Repository di kyegomez

Multi-Modal Multi-Embodied Hivemind-like Iteration of RTX-2

Ultimo commit 27 giu 2025

Implementation of a Hierarchical Mamba as described in the paper: "Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling"

Ultimo commit 17 feb 2024

Lessons from hacking books and resources

Ultimo commit 26 lug 2023

Revolutionize your farm with HarvestNet! Unleash Multi-Modal AI power for smarter, greener, and more sustainable agriculture. Be part of the agro-future now!

Ultimo commit 15 giu 2023

Implementation of the model "Hedgehog" from the paper: "The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry"

Ultimo commit 9 feb 2024

An Implementation of an Transformer model that generates tokens non-linearly all at once like the heptapods from Arrival

Ultimo commit 8 gen 2024

My implementation of Hindsight replay in PyTorch: "Hindsight Experience Replay"

Ultimo commit 25 ott 2023

Automating billions of tasks with millions of autonomous swarms

Ultimo commit 15 lug 2023

First ever AI-designed rocket engine for long distance solar travel.

Ultimo commit 23 set 2024

A table of hyper-parameters used by the largest models. Add your favorite's models hyperparams!

Ultimo commit 20 feb 2025

A curious inquiry into Ihara-Grubb Transformation algorithms from the cyberpunk universe and trying to implement them in the real-world

Ultimo commit 9 nov 2025

Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTORCH

Ultimo commit 15 apr 2024

Open-source repository dedicated to advancing AI Reasoning towards superintelligence.

Ultimo commit 12 mag 2023

InternVideo: General Video Foundation Models via Generative and Discriminative Learning (https://arxiv.org/abs/2212.03191)

Ultimo commit 12 lug 2023

PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"

Ultimo commit 1 apr 2024

This repository demonstrates how to build a Decoder-Only Transformer with Multi-Query Attention in JAX.

Ultimo commit 8 set 2024

Humanity's roadmap

Ultimo commit 16 mag 2023

KNOTX is a new and theoretical activation function designed for ultra-fast multi-modality learning utilizing knot theory + dynamical systems modeling.

Nessun dato recente sui commit

A simple pytorch implementation of a meta learning algorithm from OPENAI "Reptile: A scalable meta-learning algorithm"

Ultimo commit 11 set 2023

My personal implementation of Kosmos-2, Kosmos-2: Grounding Multimodal Large Language Models to the World, much simpler codebase

Ultimo commit 28 ago 2023