corranmac

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

dspy

DSPy: The framework for programming—not prompting—foundation models

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

fiftyone

The open-source tool for building high-quality datasets and computer vision models

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

google-indexing-script

Script to get your site indexed on Google in less than 48 hours

DeepSpeedExamples

Example models using DeepSpeed

CoDeF

[CVPR 2024 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

fastapi-users

Ready-to-use and customizable users management for FastAPI

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

rift

Rift: an AI-native language server for your personal AI software engineer

SVD_Xtend

Stable Video Diffusion Training Code and Extensions.

lumos

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

prompt-lookup-decoding

knnlm

50Algorithms

qwikidata

Python tools for interacting with Wikidata

SEARLE

[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

rng-kbqa

SkyScript

Official repo for "SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing"

entity-related-papers

Named Entity Recognition, Entity Linking, and more

NEUTART

PyTorch implementation of NEUTART, a system that creates photorealistic talking avatars from an input text transcription.

llm-science-exam

6th Position Solution Code for Kaggle - LLM Science Exam Competition

awesome-industrial-symbiosis

Databases and other resources for Industrial Symbiosis

un-knowledge-extraction

The goal is to pilot Microsoft Cognitive Services to unlock the strategic value of UN unstructured content by building on AI and semantic technologies. The idea is to showcase the innovative smart services that natural language processing and machine learning to effectively support policy and decision making, coordination, synergies and accountability.

Localized-CNNs-for-Geospatial-Wind-Forecasting

Code for "Localized Convolutional Neural Networks for Geospatial Wind Forecasting"

BLIP-Adapter

ideas

Ideas on making the world data useful for ML by building and maintaining reusable tools.

datasets-for-sequential-sentence-classification

Curated list of public datasets which focus on sentence classification in academic papers or abstracts

restgdf

improved esri rest io for geopandas