# LLMs that are Helpful, Honest, Harmless, and Huggy 🤗
## Installation
Download and install `h4` by running:
```bash
python -m pip install h4
```
If you want the bleeding-edge version, install from source by running:
```bash
python -m pip install git+https://github.com/huggingface/h4.git
```
### Developer installation
To contribute code to this project, first create a Python virtual environment using e.g. Conda:
```bash
conda create -n h4 python=3.8 && conda activate h4
```
Then install the base requirements with:
```bash
python -m pip install -e '.[dev]'
```
This will install core packages like `black` and `isort` that we use to ensure consistent code formatting.
## Formatting your code
We use `black` and `isort` to ensure consistent code formatting. After following the installation steps, you can check your code locally by running:
```
make style && make quality
```
Raw data
{
"_id": null,
"home_page": "https://github.com/huggingface/h4",
"name": "h4",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8.0",
"maintainer_email": "",
"keywords": "nlp deep learning rlhf",
"author": "The Hugging Face team (past and future)",
"author_email": "lewis@huggingface.co",
"download_url": "https://files.pythonhosted.org/packages/18/b2/d494228d6da6f56aed150a3b95806e30024946093e0f067184c5078bfb74/h4-0.1.0.tar.gz",
"platform": null,
"description": "# LLMs that are Helpful, Honest, Harmless, and Huggy \ud83e\udd17\n\n## Installation\n\nDownload and install `h4` by running:\n\n```bash\npython -m pip install h4\n```\n\nIf you want the bleeding-edge version, install from source by running:\n\n```bash\npython -m pip install git+https://github.com/huggingface/h4.git\n```\n\n### Developer installation\n\nTo contribute code to this project, first create a Python virtual environment using e.g. Conda:\n\n```bash\nconda create -n h4 python=3.8 && conda activate h4\n```\n\nThen install the base requirements with:\n\n```bash\npython -m pip install -e '.[dev]'\n```\n\nThis will install core packages like `black` and `isort` that we use to ensure consistent code formatting.\n\n## Formatting your code\n\nWe use `black` and `isort` to ensure consistent code formatting. After following the installation steps, you can check your code locally by running:\n\n```\nmake style && make quality\n```\n",
"bugtrack_url": null,
"license": "Apache",
"summary": "Reinforcment Learning from Human Feedback",
"version": "0.1.0",
"split_keywords": [
"nlp",
"deep",
"learning",
"rlhf"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "81d6a73ceb7e767216de3820307c359e8ec654cc108f77f3bf2a53aa83c76d59",
"md5": "fecdeb698aa2f72769798e44aea653b9",
"sha256": "b481a4fc141e47f3e25fa57d2873c4a8e2549787e40e50f53b077aaeb4c62b06"
},
"downloads": -1,
"filename": "h4-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "fecdeb698aa2f72769798e44aea653b9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8.0",
"size": 6136,
"upload_time": "2023-02-09T15:18:37",
"upload_time_iso_8601": "2023-02-09T15:18:37.659420Z",
"url": "https://files.pythonhosted.org/packages/81/d6/a73ceb7e767216de3820307c359e8ec654cc108f77f3bf2a53aa83c76d59/h4-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "18b2d494228d6da6f56aed150a3b95806e30024946093e0f067184c5078bfb74",
"md5": "62a7b95939566f847ee66bc5e17abdc5",
"sha256": "a1d1f2aaf87c0bb909ddadddbf857f075d026754c97584019a09ed345a9e7455"
},
"downloads": -1,
"filename": "h4-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "62a7b95939566f847ee66bc5e17abdc5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.0",
"size": 7356,
"upload_time": "2023-02-09T15:18:41",
"upload_time_iso_8601": "2023-02-09T15:18:41.266221Z",
"url": "https://files.pythonhosted.org/packages/18/b2/d494228d6da6f56aed150a3b95806e30024946093e0f067184c5078bfb74/h4-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-02-09 15:18:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "huggingface",
"github_project": "h4",
"lcname": "h4"
}