GuangkeChen's repositories
awesome-llm-security
A curation of awesome tools, documents and projects about LLM Security.
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
Baichuan-13B
A 13B large language model developed by Baichuan Intelligent Technology
CPAD
The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".
CRoSS
[NeurIPS 2023] Official PyTorch implementation for the paper "CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography"
Diff-PGD
[NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
fast-detect-gpt
Code base for "Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature".
GPTFuzz
Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Grad-SVC
Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei
GuangkeChen.github.io
The resources of my website
leon
🧠 Leon is your open-source personal assistant.
llark
Code for the paper "LLark: A Multimodal Foundation Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.
LLaSM
第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验,同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
lm-ssp
A reading list for large models safety, security, and privacy.
MOSS
An open-source tool-augmented conversational language model from Fudan University
musiclm-pytorch
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
OpenVoice
Instant voice cloning by MyShell.
OPERA
[CVPR 2024] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
Pengi
An Audio Language model for Audio Tasks
persuasive_jailbreaker
Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!
Qwen-Audio
The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.
Retrieval-based-Voice-Conversion-WebUI
Voice data <= 10 mins can also be used to train a good VC model!
SALMONN
SALMONN: Speech Audio Language Music Open Neural Network
stable_signature
Official implementation of the paper "The Stable Signature Rooting Watermarks in Latent Diffusion Models"
synthea
Synthetic Patient Population Simulator
TrustLLM
TrustLLM: Trustworthiness in Large Language Models
UnIVAL
[TMLR23] Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.