# 🔥 One Line LLM Tuner 🔥
Fine-tune any Large Language Model (LLM) available on [Hugging Face](https://www.huggingface.co) in a single line. It is created by [Suhas Bhairav](https://www.metriccoders.com).
## Overview
`one-line-llm-tuner` is a Python package designed to simplify the process of fine-tuning large language models (LLMs) like GPT-2, Llama-2, GPT-3 and more. With just one line of code, you can fine-tune a pre-trained model to your specific dataset. Consider it as a wrapper for `transformers` library, just like how `keras` is for `tensorflow`.
## Features
- **Simple**: Fine-tune models with minimal code.
- **Supports Popular LLMs**: Works with models from the `transformers` library, including GPT, BERT, and more.
- **Customizable**: Advanced users can customize the fine-tuning process with additional parameters.
## Installation
You can install `one-line-llm-tuner` using pip:
```bash
pip install one-line-llm-tuner
```
## Usage
The PyPI package can be used in the following way after installation.
```bash
from one_line_llm_tuner.tuner import llm_tuner
fine_tune_obj = llm_tuner.FineTuneModel()
fine_tune_obj.fine_tune_model(input_file_path="train.txt")
fine_tune_obj.predict_text("Elon musk founded Spacex in ")
```
If you want to modify the default values such as type of model used, tokenizer and more, use the following code.
```bash
from one_line_llm_tuner.tuner import llm_tuner
fine_tune_obj = llm_tuner.FineTuneModel(model_name="gpt2",
test_size=0.3,
training_dataset_filename="train_dataset.txt",
testing_dataset_filename="test_dataset.txt",
tokenizer_truncate=True,
tokenizer_padding=True,
output_dir="./results",
num_train_epochs=2,
logging_steps=500,
save_steps=500,
per_device_train_batch_size=128,
per_device_eval_batch_size=128,
max_output_length=100,
num_return_sequences=1,
skip_special_tokens=True,)
fine_tune_obj.fine_tune_model(input_file_path="train.txt")
fine_tune_obj.predict_text("Elon musk founded Spacex in ")
```
## Contributing
We welcome contributions! Please see the [contributing guide](Contributing.md) for more details.
## License
This project is licensed under the terms of the MIT license. See the [LICENSE](LICENSE.txt) file for details.
Raw data
{
"_id": null,
"home_page": "https://github.com/metriccoders/one-line-llm-tuner",
"name": "one-line-llm-tuner",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Suhas Bhairav",
"author_email": "info@metriccoders.com",
"download_url": "https://files.pythonhosted.org/packages/5b/4a/c38cfb6cd5d1ebdf4b42ebe6a9a9c86b41565089f1cedc0cf9ea4238a60e/one_line_llm_tuner-0.0.15.tar.gz",
"platform": null,
"description": "# \ud83d\udd25 One Line LLM Tuner \ud83d\udd25\n\nFine-tune any Large Language Model (LLM) available on [Hugging Face](https://www.huggingface.co) in a single line. It is created by [Suhas Bhairav](https://www.metriccoders.com).\n\n## Overview\n\n`one-line-llm-tuner` is a Python package designed to simplify the process of fine-tuning large language models (LLMs) like GPT-2, Llama-2, GPT-3 and more. With just one line of code, you can fine-tune a pre-trained model to your specific dataset. Consider it as a wrapper for `transformers` library, just like how `keras` is for `tensorflow`.\n\n## Features\n\n- **Simple**: Fine-tune models with minimal code.\n- **Supports Popular LLMs**: Works with models from the `transformers` library, including GPT, BERT, and more.\n- **Customizable**: Advanced users can customize the fine-tuning process with additional parameters.\n\n## Installation\n\nYou can install `one-line-llm-tuner` using pip:\n\n```bash\npip install one-line-llm-tuner\n```\n\n## Usage\n\nThe PyPI package can be used in the following way after installation.\n\n```bash\nfrom one_line_llm_tuner.tuner import llm_tuner\n\nfine_tune_obj = llm_tuner.FineTuneModel()\n\nfine_tune_obj.fine_tune_model(input_file_path=\"train.txt\")\n\nfine_tune_obj.predict_text(\"Elon musk founded Spacex in \")\n```\n\nIf you want to modify the default values such as type of model used, tokenizer and more, use the following code.\n\n```bash\nfrom one_line_llm_tuner.tuner import llm_tuner\n\nfine_tune_obj = llm_tuner.FineTuneModel(model_name=\"gpt2\",\n test_size=0.3,\n training_dataset_filename=\"train_dataset.txt\",\n testing_dataset_filename=\"test_dataset.txt\",\n tokenizer_truncate=True,\n tokenizer_padding=True,\n output_dir=\"./results\",\n num_train_epochs=2,\n logging_steps=500,\n save_steps=500,\n per_device_train_batch_size=128,\n per_device_eval_batch_size=128,\n max_output_length=100,\n num_return_sequences=1,\n skip_special_tokens=True,)\n\nfine_tune_obj.fine_tune_model(input_file_path=\"train.txt\")\n\nfine_tune_obj.predict_text(\"Elon musk founded Spacex in \")\n```\n\n\n## Contributing\nWe welcome contributions! Please see the [contributing guide](Contributing.md) for more details.\n\n## License\nThis project is licensed under the terms of the MIT license. See the [LICENSE](LICENSE.txt) file for details.\n",
"bugtrack_url": null,
"license": null,
"summary": "A Large Language Model Fine-tuning package. The package uses a single line to fine-tune an LLM by taking care of all the boilerplate in the backend.",
"version": "0.0.15",
"project_urls": {
"Bug Tracker": "https://github.com/metriccoders/one-line-llm-tuner/issues",
"Homepage": "https://github.com/metriccoders/one-line-llm-tuner"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "97e1a71d245cea9de8f7dc67a16a14c5731ef3d9031083888ded9858bfab5cb6",
"md5": "48c196edf16455ea2996ac385a109853",
"sha256": "d5899368edb9f069c6abbfd3269ae3f3a316662ad06a31b8ebb0dc4d2a3e1306"
},
"downloads": -1,
"filename": "one_line_llm_tuner-0.0.15-py3-none-any.whl",
"has_sig": false,
"md5_digest": "48c196edf16455ea2996ac385a109853",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 6085,
"upload_time": "2024-08-05T23:21:36",
"upload_time_iso_8601": "2024-08-05T23:21:36.409889Z",
"url": "https://files.pythonhosted.org/packages/97/e1/a71d245cea9de8f7dc67a16a14c5731ef3d9031083888ded9858bfab5cb6/one_line_llm_tuner-0.0.15-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5b4ac38cfb6cd5d1ebdf4b42ebe6a9a9c86b41565089f1cedc0cf9ea4238a60e",
"md5": "c88f253dd77dc0460fe5d83509147ae9",
"sha256": "282fd46c7ae195da16ed3aa54c980126251acd8c63f96c3ed536e96ce25c9a01"
},
"downloads": -1,
"filename": "one_line_llm_tuner-0.0.15.tar.gz",
"has_sig": false,
"md5_digest": "c88f253dd77dc0460fe5d83509147ae9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 5956,
"upload_time": "2024-08-05T23:21:49",
"upload_time_iso_8601": "2024-08-05T23:21:49.354878Z",
"url": "https://files.pythonhosted.org/packages/5b/4a/c38cfb6cd5d1ebdf4b42ebe6a9a9c86b41565089f1cedc0cf9ea4238a60e/one_line_llm_tuner-0.0.15.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-05 23:21:49",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "metriccoders",
"github_project": "one-line-llm-tuner",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "one-line-llm-tuner"
}
JSON
