Keytoyze/JumpCoder
Code for ACL (main) paper "JumpCoder: Go Beyond Autoregressive Coder via Online Modification"
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.
Stars
27
Forks
—
Language
Python
License
—
Category
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.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase