Metadata-Version: 2.1
Name: tensorkiko
Version: 0.1.5
Summary: A fast and intuitive tool for visualizing and analyzing model structures from safetensors files
Home-page: https://github.com/takara-ai/TensorKiko
Author: takara-ai
Author-email: jordan@takara.ai
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: anytree==2.12.1
Requires-Dist: filelock==3.16.1
Requires-Dist: fsspec==2024.9.0
Requires-Dist: Jinja2==3.1.4
Requires-Dist: MarkupSafe==3.0.0
Requires-Dist: mpmath==1.3.0
Requires-Dist: networkx==3.3
Requires-Dist: numpy==1.26.4
Requires-Dist: safetensors==0.4.5
Requires-Dist: six==1.16.0
Requires-Dist: sympy==1.13.3
Requires-Dist: torch==2.2.2
Requires-Dist: typing-extensions==4.12.2

# TensorKiko

A fast and intuitive tool for visualizing and analyzing model structures from safetensors files, supporting tree-based visualizations and detailed parameter analysis.

## Installation

### Using pip

```
pip install tensorkiko
```

### Using Homebrew

```
brew tap takara-ai/tensorkiko https://github.com/takara-ai/TensorKiko
brew install tensorkiko
```

## Usage

After installation, you can use TensorKiko from the command line:

```
tensorkiko path/to/your/model.safetensors
```

For more options, use:

```
tensorkiko --help
```

## Features

- Load and process safetensors files
- Generate interactive HTML visualizations of model structures
- Analyze model parameters, memory usage, and estimated FLOPs
- Search functionality for easy navigation of large models

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

## License

This project is licensed under the MIT License.
