Guang Yang's repositories
BASHEXPLAINER
code and data for paper "BASHEXPLAINER: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT", which accepted in ICSME 2022
DeepPseudo
code and data for paper "Fine-grained Pseudo-code Generation Method via Code Feature Extraction and Transformer", which accepted in APSEC 2021
ExploitGen
ExploitGen is a template-augmented Exploit Code generation method based on CodeBERT, which accepted in JSS.
TurduckenGen
Code for paper "A Syntax-Guided Multi-Task Learning Approach for Turducken-Style Code Generation", which accepted in EMSE.
StackOverflow
挖掘StackOverflow里的post.xml文件
CodeTF
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
CodeUtils
Program analysis code utils (for self-use)
ebooks
收藏的一些经典的历史、政治、心理、哲学、数学、计算机方面电子书(约10万本)
NTDXYG
Config files for my GitHub profile.
OpenBA-v2
OpenBA-V2: 3B LLM (Large Language Model) with T5 architecture, utilizing model pruning technique and continuing pretraining from OpenBA-15B.
THU-PPT-Theme
清华主题PPT模板
torchtune
A Native-PyTorch Library for LLM Fine-tuning