wangyanli3630

RLCoder

SOChecker

SOChecker is dedicated to detecting vulnerabilities in smart contract code snippets from Q&A forums like Stack Overflow.

hierarchical-attention-HAR

[PAKDD-2021] Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition

CodeS

monitors4codegen

Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

ccf-deadlines

⏰ Collaboratively track deadlines of conferences recommended by CCF (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~

transformer-debugger

repobench

✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024

CoderEval

A collection of practical code generation tasks and tests in open source projects. Complementary to HumanEval by OpenAI.

Tencent2020_Rank1st

The code for 2020 Tencent College Algorithm Contest, and the online result ranks 1st.

ClassEval

Benchmark ClassEval for class-level code generation.

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

starcoder

Home of StarCoder: fine-tuning & inference!

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

awesome-smart-contract-datasets

A curated list of awesome smart contract datasets

TRACE

TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

alpaca-lora

Instruct-tune LLaMA on consumer hardware

llm-finetuning

Guide for fine-tuning Llama/Mistral/CodeLlama models and more

Llama2-Code-Interpreter

Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet

ge-sc

MANDO is a new heterogeneous graph representation to learn the heterogeneous contract graphs' structures to accurately detect vulnerabilities in smart contract source code at both coarse-grained contract-level and fine-grained line-level.

smart-contract-sanctuary

🐦🌴🌴🌴🦕 A home for ethereum smart contracts. 🏠

STUDY

GPT4scv

An empirical study on detecting smart contract vulnerabilities using ChatGPT

llama

Inference code for Llama models

ReentrancyStudy-Data

oyente

The project has been moved to this new repo https://github.com/melonproject/oyente