196sigma

stable-diffusion

A latent text-to-image diffusion model

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

OpenHands

🙌 OpenHands: Code Less, Make More

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

marker

Convert PDF to markdown quickly with high accuracy

flash-attention

Fast and memory-efficient exact attention

FinRL

FinRL: Financial Reinforcement Learning. 🔥

claude-engineer

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capabilities of a large language model with practical file system operations and web search functionality.

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

gpt-neox

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

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Time-Series-Library

A Library for Advanced Deep Time Series Models.

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Merlion

Merlion: A Machine Learning Framework for Time Series Intelligence

MLPP

A library created to revitalize C++ as a machine learning front end. Per aspera ad astra.

math-lm

texify

Math OCR model that outputs LaTeX and markdown

DataStructuresAlgorithms

500+ Data Structures and Algorithms practice problems

cookbook

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

DisTrO

Distributed Training Over-The-Internet

torchlens

Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.

scribepod

Some of the scripts I use for scribepod @ https://scribepod.substack.com/, an automated AI podcast

DeeperSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

samformer

Official implementation of SAMformer, a transformer leveraging Sharpness-Aware Minimization and Channel-Wise Attention for Time Series Forecasting.

awesome-neurips-2023

Conference schedule, top papers, and analysis of the data for NeurIPS 2023!

TensorHue

TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor contents easier.

Causal-Discovery-from-Nonstationary-Heterogeneous-Data

Causal Discovery from Nonstationary/Heterogeneous Data.

hdflex

This repository contains the R-Package for a novel time series forecasting method designed to handle very large sets of predictive signals, many of which are irrelevant or have only short-lived predictive power.