安迪·肖's starred repositories
Reflection_Tuning
[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
PoisonedRAG
[USENIX Security 2025] PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models
Open-Prompt-Injection
This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses
KnowledgeCircuits
Knowledge Circuits in Pretrained Transformers
Clip_crossmodal_retrieval
CLIP Crossmodal retrieval with moscoco and flickr for zero-shot and fine-tune
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
chat_templates
Chat Templates for 🤗 HuggingFace Large Language Models
LLaMA-Factory
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
Megatron-LM
Ongoing research training transformer models at scale
Universal-Prompt-Injection
The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".
CrossModal-HomeWork
Record homework for UCAS's cross-modal course
Chinese-Mixtral
中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)
traffic_classification_utils
网络流量分类对比方法汇总
TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
Video-LLaVA
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
hello-algo
《Hello 算法》:动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新,English version ongoing
torchscale
Foundation Architecture for (M)LLMs