https://github.com/binkley/bridge
Bridge with AI
https://github.com/binkley/bridge
Last synced: 9 months ago
JSON representation
Bridge with AI
- Host: GitHub
- URL: https://github.com/binkley/bridge
- Owner: binkley
- License: unlicense
- Created: 2024-12-10T15:51:09.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-11T19:32:41.000Z (about 1 year ago)
- Last Synced: 2025-03-29T07:36:45.245Z (10 months ago)
- Language: Python
- Size: 28.3 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Bridge with AI
I am not a data scientist nor an expert in LLM model training nor an expert in
Python libraries.
This repo is me applying LLMs to what user experience might be like when
starting from scratch.
I use the game of [_bridge_](https://en.wikipedia.org/wiki/Contract_bridge) as
an interesting complex domain model.
The initial data for setup comes from
[_alpaca_](https://huggingface.co/datasets/tatsu-lab/alpaca/tree/main/data).
## Setup
This project uses Python.
This is a common choice by experts in AI/LLM/ML work.
Assuming Python, Conda is a common choice for managing libraries.
### Use Conda
[Install
Conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html)
for setting up your Python environment.
From your command line:
```bash
conda env create --file environment.yml
conda activate bridge
```
When you edit [`environment.yml`](./environment.yml), update with:
```bash
conda env update
```
## Training
Follow along with [How to Train an LLM with
PyTorch](https://www.datacamp.com/tutorial/how-to-train-a-llm-with-pytorch).