AirPods liberated from Apple's ecosystem.

String decrypt plugin powered by unicorn engine

Source Code Obfuscation And Binary Obfuscation, Multiple Languages And Multiple Platforms. Including 250+ Tools and 600+ Posts

An implementation of Shazam's song recognition algorithm.

Process Android Memory Dumper

A tool that can share DeviceOwner permissions to other application.

Collection of leaked system prompts

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

smolbox of recipies

prime is a framework for efficient, globally distributed training of AI models over the internet.

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Unofficial Scalable-Softmax Is Superior for Attention

A *tuned* minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Rectified Rotary Position Embeddings

maximal update parametrization (µP)

🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

Research projects built on top of Transformers

verl: Volcano Engine Reinforcement Learning for LLMs

Model Activity Visualiser

Indi language BPE tokenization

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

🚀 Efficient implementations of state-of-the-art linear attention models

A hooking framework, symbol rebinder and memory-manager for jailed IOS, All-In-One.

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

Doge Family of Small Language Models

Minimalistic large language model 3D-parallelism training

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Supercharge Your Model Training