cca-gpt-model-trainer
This repository contains a script to automate the process of fetching, cleaning, and combining data from MediaWiki and Jira, and then fine-tuning a language model (GPT) on the combined dataset. The script is designed to handle GPU memory constraints and can switch to CPU if needed.
MIT License
Stars
0
Committers
1
Commit Statistics
Past Year
All Time
Total Commits
8
8
Total Committers
2
2
Avg. Commits Per Committer
4.0
4.0
Bot Commits
0
0
Issue Statistics
Past Year
All Time
Total Pull Requests
0
0
Merged Pull Requests
0
0
Total Issues
0
0
Time to Close Issues
N/A
N/A