Agentic components of the Llama Stack APIs

Repository to learn Azure from Zero. This repository covers the complete Azure fundamentals required for a DevOps Engineer.

LLM101n: Let's build a Storyteller

tha3, but run 40fps on 3080 with virtural webcam support

Faster Whisper transcription with CTranslate2

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Building a modern alternative to Salesforce, powered by the community.

Open-Sora: Democratizing Efficient Video Production for All

An implementation of masked language modeling for Pytorch, made as concise and simple as possible

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Ongoing research training transformer models at scale

Supercharge Your Model Training

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

A massively parallel, high-level programming language

Kolmogorov Arnold Networks

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

LLM training in simple, raw C/CUDA

A complete computer science study plan to become a software engineer.

Instant voice cloning by MyShell.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

GPT based autonomous agent that does online comprehensive research on any given topic

OpenUI let's you describe UI using your imagination, then see it rendered live.

#1 Locally hosted web application that allows you to perform various operations on PDF files

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

🐚 OpenDevin: Code Less, Make More

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…