Keytoyze/JumpCoder

Code for ACL (main) paper "JumpCoder: Go Beyond Autoregressive Coder via Online Modification"

15
/ 100
Experimental

This project helps large language models (LLMs) generate more accurate and human-like code by allowing them to go back and fix mistakes or insert missing pieces in the middle of a code snippet. You feed in a coding problem or prompt to an existing code LLM, and it outputs improved, functional code. This is for AI/ML engineers or researchers working on improving code generation capabilities of LLMs.

No commits in the last 6 months.

Use this if you need to improve the accuracy and naturalness of code generated by large language models without extensive fine-tuning or human intervention.

Not ideal if you are looking for a standalone code generation tool for direct use by a software developer.

AI-driven code generation Large Language Models (LLMs) Natural Language Processing (NLP) AI/ML research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

27

Forks

Language

Python

License

Last pushed

May 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Keytoyze/JumpCoder"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.