安迪·肖 (AndyShaw01)

AndyShaw01

Geek Repo

Company:University of Chinese Academy of Sciences

Location:Beijing, China

Github PK Tool:Github PK Tool

安迪·肖's starred repositories

Reflection_Tuning

[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Language:PythonStargazers:70Issues:0Issues:0

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

Language:PythonLicense:Apache-2.0Stargazers:4281Issues:0Issues:0

ProLLaMA

A Protein Large Language Model for Multi-Task Protein Language Processing

Language:PythonLicense:Apache-2.0Stargazers:119Issues:0Issues:0

DPR

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

Language:PythonLicense:NOASSERTIONStargazers:1684Issues:0Issues:0

PoisonedRAG

[USENIX Security 2025] PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models

Language:PythonStargazers:51Issues:0Issues:0

Open-Prompt-Injection

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

Language:PythonStargazers:113Issues:0Issues:0

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Language:PythonLicense:MITStargazers:11561Issues:0Issues:0

llm.c

LLM training in simple, raw C/CUDA

Language:CudaLicense:MITStargazers:22745Issues:0Issues:0

KnowledgeCircuits

Knowledge Circuits in Pretrained Transformers

Language:PythonLicense:MITStargazers:36Issues:0Issues:0

Clip_crossmodal_retrieval

CLIP Crossmodal retrieval with moscoco and flickr for zero-shot and fine-tune

Language:PythonStargazers:3Issues:0Issues:0

yt-dlp

A feature-rich command-line audio/video downloader

Language:PythonLicense:UnlicenseStargazers:80585Issues:0Issues:0

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

Language:Jupyter NotebookLicense:MITStargazers:12655Issues:0Issues:0

chat_templates

Chat Templates for 🤗 HuggingFace Large Language Models

Language:JinjaLicense:MITStargazers:416Issues:0Issues:0

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Language:PythonLicense:Apache-2.0Stargazers:29368Issues:0Issues:0

Megatron-LM

Ongoing research training transformer models at scale

Language:PythonLicense:NOASSERTIONStargazers:9733Issues:0Issues:0

Universal-Prompt-Injection

The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".

Language:PythonStargazers:26Issues:0Issues:0

CrossModal-HomeWork

Record homework for UCAS's cross-modal course

Language:PythonStargazers:4Issues:0Issues:0

Aurora

🐳 Aurora is a [Chinese Version] MoE model. Aurora is a further work based on Mixtral-8x7B, which activates the chat capability of the model's Chinese open domain.

Language:PythonLicense:Apache-2.0Stargazers:257Issues:0Issues:0

GmSSL

支持国密SM2/SM3/SM4/SM9/SSL的密码工具箱

Language:CLicense:Apache-2.0Stargazers:5017Issues:0Issues:0

Chinese-Mixtral

中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)

Language:PythonLicense:Apache-2.0Stargazers:571Issues:0Issues:0

traffic_classification_utils

网络流量分类对比方法汇总

Language:PythonStargazers:130Issues:0Issues:0

TAADpapers

Must-read Papers on Textual Adversarial Attack and Defense

Language:PythonLicense:MITStargazers:1480Issues:0Issues:0

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。

Language:PythonLicense:GPL-3.0Stargazers:63368Issues:0Issues:0

SecGPT

SecGPT网络安全大模型

Language:PythonLicense:Apache-2.0Stargazers:1681Issues:0Issues:0

Video-LLaVA

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Language:PythonLicense:Apache-2.0Stargazers:2799Issues:0Issues:0

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.

Language:PythonLicense:Apache-2.0Stargazers:12131Issues:0Issues:0

VulHawk

This is the official repository for VulHawk.

Language:PythonLicense:MITStargazers:61Issues:0Issues:0

RetNet

An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

Language:PythonLicense:MITStargazers:1152Issues:0Issues:0

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

Language:JavaLicense:NOASSERTIONStargazers:93547Issues:0Issues:0

torchscale

Foundation Architecture for (M)LLMs

Language:PythonLicense:MITStargazers:2990Issues:0Issues:0