# Tune The Model python wrapper
[Tune The Model](https://tunethemodel.com) is a few-shot AutoML system.
Tune The Model can do almost anything that requires understanding or generating natural language. It is able to solve tasks in 12 languages: English, Spanish, Portuguese, Russian, Turkish, French, German, Italian, Arabic, Polish, Dutch, and Hebrew.
This package provides a simple wrapper for using our api.
Using `tune-the-model` package allows you to train and apply models.
## Documentation
You can find the documentation at our [Tune The Model API docs site](https://tune-the-model.github.io/tune-the-model-docs/index.html).
## Just try
We have fine-tuned several models. You can use the [notebook](https://colab.research.google.com/github/beyondml/model-one-py/blob/main/playbook.ipynb) to try them out. You can [get the token](https://tunethemodel.com) to fine tune your own model.
## Getting started
Firstly fill out the [form](https://tunethemodel.com) to get a key to access the API. We will send you the key within a day.
### Installation
To install the package just use `pip install -U tune-the-model`.
### Usage
```py
import tune_the_model as ttm
import pandas as pd
ttm.set_api_key('YOUR_API_KEY')
# load datasets
tdf = pd.read_csv('train.csv')
vdf = pd.read_csv('test.csv')
# Call one method. It will do everything for you:
# create a model, save it to the file, upload datasets and put the model in the queue for training.
model = ttm.tune_generator(
'filename.json',
tdf['inputs'], tdf['outputs'],
vdf['inputs'], vdf['outputs']
)
# wait...
# a few hours
# while our GPUs train your model
model.wait_for_training_finish()
print(model.status)
print(model.is_ready)
# inference!
the_answer = model.generate('The Answer to the Ultimate Question of Life, the Universe, and Everything')
print(the_answer)
```
Raw data
{
"_id": null,
"home_page": "https://github.com/tune-the-model/tune-the-model-py",
"name": "tune-the-model",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "beyondml,tune-the-model,gpt-3,nlp",
"author": "BeyondML",
"author_email": "pavel.gavrilov@beyond.ml",
"download_url": "https://files.pythonhosted.org/packages/5f/ba/52259d21fe2ee021ca557101ff267184ab49dc8a81bd3383c798948f4263/tune_the_model-0.1.33.tar.gz",
"platform": null,
"description": "# Tune The Model python wrapper\n\n[Tune The Model](https://tunethemodel.com) is a few-shot AutoML system.\n\nTune The Model can do almost anything that requires understanding or generating natural language. It is able to solve tasks in 12 languages: English, Spanish, Portuguese, Russian, Turkish, French, German, Italian, Arabic, Polish, Dutch, and Hebrew.\n\nThis package provides a simple wrapper for using our api.\n\nUsing `tune-the-model` package allows you to train and apply models.\n\n## Documentation\n\nYou can find the documentation at our [Tune The Model API docs site](https://tune-the-model.github.io/tune-the-model-docs/index.html).\n\n## Just try\n\nWe have fine-tuned several models. You can use the [notebook](https://colab.research.google.com/github/beyondml/model-one-py/blob/main/playbook.ipynb) to try them out. You can [get the token](https://tunethemodel.com) to fine tune your own model.\n\n## Getting started\n\nFirstly fill out the [form](https://tunethemodel.com) to get a key to access the API. We will send you the key within a day.\n\n### Installation\n\nTo install the package just use `pip install -U tune-the-model`.\n\n### Usage\n\n```py\nimport tune_the_model as ttm\nimport pandas as pd\n\nttm.set_api_key('YOUR_API_KEY')\n\n# load datasets\ntdf = pd.read_csv('train.csv')\nvdf = pd.read_csv('test.csv')\n\n# Call one method. It will do everything for you:\n# create a model, save it to the file, upload datasets and put the model in the queue for training.\nmodel = ttm.tune_generator(\n 'filename.json',\n tdf['inputs'], tdf['outputs'],\n vdf['inputs'], vdf['outputs']\n)\n\n# wait...\n# a few hours\n# while our GPUs train your model\nmodel.wait_for_training_finish()\n\nprint(model.status)\nprint(model.is_ready)\n\n# inference!\nthe_answer = model.generate('The Answer to the Ultimate Question of Life, the Universe, and Everything')\nprint(the_answer)\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "beyondml",
"version": "0.1.33",
"split_keywords": [
"beyondml",
"tune-the-model",
"gpt-3",
"nlp"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "81397b985ef5f75544359290768cdfd7b8df07d4f534844a516eb1512d128b5a",
"md5": "cef60c6990d1241ea211ee96c67f9793",
"sha256": "4894ac4d97d77d10f7e30e11cb246205c980b54aea9ea79c5e451c2214b883cb"
},
"downloads": -1,
"filename": "tune_the_model-0.1.33-py3-none-any.whl",
"has_sig": false,
"md5_digest": "cef60c6990d1241ea211ee96c67f9793",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 15437,
"upload_time": "2023-03-30T12:58:18",
"upload_time_iso_8601": "2023-03-30T12:58:18.100371Z",
"url": "https://files.pythonhosted.org/packages/81/39/7b985ef5f75544359290768cdfd7b8df07d4f534844a516eb1512d128b5a/tune_the_model-0.1.33-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5fba52259d21fe2ee021ca557101ff267184ab49dc8a81bd3383c798948f4263",
"md5": "67778bf510ad477f51c574c4f4f5d2c4",
"sha256": "cce80eeb6f998c686ecb7f7e9c12d333dbcbc075052ad5339af29cd22d9de805"
},
"downloads": -1,
"filename": "tune_the_model-0.1.33.tar.gz",
"has_sig": false,
"md5_digest": "67778bf510ad477f51c574c4f4f5d2c4",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 14814,
"upload_time": "2023-03-30T12:58:21",
"upload_time_iso_8601": "2023-03-30T12:58:21.086443Z",
"url": "https://files.pythonhosted.org/packages/5f/ba/52259d21fe2ee021ca557101ff267184ab49dc8a81bd3383c798948f4263/tune_the_model-0.1.33.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-03-30 12:58:21",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "tune-the-model",
"github_project": "tune-the-model-py",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "tune-the-model"
}
JSON
