Skip to content

[ICML 2025] EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning

License

Notifications You must be signed in to change notification settings

huangd1999/EffiCoder

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning

Installation

cd EffiCoder
pip install -r requirements.txt
cd LLaMA-Factory
pip install -e ".[torch,metrics]"

Fine-tune LLMs with EffiCoder

We have provided the EffiCoder dataset in EffiCoder/LLaMA-Factory/data/efficoder.json, so we can directly use SFT and other methods to finetune LLMs.

cd EffiCoder/LLaMA-Factory
bash run.sh

VLLM inference

cd EffiCoder/scripts
bash run.sh

Report Efficiency and pass@1 results

cd EffiCoder/src
python code_efficiency_calculator.py
python calculate_memory_usage.py

About

[ICML 2025] EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages