1.5 KiB
ucsinfer
Universal Category System LLM toolkit.
Install
Since this project is still experimental and not for production, it's not packaged on PyPi. You should cloen the project to your local machine and do an editable install in a virtual environment.
$ git clone https://git.squad51.us/jamie/ucsinfer.git
$ git submodule sync
$ python -m venv .venv
$ source .venv/bin/activate # or whatever command is approprate for your shell
$ pip install -e .
Or alternately, this module is packaged with the poetry dependency manager and can be run within a poetry virtualenv.
$ poetry run python -m ucsinfer
Running
python -m ucsinfer [command]
Pass --help
to see a summary of subcommands and options.
The subcommands available at this time are gather
and evaluate
.
Functions
-
recommend(in-progress)Infer a UCS category for a text description.
-
gather
Scan files to capture existing text descriptions and UCS categories and save as a dataset. This function is used to countruct datasets that
evaluate
can use to test models and finetune can use to refine them. -
finetune(planned)Fine-tune an existing sentence embedding model with training data.
-
evaluate
Use datasets to evaluate the performance of a model and fine-tuning.