nancyjlau's Stars
Nerogar/OneTrainer
OneTrainer is a one-stop solution for all your stable diffusion training needs.
naklecha/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
HLSTransform/submission
OpenMask3D/openmask3d
athen-lab/mai
Multilayer Authenticity Identifier (MAI), a CNN model that attempts to identify synthetic AI images.
pytorch/torchtitan
A PyTorch native library for large model training
apple/corenet
CoreNet: A library for training deep neural networks
google-deepmind/penzai
A JAX research toolkit for building, editing, and visualizing neural networks.
HyperDbg/hwdbg
HyperDbg's logic analyzer and chip-level hardware debugger
meta-llama/llama3
The official Meta Llama 3 GitHub site
dmMaze/sketch2manga
Apply screentone to line drawings or colored illustrations with diffusion models.
huggingface/cosmopedia
mistralai/mistral-common
prompt-security/ps-fuzz
Make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt
ollama/ollama
Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.
insula-rs/libwhp
Windows Hypervisor Platform Rust crate
SWE-agent/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
argmaxinc/WhisperKit
On-device Speech Recognition for Apple Silicon
amlweems/xzbot
notes, honeypot, and exploit demo for the xz backdoor (CVE-2024-3094)
tinygrad/7900xtx
fr3fou/gone
neural network library in go from scratch
KohakuBlueleaf/LyCORIS
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
fuzzland/girlfriend
Girl Friend <- Generate Foundry Fork Test from Attack Transaction
hpcaitech/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
AnswerDotAI/fsdp_qlora
Training LLMs with QLoRA + FSDP
yogeshojha/rengine
reNgine is an automated reconnaissance framework for web applications with a focus on highly configurable streamlined recon process via Engines, recon data correlation and organization, continuous monitoring, backed by a database, and simple yet intuitive User Interface. reNgine makes it easy for penetration testers to gather reconnaissance with minimal configuration and with the help of reNgine's correlation, it just makes recon effortless.
shellphish/how2heap
A repository for learning various heap exploitation techniques.
amaranth-lang/amaranth
A modern hardware definition language and toolchain based on Python
carlini/yet-another-applied-llm-benchmark
A benchmark to evaluate language models on questions I've previously asked them to solve.
Speykious/cve-rs
Blazingly 🔥 fast 🚀 memory vulnerabilities, written in 100% safe Rust. 🦀