Rich is a Python library for rich text and beautiful formatting in the terminal.

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Automatic headphone equalization from frequency responses

Hierarchical Reasoning Model Official Release

TinyDB is a lightweight document oriented database optimized for your happiness :)

Real-Time High-Resolution Background Matting

PyTorch implementations of deep reinforcement learning algorithms and environments

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Common User Passwords Profiler (CUPP)

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

Deep neural networks for voice conversion (voice style transfer) in Tensorflow

💫 Ngrok FRP Alternative • ⚡ Fast • 🪶 Lightweight • 0️⃣ Dependency • 🔌 Pluggable • 😈 TLS interception • 🔒 DNS-over-HTTPS • 🔥 Poor Man's VPN • ⏪ Reverse & ⏩ Forward • 👮🏿 "Proxy Server" framework • 🌐 …

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Foundation Architecture for (M)LLMs

Flops counter for neural networks in pytorch framework

Defeating Google's audio reCaptcha with 85% accuracy.

Schedule-Free Optimization in PyTorch

Projects motion of pixels to a voxel

DDoS attack tool for sending forged UDP packets to vulnerable Memcached servers obtained using Shodan API

Genetic neural architecture search with Keras

Human-readable digests.

An on-disk B+tree for Python 3

A open source reimplementation of Google's Tensor Processing Unit (TPU).

A neural network for end-to-end speech denoising

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Provider-agnostic, open-source evaluation infrastructure for language models