YixingLuo

MinerU

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

PDEval

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

tapas

End-to-end neural table-text understanding models.

airllm

AirLLM 70B inference with single 4GB GPU

NoRBERT

Requirements classification approach using BERT's transfer learning capabilities

mllm

Fast Multimodal LLM on Mobile Devices

ChatLaw

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

qlora-chinese-LLM

使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE

chatGLM-6B-QLoRA

使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

Efficient_Foundation_Model_Survey

Survey Paper List - Efficient LLM and Foundation Models

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

reqclass

Requirements Classification

fret

A framework for the elicitation, specification, formalization and understanding of requirements.

CodeGeeX

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

CodeGeeX2

CodeGeeX2: A More Powerful Multilingual Code Generation Model

HighwayEnv

A minimalist environment for decision-making in autonomous driving

rrt-algorithms

n-dimensional RRT, RRT* (RRT-Star)

tool-competition-av

The repository hosts the code for the SBST CPS Tool competition for testing autonomous cars.

Test-case-Prioterization-using-Genetic-Algorithm

Prioritize test case scenarios by identifying the critical path cluster using Genetic algorithm

test-case-prioritisation-ga

SPECTRE

OUCML

river

🌊 Online machine learning in Python

BeamNGpy

Python API for BeamNG.tech

leetcode-master

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

SMARTS

Scalable Multi-Agent RL Training School for Autonomous Driving

style-check

Style checker for latex documents

awesome-fuzzing

A curated list of awesome Fuzzing(or Fuzz Testing) for software security

jMetalPy

A framework for single/multi-objective optimization with metaheuristics