Top Repositories on Github with TechGarden

An open-source starter kit based on Midday.

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Distributed Training Over-The-Internet

open-source multimodel large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

A 3DGS framework for omni urban scene reconstruction and simulation.

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

Starter Kit for mobile game development using Godot

NLP Zero to Hero in just 10 Kernels