sssszh/CodePLAN
The code repository for the paper “Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs”.
This project helps machine learning engineers improve how smaller AI models write code. It takes a problem description and a 'solution plan' (a high-level strategy for solving the problem) to produce more accurate code. The end-user is a machine learning engineer responsible for training and deploying code generation models.
No commits in the last 6 months.
Use this if you are a machine learning engineer looking to enhance the code generation capabilities of smaller language models by leveraging strategic 'solution plans'.
Not ideal if you are a software developer seeking an off-the-shelf tool to directly generate production code, or if you are not working with training and fine-tuning language models.
Stars
8
Forks
1
Language
Python
License
—
Category
Last pushed
Nov 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/sssszh/CodePLAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
k4black/codebleu
Pip compatible CodeBLEU metric implementation available for linux/macos/win
LiveCodeBench/LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of...
EdinburghNLP/code-docstring-corpus
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and...
hendrycks/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
solis-team/Hydra
[FSE 2026] Do Not Treat Code as Natural Language: Implications for Repository-Level Code...