# gguf_llama
Provides a LlamaAI class with Python interface for generating text using Llama models.
## Features
- Load Llama models and tokenizers automatically from gguf file
- Generate text completions for prompts
- Automatically adjust model size to fit longer prompts up to a specific limit
- Convenient methods for tokenizing and untokenizing text
- Fix text formatting issues before generating
## Usage
```python
from llama_ai import LlamaAI
ai = LlamaAI("my_model.gguf", max_tokens=500, max_input_tokens=100)"
```
Generate text by calling infer():
```python
text = ai.infer("Once upon a time")
print(text)"
```
## Installation
```python
pip install gguf_llama
```
## Documentation
See the [API documentation](https://laelhalawani.github.io/gguf_llama) for full details on classes and methods.
## Contributing
Contributions are welcome! Open an issue or PR to improve gguf_llama.
Raw data
{
"_id": null,
"home_page": "https://github.com/laelhalawani/gguf_llama",
"name": "gguf-llama",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "llama,gguf,quantized models,llama gguf,cpu inference",
"author": "\u0141ael Al-Halawani",
"author_email": "laelhalawani@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/c2/94/548a808b940863e91e4a377d9765d4ca5966e02112602d36b275ad1c2682/gguf_llama-0.0.18.tar.gz",
"platform": null,
"description": "# gguf_llama\n\nProvides a LlamaAI class with Python interface for generating text using Llama models.\n\n## Features\n\n- Load Llama models and tokenizers automatically from gguf file\n- Generate text completions for prompts\n- Automatically adjust model size to fit longer prompts up to a specific limit\n- Convenient methods for tokenizing and untokenizing text \n- Fix text formatting issues before generating\n\n## Usage\n\n```python\nfrom llama_ai import LlamaAI\n\nai = LlamaAI(\"my_model.gguf\", max_tokens=500, max_input_tokens=100)\"\n```\nGenerate text by calling infer():\n```python\ntext = ai.infer(\"Once upon a time\") \nprint(text)\"\n```\n## Installation\n\n```python\npip install gguf_llama\n``` \n\n## Documentation\n\nSee the [API documentation](https://laelhalawani.github.io/gguf_llama) for full details on classes and methods. \n\n## Contributing\n\nContributions are welcome! Open an issue or PR to improve gguf_llama.\n",
"bugtrack_url": null,
"license": "",
"summary": "Wrapper for simplified use of Llama2 GGUF quantized models.",
"version": "0.0.18",
"project_urls": {
"Homepage": "https://github.com/laelhalawani/gguf_llama"
},
"split_keywords": [
"llama",
"gguf",
"quantized models",
"llama gguf",
"cpu inference"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "07bd9a12ace7bdfc65d458c0d9a19c6394172bd187e779dcb865bb70364120c1",
"md5": "608e42ce2bfce8ad00b4e21967f59e2f",
"sha256": "77f0ae941b1cf4766c25b5071ad718ceab8a31abb0dd28e852227c76785e8596"
},
"downloads": -1,
"filename": "gguf_llama-0.0.18-py3-none-any.whl",
"has_sig": false,
"md5_digest": "608e42ce2bfce8ad00b4e21967f59e2f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 4709,
"upload_time": "2024-01-13T18:59:56",
"upload_time_iso_8601": "2024-01-13T18:59:56.872607Z",
"url": "https://files.pythonhosted.org/packages/07/bd/9a12ace7bdfc65d458c0d9a19c6394172bd187e779dcb865bb70364120c1/gguf_llama-0.0.18-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c294548a808b940863e91e4a377d9765d4ca5966e02112602d36b275ad1c2682",
"md5": "3202b9ceb859947633a4e197116e2ecd",
"sha256": "485c467705699bcc7f4f77034167a33ae4380da73bb10ac5ca93817cbc87fdde"
},
"downloads": -1,
"filename": "gguf_llama-0.0.18.tar.gz",
"has_sig": false,
"md5_digest": "3202b9ceb859947633a4e197116e2ecd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 4570,
"upload_time": "2024-01-13T18:59:58",
"upload_time_iso_8601": "2024-01-13T18:59:58.366769Z",
"url": "https://files.pythonhosted.org/packages/c2/94/548a808b940863e91e4a377d9765d4ca5966e02112602d36b275ad1c2682/gguf_llama-0.0.18.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-13 18:59:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "laelhalawani",
"github_project": "gguf_llama",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "gguf-llama"
}