venv venv\nsource venv/bin/activate\n```\nNow install the dependencies and test dependencies:\n```bash\npip install -e '.[test]'\n```\nTo run the tests:\n```bash\npytest\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "LLM plugin for models hosted by SambaNova",
"version": "0.1",
"project_urls": {
"CI": "https://github.com/ghostofpokemon/llm-sambanova/actions",
"Changelog": "https://github.com/ghostofpokemon/llm-sambanova/releases",
"Homepage": "https://github.com/ghostofpokemon/llm-sambanova",
"Issues": "https://github.com/ghostofpokemon/llm-sambanova/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "179a4d8d52e4fde38998b0c061fab146e81dd049f2fe643b546d6a5792ed3460",
"md5": "9cc8e0c63c7237a03595971d657107ae",
"sha256": "0c1c436d72a7cdb6a29eef5d448b627391bb39bac2cab0ab3f4cfab23db66651"
},
"downloads": -1,
"filename": "llm_sambanova-0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9cc8e0c63c7237a03595971d657107ae",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 3998,
"upload_time": "2024-10-09T00:56:57",
"upload_time_iso_8601": "2024-10-09T00:56:57.551149Z",
"url": "https://files.pythonhosted.org/packages/17/9a/4d8d52e4fde38998b0c061fab146e81dd049f2fe643b546d6a5792ed3460/llm_sambanova-0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "63abf1bb24e4fdb84ef8b84a2ee1c373aa2721924fef3a2ff05318ffa772f924",
"md5": "6f0828a420c3caf294000b3f5ade5ea7",
"sha256": "6aae71acfe4286896b0f16e38aa9199ba0277b9f192cc5d68d245572daf5e9e8"
},
"downloads": -1,
"filename": "llm_sambanova-0.1.tar.gz",
"has_sig": false,
"md5_digest": "6f0828a420c3caf294000b3f5ade5ea7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 3600,
"upload_time": "2024-10-09T00:56:59",
"upload_time_iso_8601": "2024-10-09T00:56:59.406313Z",
"url": "https://files.pythonhosted.org/packages/63/ab/f1bb24e4fdb84ef8b84a2ee1c373aa2721924fef3a2ff05318ffa772f924/llm_sambanova-0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-09 00:56:59",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ghostofpokemon",
"github_project": "llm-sambanova",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "llm-sambanova"
}