medxiaorudan/CodeGeneration
Prompt engineering with Langchain and fine-tuning the CodeLlama model. The main aim is to generate task-specific C++ code snippets. Experiment with various prompts and models to create accurate C++ code. Unit test is conducted to validate the correctness and effectiveness of the generated code snippets.
This project helps C++ developers quickly generate task-specific C++ code snippets by leveraging a pre-trained code model. You provide a prompt describing the desired functionality, and the system outputs accurate C++ code. This is ideal for C++ programmers looking to accelerate their coding process and generate boilerplate or specific utility functions.
No commits in the last 6 months.
Use this if you are a C++ developer needing to quickly generate functional C++ code snippets from plain language descriptions, like creating a program to record and sort user input.
Not ideal if you are a non-developer or if your primary programming language is not C++.
Stars
8
Forks
2
Language
C++
License
—
Category
Last pushed
Feb 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/medxiaorudan/CodeGeneration"
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...