feat: first commit

.gitignore

@@ -0,0 +1,28 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+build/
+dist/
+*.egg-info/
+
+# Poetry
+poetry.lock
+
+# Virtual environment
+.env/
+.venv/
+
+# Pytest cache
+.pytest_cache/
+
+# MyPy cache
+.mypy_cache/
+
+# VSCode settings
+.vscode/
+
+#csv files
+*.csv

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Zjh-819
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,64 @@
+
+# LLMDataParser
+
+**LLMDataParser** is a Python library that provides parsers for benchmark datasets used in evaluating Large Language Models (LLMs). It offers a unified interface for loading and parsing datasets like **MMLU** and **GSM8k**, simplifying dataset preparation for LLM evaluation.
+
+## Features
+
+- **Unified Interface**: Consistent `DatasetParser` for all datasets.
+- **LLM-Agnostic**: Independent of any specific language model.
+- **Easy to Use**: Simple methods and built-in Python types.
+- **Extensible**: Easily add support for new datasets.
+
+## Installation
+
+### Option 1: Using pip
+
+You can install the package directly using `pip`. Even with only a `pyproject.toml` file, this method works for standard installations.
+
+1. **Clone the Repository**:
+
+    ```bash
+    git clone https://github.com/jeff52415/LLMDataParser.git
+    cd LLMDataParser
+    ```
+
+2. **Install Dependencies with pip**:
+
+    ```bash
+    pip install .
+    ```
+
+### Option 2: Using Poetry
+
+Poetry manages the virtual environment and dependencies automatically, so you don't need to create a conda environment first.
+
+1. **Install Dependencies with Poetry**:
+
+    ```bash
+    poetry install
+    ```
+
+2. **Activate the Virtual Environment**:
+
+    ```bash
+    poetry shell
+    ```
+
+
+## Available Parsers
+
+- **MMLUParser**: Parses the MMLU dataset.
+- **GSM8kParser**: Parses the GSM8k dataset.
+
+## Contributing
+
+Contributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+## License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+
+## Contact
+
+For questions or support, please open an issue on GitHub or contact [[email protected]](mailto:[email protected]).

pyproject.toml

@@ -0,0 +1,56 @@
+[tool.poetry]
+name = "llmdataparser"
+version = "0.1.0"
+description = "A collection of parsers for LLM benchmark datasets like MMLU, MMLU-Pro, GSM8k, and more."
+authors = ["Jeff <[email protected]>"]
+license = "MIT"
+readme = "README.md"
+homepage = "https://github.com/jeff52415/LLMDataParser"
+repository = "https://github.com/jeff52415/LLMDataParser"
+keywords = ["LLM", "benchmark", "dataset", "parser", "NLP", "machine learning"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Intended Audience :: Developers",
+]
+
+[tool.poetry.dependencies]
+python = ">=3.11"
+pandas = "^2.0.3"
+datasets = "^2.14.4"
+typing-extensions = "^4.8.0"
+
+
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.0"
+black = {version = "^23.9.1", allow-prereleases = true}
+flake8 = "^6.1.0"
+isort = "^5.12.0"
+mypy = "^1.5.1"
+pre-commit = "^3.4.0"
+types-python-dateutil = "^2.8.19.14"
+ipykernel = "^6.7.0"
+
+[tool.black]
+line-length = 88
+target-version = ["py311"]
+exclude = '''
+/(
+    \.git
+  | \.venv
+  | build
+  | dist
+)/
+'''
+
+[tool.isort]
+profile = "black"
+line_length = 88
+known_first_party = ["llmdataparser"]
+
+[build-system]
+requires = ["poetry-core>=1.5.0"]
+build-backend = "poetry.core.masonry.api"