Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
You like pytorch? You like micrograd? You love tinygrad! ❤️
Integrate cutting-edge LLM technology quickly and easily into your apps
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
Haptic input knob with software-defined endstops and virtual detents
🧮 A collection of resources to learn mathematics for machine learning
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
TypeScript-first expansion pack for TanStack Query that gives you Protobuf superpowers.
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
A pure Python LR/GLR parser - http://www.igordejanovic.net/parglare/
NPTEL2020: Speech2Text dataset for Indian-English Accent
Build awesome Golang desktop apps and beautiful interfaces with Vue.js, React.js, Framework 7, and more...
An idiomatic protobuf generator for TypeScript
High-performance extensible build system for reproducible multi-language builds.
Simple, fast, safe, compiled language for developing maintainable software. Compiles itself in <1s with zero library dependencies. Supports automatic C => V translation. https://vlang.io
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
Ongoing research training transformer models at scale
ibnuda / dactyl-keyboard
Forked from tshort/dactyl-keyboardWeb generator for dactyl keyboards.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)