This repository holds the infrastructure to serve Kosmos to customers.
Repositories
kyegomez repositories
The Next Generation Multi-Modality Superintelligence
My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"
My implementation of the model KosmosG from "KOSMOS-G: Generating Images in Context with Multimodal Large Language Models"
API for Deploying Kosmos-X
An open source implementation of LFMs from Liquid AI: Liquid Foundation Models
A simple and minimal open source implementation of "Introducing LFM2: The Fastest On-Device Foundation Models on the Market" from Liquid AI in Pytorch
Implementation of the "the first large-scale multimodal mixture of experts models." from the paper: "Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts"
Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"
Plug in and Play implementation of "Certified Reasoning with Language Models" that elevates model reasoning by 40%
Implementation of the text to video model LUMIERE from the paper: "A Space-Time Diffusion Model for Video Generation" by Google Research
Open-source pre-training implementation of Google's LaMDA in PyTorch.
The Prompt Guided Neural Architecture Search (PG-NAS) is a PyTorch-based framework designed to generate neural network architectures based on textual prompts.
Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch. A single-file, dependency-light layer you can drop in place of a standard MoE FFN.
A simple implementation of LeNet5 for practice for the book "Pytorch Pocket Reference"
"Improving Mathematical Reasoning with Process Supervision" by OPENAI
A framework to enable bulk processing of Linkedin Leads profile URLs to acquire lead emaisl
Implementation of Liquid Nets in Pytorch
Transform Transformers Into Liquid Transformers
Experiments with Liquid Neural Nets