kyegomez

VisionMamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

PALM-E

Implementation of "PaLM-E: An Embodied Multimodal Language Model"

swarms-pytorch

Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊

Python-Package-Template

A easy, reliable, fluid template for python packages complete with docs, testing suites, readme's, github workflows, linting and much much more

MambaByte

Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta

MoE-Mamba

Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Zeta

metnet3

An implementation of "metnet3" in Pytorch

Mirasol

Pytorch Implementation of the Model from "MIRASOL3B: A MULTIMODAL AUTOREGRESSIVE MODEL FOR TIME-ALIGNED AND CONTEXTUAL MODALITIES"

MLXTransformer

Simple Implementation of a Transformer in the new framework MLX by Apple

SwitchTransformers

Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"

TeraGPT

Train a production grade GPT in less than 400 lines of code. Better than Karpathy's verison and GIGAGPT

USM

Implementation of Google's USM speech model in Pytorch

FastFF

Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"

M2PT

Implementation of M2PT in PyTorch from the paper: "Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities"

Qwen-VL

My personal implementation of the model from "Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities", they haven't released model code yet sooo...

Poly

A Fluid, PolyMorphic,and shapeless Types Package that activates radically flexiblity and simplicity in your programs

GATS

Implementation of GATS from the paper: "GATS: Gather-Attend-Scatter" in pytorch and zeta

SoundStream

Implementation of SoundtStream from the paper: "SoundStream: An End-to-End Neural Audio Codec"

CELESTIAL-1

Omni-Modality Processing, Understanding, and Generation

FlamingoZeta

Flamingo Implemnted in Zeta + Pytorch primitives for high performance multi-modal learning

Midas

Implementation of Midas from [Towards Robust Monocular Depth Estimation] in Pytorch and Zeta

ShallowFF

Zeta implemantion of "Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers"

SwarmsDiscord

A discord bot that can do anything.

GiediPrime

An experimental architecture using Mixture of Attentions with sandwiched Maracron Feedforward's and other modules

TritonTransformer

Transformer Implementation in Triton

AoA-torch

Implementation of Attention on Attention in Zeta

AutoGPT

An experimental open-source attempt to make GPT-4 fully autonomous.

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

gill

🐟 Code and models for the paper "Generating Images with Multimodal Language Models".

med-flamingo1