Stars
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
A TTS model capable of generating ultra-realistic dialogue in one pass.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
This repository hosts a collection of datasets for training and evaluating CUA / GUI agents.
Get your documents ready for gen AI
A curated learning repository focused on High-Performance Computing (HPC) — covering fundamentals to advanced topics in CUDA, MPI, C++, and Python-C++ interoperability.
A cross-platform command-line tool to convert images into ascii art and print them on the console. Now supports braille art!
Official PyTorch implementation for "Large Language Diffusion Models"
【NeurIPS 2024】Official implementation of "Visual Fourier Prompt Tuning"
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
N-dimensional Rotary Position Embeddings for PyTorch
Official repo of M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning
Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.
Build effective agents using Model Context Protocol and simple workflow patterns
Convert LLaMA3.1-8B to DeepSeek R1 MLA & MoE (raw)
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
DSPy: The framework for programming—not prompting—language models
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Open Source Text Embedding Models with OpenAI Compatible API
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
python script to download & process data to train a speech-synthesis model of Vietnamese M.C. Nguyễn Ngọc Ngạn
Comprehensive tools for building (Retrieval Augmented Generation) RAG chatbots.
Built and deployed scalable LLM retrieval APIs on a hybrid GCP architecture with full CI/CD, IaC, and monitoring