claude code system prompt

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Video Annotation Tool

Fast and memory-efficient exact attention

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

ModelScope: bring the notion of Model-as-a-Service to life.

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

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io

A Python tool to visualize + enforce dependencies, using modular architecture 🌎 Open source 🐍 Installable via pip 🔧 Able to be adopted incrementally - ⚡ Implemented with no runtime impact ♾️ Intero…

Minimal reproduction of DeepSeek R1-Zero

Scalable and user friendly neural 🧠 forecasting algorithms.

Calculates various features from time series data. Python implementation of the R package tsfeatures.

Lightning ⚡️ fast forecasting with statistical and econometric models.

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Simple text to phones converter for multiple languages

prime is a framework for efficient, globally distributed training of AI models over the internet.

Machine Learning Engineering Open Book

A generative world for general-purpose robotics & embodied AI learning.

Code for BLT research paper

NanoGPT (124M) quality in 2.67B tokens

Mamba SSM architecture

Tabular Deep Learning Library for PyTorch

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)