Highlights
- Pro
Stars
A very quick project that transforms research papers into engaging three-person discussions, offering an intuitive and thought-provoking listening experience. Perfect for podcast enthusiasts seekin…
Code and documentation to train Stanford's Alpaca models, and generate the data.
The conventional commits specification
Repo for ICSE2025 paper "A First Look at Conventional Commits Classification"
Completely free, unbelievably stupid wi-fi on long-haul flights
Understanding Code Changes Practically with Small-Scale Language Models (ASE '24)
📡️ vCards 中国黄页 - 优化 iOS/Android 来电、信息界面体验
One place for all the default credentials to assist the Blue/Red teamers activities on finding devices with default password 🛡️
A Deep Learning Augmented Large Language Model Prompting Framework for Software Vulnerability Detection
Implementation of 'Commit message generation for source code change'.
this is the repository for the paper titled "The Best of Both Worlds: Integrating Semantic Features with Expert Features for Defect Prediction and Localization" accepted by FSE'22.
General technology for enabling AI capabilities w/ LLMs and MLLMs
[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.
An implementation of the ACL 2024 Findings paper "Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning".
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
DeepSeek Coder: Let the Code Write Itself
Knowledge Base + LLM Powered Code Review Mentor。知识库 + LLM 驱动的 Code Review 导师
This repository can be used to get started the SmartSHARK database (with Python).
An approach of treating commits as graphs and then untangling composite/tangled commits by detecting hidden relationships between code changes