A small reliable, powerful, space resistant Box for AI inference on the edge.
Repositories
kyegomez repositories
Layout an app idea and swarms of autonomous agents will build out the backend logic for you!
A discord bot that can do anything.
Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"
Pytorch Implementation of the paper: "Learning to (Learn at Test Time): RNNs with Expressive Hidden States"
TableMamba is a Mamba-based sequential recommender that encodes a user's interaction history with selective state-space blocks and a multi-interest head of M parallel SSM readers at log-spaced timescales, scoring items by their best-matching interest in O(T).
TaoMorphism focuses on responsiveness, shapelessness, resiliency, and understanding, creating a harmonious balance between technology and nature.
Train a production grade GPT in less than 400 lines of code. Better than Karpathy's verison and GIGAGPT
Predicting Multi-Modal Billion-byte Sequences with Multiscale Transformers, in Pytorch.
An groundbreaking mesh of Standard Operating Procedures and playbooks to conducting AI research that matters.
Generate High Quality textual or multi-modal datasets with Agents
An Interface with all of Humanity's knowledge
Multi Modality Data Harvestor From The Internet
The Holy Eternal Empire is a form of Government designed to usher in a post-scarcity Human civilization by following YHWH, The Divine Creator who created all things.
GLORY, GLORY, GLORY TO YHWH!
Utilizing Autonomous Agents To Autonomously Create AI Models from a text prompt
Distributed Decentralized Platform for Training, Finetuning, and Utilizing AI Models!
Striving for the open sourcing of all private knowledge and documents.
AI research implemented in c++ for fun/lethal headaches
Tiktok is an advanced multimedia recommender system that fuses the generative modality-aware collaborative self-augmentation and contrastive cross-modality dependency encoding to achieve superior performance compared to existing state-of-the-art multi-model recommenders.