assimilator101

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Language:PythonApache-2.01180700

imaginAIry

Pythonic AI generation of images and videos

Language:PythonMIT782400

whisper.cpp

Port of OpenAI's Whisper model in C/C++

Language:CMIT3217700

PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Language:PythonMIT761500

GLM-130B

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Language:PythonApache-2.0762700

armrest

UI / HWR library for the reMarkable tablet

Language:RustApache-2.02700

incubator-pegasus

Apache Pegasus - A horizontally scalable, strongly consistent and high-performance key-value store

Language:C++Apache-2.0194700

wren

The Wren Programming Language. Wren is a small, fast, class-based concurrent scripting language.

Language:WrenMIT677800

scala-markov

A Markov Chain Generator In Scala

Language:Scala1400

XiangShan

Open-source high-performance RISC-V processor

Language:ScalaNOASSERTION438700

Metascala

A JVM written in Scala

Language:Scala117000

apalache

APALACHE: symbolic model checker for TLA+ and Quint

Language:ScalaApache-2.041400

uvc-util

USB Video Class (UVC) control management utility for Mac OS X

Language:Objective-CMIT10300

proxygen

A collection of C++ HTTP libraries including an easy to use HTTP server.

Language:C++NOASSERTION803900

fatal

Fatal is a library for fast prototyping software in modern C++. It provides facilities to enhance the expressive power of C++. The library is heavily based on template meta-programming, while keeping the complexity under-the-hood.

Language:C++NOASSERTION100100