An implementation of SEAL: Safety-Enhanced Aligned LLM fine-tuning via bilevel data selection.

A framework for few-shot evaluation of language models.

[NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

The ultimate LLM/AI application development framework in Golang.

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Implements harmful/harmless refusal removal using pure HF Transformers

企业级RAG系统从入门到精通

文本去重算法，研究自推荐系统中新闻的去重，采用了雅虎的Near-duplicates and shingling算法，服务端用c实现，客户端用java实现，利用thrift框架进行通信，为了提高扩展性，去重可以在服务端实现，服务器也提供了计算的接口，方便客户端自己扩展

这是一个自动收集各大平台热点新闻（更关注 AI热点）、RSS订阅源以及特定Twitter Feed，进行处理、去重、总结，并通过多种渠道推送热点摘要的工具。该项目完全由Cursor和Trae接力编写

Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

The simplest, fastest repository for training/finetuning medium-sized GPTs.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Supercharge Your LLM Application Evaluations 🚀

Evaluation and Tracking for LLM Experiments and AI Agents

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A survey on harmful fine-tuning attack for large language model

An extremely fast Python package and project manager, written in Rust.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Multilingual Voice Understanding Model

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/

Mastering Machine Learning for Penetration Testing, published by Packt

Defund the Police.