A Data Streaming Library for Efficient Neural Network Training

Supercharge Your Model Training

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

A modular graph-based Retrieval-Augmented Generation (RAG) system

LlamaIndex is a data framework for your LLM applications

Open-source RAG Framework for building GenAI Second Brains 🧠 Build productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic…

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Fast and memory-efficient exact attention

You like pytorch? You like micrograd? You love tinygrad! ❤️

Tensors and Dynamic neural networks in Python with strong GPU acceleration

An Open Source Machine Learning Framework for Everyone

Hackable and optimized Transformers building blocks, supporting a composable construction.

Drift Detection for your PyTorch Models

Always know what to expect from your data.

Tensor library for machine learning

Optimized primitives for collective multi-GPU communication

Collective communications library with various primitives for multi-machine training.

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Official repository of Evolutionary Optimization of Model Merging Recipes

Tools for merging pretrained large language models.

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

the portable Python dataframe library

DuckDB is an analytical in-process SQL database management system

Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind

The memory layer for Personalized AI

DSPy: The framework for programming—not prompting—foundation models

Go ahead and axolotl questions