davzoku

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

wizmap

Explore and interpret large embeddings in your browser with interactive visualization! 📍

manim

A community-maintained Python framework for creating mathematical animations.

manim

Animation engine for explanatory math videos

videos

Code for the manim-generated scenes used in 3blue1brown videos

Bend

A massively parallel, high-level programming language

SeaEval

NAACL 2024: SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

ThunderKittens

Tile primitives for speedy kernels

Awesome-LLM-for-RecSys

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

ml-sad

recommenders

Best Practices on Recommendation Systems

cudf

cuDF - GPU DataFrame Library

embedding-lenses

muliwai

experimental PII framework

news-crawl

News crawling with StormCrawler - stores content as WARC

python-fire

Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

MetaRec

PyTorch Implementations For A Series Of Deep Learning-Based Recommendation Models

rouge_chinese

Python ROUGE Score Implementation for Chinese Language Task (official rouge score)

faiss

A library for efficient similarity search and clustering of dense vectors.

annoy

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

bun

Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

zig

General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.

llvmlite

A lightweight LLVM python binding for writing JIT compilers

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

cuda-checkpoint

CUDA checkpoint and restore utility

data-preparation

Code used for sourcing and cleaning the BigScience ROOTS corpus

sailcraft

Data Toolkit for Sailor Language Models

trl

Train transformer language models with reinforcement learning.

project-management