CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

A simple screen parsing tool towards pure vision based GUI agent

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

StableLM: Stability AI Language Models

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

this repository accompanies the book "Grokking Deep Learning"

Puzzles for learning Triton

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Developer APIs to Accelerate LLM Projects

comparing stand up comedians using natural language processing

Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.

Analysis and datasets about football (soccer)

SkillCorner Open Data with 10 matches of broadcast tracking data.

Graph based retrieval + GenAI = Better RAG in production

The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository contains the implementation of the flowing paper htt…

A C++ monorepo for discrete and continuous optimization. Batteries included!

Last row tracking data and code

Computer vision based technologies implemented using tensorflow from ground up