Open-source alternatives to Tiny Universe

This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

tiny-llm is a large language model inference engine and transformer model implementation. It serves as a quantized model runtime and paged key-value cache manager, providing a specialized inference stack optimized for Apple Silicon. The system distinguishes itself through high-throughput execution techniques, including continuous batching and paged attention. It utilizes a paged memory system to eliminate fragmentation during token generation and employs on-the-fly dequantization of compressed weights to reduce the memory footprint during matrix multiplication. The project covers a broad ran

This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum

x-transformers is a PyTorch library and research toolkit for building transformer architectures. It provides a modular framework for implementing experimental transformer research, including a suite of advanced attention mechanisms, long-sequence modeling tools, and a framework for vision transformers. The project is distinguished by its focus on memory-efficient and high-performance components, such as Flash Attention with tiled kernels and multi-query attention. It also implements specialized methods for extending context windows, including sequence recurrence and rotary positional embeddin

This project is a manual reconstruction of the Llama 3 transformer architecture implemented as a PyTorch neural network. It serves as a reference for the internal mathematical structure and tensor flow of a transformer-based language model designed for next token prediction. The implementation focuses on building the model from scratch using basic matrix operations and tensor manipulations. It demonstrates the manual construction of core components, including rotary positional embeddings, multi-head self-attention, and root mean square normalization. The codebase covers the full inference pi

TransformerLens is a library for mechanistic interpretability research designed to reverse engineer the learned algorithms within large language models. It provides a standardized framework for wrapping diverse transformer architectures, allowing researchers to extract, manipulate, and analyze internal activations and weights through a consistent interface. The project distinguishes itself through a comprehensive system of activation hooks that can capture, patch, and ablate internal tensors during the forward pass. It includes specialized utilities for decomposing fused projections, material

This project is a collection of deep learning research implementations and a reproduction kit designed to translate theoretical AI papers into working code. It provides a library of neural network architectures and reference implementations for reproducing seminal research concepts through interactive notebooks. The repository distinguishes itself through the implementation of AI theory and scaling laws, covering complexity dynamics, information theory, and the simulation of universal AI agents. It also includes a benchmarking suite for synthetic reasoning, allowing for the evaluation of mode

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

Qwen2.5-Coder is a code-centric large language model designed to generate, complete, and analyze source code. It serves as a polyglot programming model capable of producing functional code across hundreds of different programming languages. The model is optimized for reasoning over extensive software repositories, utilizing a context window that supports up to one million tokens. It also functions as an agentic coding framework, executing multi-step workflows and browser tasks through specialized function call formats. Its capabilities include large-scale codebase analysis, intelligent parti

This project is a Transformer machine translation model and attention-based neural network implemented using the PyTorch deep learning framework. It functions as a text-to-text translation tool designed to convert source sequences into target language text. The implementation focuses on neural machine translation, covering the development of sequence-to-sequence architectures. It includes the full pipeline for translation, from text sequence preprocessing and vocabulary creation to model training and text generation inference. The system incorporates standard transformer components such as a

This project is a PyTorch implementation of an attention-based neural network designed for sequence-to-sequence deep learning tasks. It serves as a library for constructing deep learning sequence models that utilize encoder and decoder structures to process natural language and sequential data. The implementation centers on a multi-head attention mechanism to capture diverse relationships between tokens without using recurrence. It includes sinusoidal positional encoding to maintain sequence order and point-wise feed-forward networks to transform token positions independently. The architectu

FalkorDB is a high-performance graph database management system and vector graph database. It serves as a knowledge graph construction tool and a GraphRAG knowledge store, integrating structured property graphs with vector search to provide grounded context for large language models. The engine is designed as a multi-tenant graph engine, capable of hosting thousands of isolated datasets within a single instance. The system distinguishes itself by using linear algebra for query execution, treating relationship tensors as matrix multiplications to achieve low-latency multi-hop traversals. It ut

LangChain4j is a framework and library for building applications powered by large language models on the JVM. It provides a unified API for developing AI agents, implementing retrieval augmented generation, and integrating generative AI capabilities into professional software built with frameworks like Spring Boot or Quarkus. The project enables the creation of autonomous agents that can reason through tasks, manage memory, and execute external tools to achieve specific goals. It differentiates itself through a unified model interface that allows developers to switch between multiple model pr

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

This project is a comprehensive framework for constructing, managing, and evaluating knowledge graphs through multi-agent reasoning and deep search capabilities. It provides an end-to-end pipeline that ingests multi-format documents, extracts entities and relationships based on configurable schemas, and maintains structured knowledge bases to support evidence-based retrieval. The system distinguishes itself through its multi-agent orchestration, which decomposes complex queries into parallel research steps and synthesizes long-form reports. It leverages advanced graph-based techniques, includ

Open Llama is an open source large language model and pre-trained transformer designed as a permissively licensed alternative to proprietary weights. It serves as a base model reproduction of the Llama architecture, providing a set of weights for a decoder-only transformer. The project provides a transparently trained model based on the RedPajama dataset, supporting unrestricted commercial and research use. It includes systems for serving pre-trained weights in various sizes. The project covers natural language processing research and performance benchmarking through text quality evaluation

This project is a comprehensive machine learning interview guide and technical study resource designed for individuals preparing for machine learning and AI engineering roles. It provides a collection of materials and practice problems covering core algorithms, theoretical fundamentals, and the implementation of neural network architectures. The resource serves as a technical reference for generative AI development, focusing on the design and optimization of large language models and diffusion systems. It includes frameworks for system design, covering the architecture of production machine l

DeepSeek-LLM is a large language model and causal language model designed for natural language generation. It functions as a multi-lingual system capable of predicting the next token in a sequence to perform text completion and conversational generation. The model is specialized for logical reasoning, specifically as a code and math LLM. This enables it to perform complex problem solving, which includes generating executable code and solving mathematical equations through step-by-step analysis. The system's broader capabilities cover conversational AI, including the generation of chat comple

gpt-neox is a distributed training system and framework for building large-scale autoregressive language models. It implements the transformer architecture and provides a toolkit for training models with billions of parameters by distributing weights across compute clusters. The framework distinguishes itself through extensive support for distributed model parallelism, including pipeline and sequence parallelism, to overcome single-device memory limits. It further supports sparse model architectures using a mixture of experts system with Sinkhorn-based routing. The project covers a broad ran

This project is a TensorFlow implementation of a transformer model, providing a text-to-text deep learning framework designed to recognize and generate sequence patterns. It functions as an attention-based sequence model and a neural machine translation framework for converting text from one language to another. The system implements the transformer network architecture, utilizing multi-head attention and positional encoding to process sequential data. It provides the necessary tools for transformer model training and machine translation inference, allowing for the execution of trained models

LeetCUDA is a collection of high-performance GPU kernel libraries focusing on memory optimization, activation functions, and attention mechanisms. It serves as a reference library for CUDA kernel implementations, ranging from basic element-wise operations to complex neural network components, and provides Python bindings to integrate these kernels into deep learning workflows. The project is distinguished by its focus on low-level hardware optimizations. This includes the use of tensor cores for half-precision matrix multiplication, asynchronous data pipelining with double buffering, and shar

FlashInfer is a library of high-performance GPU kernels purpose-built for accelerating large language model inference. It provides optimized implementations for attention operations (including flash attention, page attention, multi-head latent attention, and cascade attention) using paged key-value caches, fused kernel composition, and just-in-time compilation. The library also includes specialized kernels for mixture-of-experts layers, block-scaled low-precision quantization (FP8, FP4), and distributed collective communication. What distinguishes FlashInfer is its fused all-reduce communicat

llmware is a Python framework for AI agent orchestration and model management, designed to coordinate multi-model workflows and autonomous agents. It provides a unified model catalog and standardized interface to execute specialized language models for complex research, analysis, and structured data generation. The project distinguishes itself through its heavy emphasis on local execution and quantized inference, allowing models to run on private infrastructure using CPU, GPU, and NPU acceleration via runtimes like ONNX and OpenVino. It features a specialized ability to translate natural lang

Gemma is a family of open-weights large language models based on a decoder-only transformer architecture. These models are designed for text generation and multi-modal conversations, capable of processing and generating responses based on both textual and visual input sequences. The project provides a fine-tunable AI model that supports weight adjustment and low-rank adaptation to specialize performance for particular tasks. It includes support for quantized weights to reduce memory usage and increase inference speed on limited hardware. The capability surface covers multi-modal AI integrati

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

This project is a retrieval augmented generation framework designed to build pipelines that connect unstructured data and knowledge graphs with large language models. It functions as a vector database orchestrator for indexing text and multimodal content, as well as a system for translating natural language queries into structured database commands. The framework integrates a hybrid retrieval engine that combines dense vector search with sparse keyword matching to increase the precision of retrieved contexts. It further enhances reasoning and relationship mapping through a graph-augmented ret

This project is a diffusion model training framework and image synthesis pipeline. It provides the tools necessary to train generative models to learn image data distributions through an iterative denoising process. The framework includes a generative model evaluation tool consisting of automated scripts used to measure the quality and accuracy of produced samples. The system covers model training pipelines and performance evaluation for generative diffusion models.