mrpositron

LLM101n

LLM101n: Let's build a Storyteller

overleaf

A web-based collaborative LaTeX editor

Perplexica

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

frame-interpolation

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

llm.c

LLM training in simple, raw C/CUDA

grok-1

Grok open release

yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

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), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

awesome-tips

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

aedat

A fast AEDAT 4 python decoder.

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

aestream

Efficient streaming of sparse event data supporting files, network I/O, GPU peripherals (via Torch/Jax/Numpy) and neuromorphic protocols

faces-in-event-streams

This repo contains code and instructions for the detection of faces in event streams

GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

nllb-pruning

Library for pruning experts per language pair in NLLB-200

event-based_vision_resources

Minipad

Minipad - simple text editor written with PyQt.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

open-neuromorphic

List of open source neuromorphic projects: SNN training frameworks, DVS handling routines and so on.

snntorch

Deep and online learning with spiking neural networks in Python

tonic

Publicly available event datasets and transforms.

emoca

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

mayavi

3D visualization of scientific data in Python

ReMoDiffuse

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model