A simple tool to format text into well-structured Markdown using Llama 3.2.
Right now the outputs are completely insane, don't use it.
Input: hello world, testing 1, 2, 3. ummm ok.
Output - Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, -end
- Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello, ! Hello,
What works is that it constrains the vocabulary, but the output is wrong.
This project uses uv for dependency management. To set up the project:
-
Install uv if you haven't already:
curl -LsSf https://astral.sh/uv/install.sh | sh
-
Create a virtual environment and install dependencies:
uv venv source .venv/bin/activate uv pip sync
-
Run the application:
python src/main.py
-
Run tests:
uv run pytest
-
Build the project:
uv build
- Use
uv add <package>
to add new dependencies - Use
uv add --dev <package>
to add new development dependencies - Run
black .
to format code - Run
mypy .
for type checking
This project is licensed under the MIT License.