WRH's repositories
OpenMMLabCourse
(fork of) OpenMMLab course index and materials
AutoDAN
The official implementation of our paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
cutlass
CUDA Templates for Linear Algebra Subroutines
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
DeepSpeedExamples
Example models using DeepSpeed
flash-attention
Fast and memory-efficient exact attention
generative-ai-for-beginners
12 Lessons, Get Started Building with Generative AI đź”— https://microsoft.github.io/generative-ai-for-beginners/
GPTFuzz
Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
InternLM
InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.
llama
Inference code for LLaMA models
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
ML-For-Beginners
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
playground
A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.
ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
red-instruct
Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
SALAD
SALAD: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
SALAD-BENCH
SALAD benchmark
TAP
TAP: An automated jailbreaking method for black-box LLMs
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.