jordandeklerk/Starcoder2-Finetune-Code-Completion
Finetuning Starcoder2-3B for Code Completion on a single A100 GPU
This project helps software developers fine-tune a powerful code-generating AI model using their company's specific codebase. It takes your existing internal code and modifies the AI model to generate new code that matches your team's coding style and uses your specialized libraries. The result is a custom AI assistant that understands and writes code exactly how your company does.
No commits in the last 6 months.
Use this if you are a software development team leader or MLOps engineer looking to customize a code-generating AI to adhere to your company's unique coding standards and leverage your internal libraries.
Not ideal if you need a code completion tool for general programming tasks that don't require deep integration with a proprietary codebase or specific internal coding styles.
Stars
8
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jordandeklerk/Starcoder2-Finetune-Code-Completion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
limix-ldm-ai/LimiX
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence...
tatsu-lab/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
google-research/plur
PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets...
YalaLab/pillar-finetune
Finetuning framework for Pillar medical imaging models.
thuml/LogME
Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML...