Open-source alternatives to LLMs From Scratch

This repository serves as a structured educational resource for machine learning and data science, providing a centralized collection of tutorials, lecture notes, and implementation guides. It is designed to support self-directed learning by organizing complex technical concepts into a clear, hierarchical path that spans from foundational statistical methods to advanced deep learning architectures. The project distinguishes itself through a comprehensive approach to skill development, bridging the gap between theoretical algorithmic foundations and functional software applications. It offers

This project is a community-maintained directory that serves as a comprehensive index of software tools, frameworks, and educational materials. It functions as an open-source knowledge base, organizing diverse engineering domains and technical resources into a structured taxonomy to assist developers in discovering high-quality content. The directory distinguishes itself through a decentralized peer-review model, where independent contributors curate, verify, and update entries to ensure accuracy and relevance. All information is stored in a version-controlled, flat-file markdown format, whic

FastChat is a training and serving platform for large language models that provides an integrated toolkit for fine-tuning, hosting, and benchmarking chatbots. It functions as an inference server capable of hosting multiple models and exposing them via a standardized API for chat applications. The platform distinguishes itself through a distributed model controller that manages worker nodes and routes requests across a hardware-agnostic inference layer supporting various accelerators. It includes a dedicated evaluation framework for assessing model quality using automated judges, multi-turn di

Curated list: Resources for machine learning in Ruby

ColossalAI is a distributed deep learning framework designed for training and deploying massive artificial intelligence models across clusters of hardware accelerators. It functions as a parallel computing engine that partitions model workloads and data across multiple processors to maximize memory efficiency and throughput. The platform distinguishes itself through a comprehensive suite of parallelization strategies, including multi-dimensional tensor parallelism and pipeline-based model parallelism, which segment neural network layers and stages across devices. To support large-scale genera

This project is an open-source educational curriculum designed to provide a structured path for developers to master machine learning and generative AI. It functions as a technical skill development platform, offering comprehensive study materials that guide learners through fundamental concepts, algorithms, and the practical implementation of artificial intelligence models from scratch. The curriculum distinguishes itself through a pedagogy centered on interactive Jupyter Notebooks, which allow students to execute code cells directly within narrative documents for immediate visual feedback.

This project is a technical learning resource and developer knowledge base focused on the integration of large language models into software applications. It provides a structured collection of guides and code examples designed to teach developers how to implement intelligent features using proven patterns and best practices. The repository distinguishes itself through a library of functional demonstrations that cover complex topics such as retrieval-augmented generation, function calling, and prompt engineering workflows. These materials are organized into a modular structure, allowing for t

This project is a comprehensive, open-source educational curriculum designed to guide developers through the mastery of generative artificial intelligence. It provides a structured learning path that covers foundational concepts, prompt engineering, and the practical application of large language models. The repository serves as a central hub for skill acquisition, offering sequential modules that progress from basic model mechanics to advanced architectural patterns. The curriculum distinguishes itself by focusing on the end-to-end lifecycle of intelligent software, including the implementat

This repository is an educational collection of deep learning implementations designed to demonstrate the fundamental principles of neural network architecture and optimization. It provides a comprehensive resource for understanding machine learning through hands-on code examples, ranging from basic multilayer perceptrons to complex generative models. The project distinguishes itself by emphasizing the manual construction of models, including the implementation of backpropagation from scratch to illustrate core mathematical mechanics. It covers a wide array of architectural design patterns, s

This project is a comprehensive machine learning educational resource and tutorial series delivered as a collection of interactive Jupyter Notebooks. It provides practical Python implementations for the end-to-end machine learning lifecycle, covering supervised and unsupervised learning, deep learning, and reinforcement learning. The resource distinguishes itself by providing detailed implementation guides for complex architectures, including transformers, generative adversarial networks, and convolutional neural networks. It also features specialized courseware for developing reinforcement l

This is a machine learning educational repository consisting of a collection of notebooks and code examples. It provides practical implementations of diverse machine learning algorithms and workflows, ranging from traditional scientific computing to deep learning. The project features specific implementations of Scikit-Learn models, such as decision trees, random forests, and support vector machines, as well as TensorFlow examples for building neural networks, convolutional layers, and recurrent architectures. It also includes tutorials on reinforcement learning development and the creation o

LLM101n is an educational machine learning curriculum and open-source resource designed to teach the fundamental principles and practical implementation of large language models. It functions as a technical manual that guides users through the end-to-end process of building and training neural network architectures from scratch using a dynamic tensor library for automatic differentiation and GPU-accelerated computation. The project distinguishes itself through interactive, notebook-based instruction that allows for real-time visualization of training processes. It supports rapid experimentati

This project is a collection of interactive Python notebooks and educational resources designed for mastering data science, machine learning, and numerical computing. It provides a series of practical guides and tutorials covering deep learning, big data processing, and statistical analysis. The repository features specialized instructional suites for implementing classical machine learning algorithms, building deep learning model architectures, and managing AWS cloud infrastructure. It includes dedicated notebooks for data visualization and numerical computing exercises. The project covers

This project is a comprehensive collection of machine learning educational resources, featuring a Python-based curriculum, study guides for deep learning, and a specialized knowledge base for machine learning operations. It provides structured learning paths that guide users from foundational programming through to advanced neural network implementations. The repository focuses on interactive learning by providing a directory of executable notebooks and cloud-hosted experiments. It maps theoretical research papers and textbooks to practical code implementations and maintains a curated directo

This project is an open educational curriculum designed to teach the fundamental concepts and practical applications of artificial intelligence. It provides a structured, modular path for developers to build technical proficiency in machine learning, neural networks, computer vision, and natural language processing. The curriculum distinguishes itself through an interactive learning path that integrates executable code blocks directly into the documentation. By utilizing a series of Jupyter notebooks, learners can run experiments, visualize results, and complete hands-on coding exercises with

This project is a comprehensive educational curriculum designed to teach the fundamental concepts, workflows, and tools of data science. It provides a structured learning path that covers the end-to-end data science lifecycle, including data acquisition, maintenance, processing, and pattern discovery, while grounding theoretical knowledge in practical, real-world applications. The curriculum distinguishes itself through a data-driven pedagogical design that utilizes interactive, notebook-based lessons. By combining narrative text with live code blocks, the platform allows learners to experime

This project is a comprehensive technical reference and educational resource designed to improve proficiency with command-line interfaces. It functions as a productivity toolkit, providing a structured knowledge base of essential terminal operations, system administration tasks, and high-impact command sequences for daily development workflows. The guide distinguishes itself through its cross-platform approach, offering standardized documentation that maps utility usage across Linux, macOS, and Windows environments. It provides specific guidance for managing native tools and compatibility lay

LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing

This project is a comprehensive, community-driven directory of machine learning resources, software libraries, and educational materials. It serves as a centralized knowledge base for developers and researchers, organizing tools and frameworks by their primary programming language and technical domain to simplify discovery across the artificial intelligence ecosystem. The collection distinguishes itself by providing a cross-language development index that spans diverse programming environments, including C, C++, Rust, Clojure, and Python. It covers a wide range of specialized capabilities, fr

Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and

BigDL is a PyTorch acceleration framework and distributed inference engine designed for large language models. It provides a toolkit for running models on Intel hardware, integrating quantization tools and libraries for parameter-efficient fine-tuning. The project distinguishes itself through the use of pipeline parallelism to distribute model workloads across multiple hardware accelerators. It utilizes low-bit integer quantization and speculative decoding to reduce memory footprints and decrease text generation latency. The system covers broad capabilities in model optimization, including w

This library provides a framework for parameter-efficient fine-tuning, enabling the adaptation of large pretrained models by training only a small subset of parameters. It functions as a distributed model training system and optimization toolkit, designed to reduce the computational and memory requirements typically associated with full model fine-tuning. The project distinguishes itself through a suite of methods for modular adapter composition, including low-rank matrix decomposition and activation-based scaling. It supports the integration of multiple task-specific adapter modules, allowin

LiteLLM is a unified gateway and proxy server designed to centralize access to over one hundred language model providers. It provides a standardized API interface that abstracts vendor-specific schemas, allowing developers to interact with diverse models through a single, consistent format. By acting as a central traffic management layer, it enables organizations to route, secure, and govern model interactions across multiple deployments. The platform distinguishes itself through its policy-driven architecture, which uses configuration-based routing to manage traffic distribution, load balanc

This repository is a deep learning for natural language processing course and curriculum. It provides educational material and guides focused on neural network architectures used for processing natural language, speech signals, and text classification. The content includes instructional tutorials on sequence modeling and neural language modeling, covering the implementation of n-gram and recurrent neural networks. It also provides a framework for studying word embeddings to map linguistic meanings into numerical representations. The curriculum covers a broad range of capabilities, including

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

LoRA is a framework for parameter-efficient fine-tuning of large-scale neural networks. It functions by injecting trainable low-rank decomposition matrices into frozen model layers, allowing for task-specific adaptation while preserving the integrity of the original base model weights. The project distinguishes itself by enabling the direct merging of these trained low-rank matrices into primary model weights. This process eliminates additional computational overhead during inference, ensuring that adapted models maintain the same performance characteristics as the original architecture. Furt

Chinese-Vicuna is a Chinese large language model and instruction-following AI based on the LLaMA architecture. It is specifically designed for natural language understanding and generation in the Chinese language, utilizing an instruction-tuned model to follow complex user prompts across conversations. The project provides a LoRA fine-tuning framework and quantization systems to enable model adaptation and inference on consumer hardware. It implements quantized inference to reduce memory usage on both CPUs and GPUs, supported by a low-level C++ implementation to minimize system resource requi