Tags: #deep-learning

A comprehensive library providing state-of-the-art pre-trained models for various machine learning tasks across text, vision, audio, and multimodal domains, facilitating both inference and training.

A scalable and lightweight infrastructure for fine-tuning, inference, and deployment of over 1000 large language models (LLMs) and multimodal large language models (MLLMs) using advanced techniques.

A state-of-the-art library for Parameter-Efficient Fine-Tuning (PEFT) of large pretrained models, drastically reducing computational and storage costs.

vLLM is a high-throughput and memory-efficient open-source library designed for fast and easy serving of large language models.

A unified and efficient framework for fine-tuning over 100 large language models (LLMs) and vision-language models (VLMs) with both CLI and Web UI.

Streamlines complex deep learning engineering, enabling scalable AI model training and finetuning across diverse hardware with minimal code changes.

MNN is a blazing-fast, lightweight deep learning inference engine optimized for high-performance on-device AI and Large Language Models.

A comprehensive repository housing open-source code and datasets officially released by Google Research.

A free and open-source framework designed for efficient fine-tuning of large language models.

An industrial-strength Python library for advanced Natural Language Processing, offering state-of-the-art models and a production-ready training system.

A next-generation training engine optimized for ultra-large Mixture-of-Experts (MoE) models, offering superior efficiency and scalability.

An educational project providing step-by-step code to build a ChatGPT-like Large Language Model (LLM) from scratch using PyTorch.

A universal viewer for neural network, deep learning, and machine learning models, supporting a wide array of formats.

An open standard and format for machine learning models, enabling interoperability across different AI frameworks and hardware.

An accessible knowledge sharing platform for Large Language Models (LLMs), designed to help individuals understand complex concepts and excel in LLM-related job interviews.

A meticulously curated list of battle-tested, production-proven open-source AI projects, models, tools, and infrastructure.

A comprehensive MLOps platform for managing, orchestrating, and scaling the machine learning lifecycle with reproducibility and automation.

An open-source, cloud-native, all-in-one MLOps platform designed for the full lifecycle management of machine learning, deep learning, and large language model development and deployment.

A PyTorch library enabling accessible large language models through k-bit quantization, significantly reducing memory consumption for both inference and training.

A low-code, declarative framework for building and deploying custom large language models (LLMs) and other deep neural networks with ease and efficiency.

A comprehensive and curated collection of deep learning study notes, integrating content from leading educators like Andrew Ng, Li Mu, and TuDui, covering CV, NLP, and Large Language Models.

OpenVINO is an open-source toolkit designed to optimize and deploy deep learning models for efficient AI inference across a wide range of hardware platforms.

A 12-week, 24-lesson curriculum from Microsoft to learn Artificial Intelligence for beginners, including practical lessons, quizzes, and labs.

A comprehensive repository offering C++ and Python code examples for computer vision, deep learning, and AI research articles from LearnOpenCV.com.

A comprehensive toolkit providing best practices, examples, and state-of-the-art algorithms to assist in prototyping, experimenting with, and operationalizing recommendation systems.

An open-source framework designed to make large AI model training and inference cheaper, faster, and more accessible through advanced distributed computing and memory optimization techniques.

A cutting-edge framework for building fast and simple neural data processing pipelines, especially for unstructured multi-modal data using LLMs.

A high-performance, scalable JAX-based open-source library for training large language models on Google Cloud TPUs and GPUs.

A no-code GUI and framework for easily fine-tuning state-of-the-art large language models (LLMs).

A PyTorch-based framework to adapt Meta AI's Segment Anything Model (SAM) for improved performance on challenging downstream computer vision tasks using adapters and prompts.

A comprehensive Chinese technical book on Large Language Models, offering a systematic framework and roadmap for beginners with a deep learning background, authored by leading experts.

A toolkit for quantizing (compressing) Large Language Models (LLMs) with hardware acceleration across various GPUs and CPUs, integrating with popular inference frameworks.

A deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music processing.

A comprehensive code repository accompanying a hands-on course for mastering Huggingface Transformers, covering fundamental concepts to advanced fine-tuning and deployment techniques.

A unified library extending HuggingFace Transformers for parameter-efficient and modular transfer learning in NLP.

Nunchaku is a high-performance AI inference engine that optimizes 4-bit neural networks, especially diffusion models, for faster and more memory-efficient execution.

A comprehensive collection of PyTorch implementations for over 60 deep learning papers, featuring side-by-side annotated notes for enhanced understanding.

LongLoRA is an efficient fine-tuning method and associated models/datasets designed to extend the context window of Large Language Models (LLMs) for processing longer inputs.

A series of high-performance, cost-effective open-source large language models (LLMs) designed for general-purpose usage and advanced reasoning.

A comprehensive collection of recipes and code for training various reward models crucial for Reinforcement Learning from Human Feedback (RLHF) in large language models.

An open-source framework providing code, models, and insights for stable Reinforcement Learning from Human Feedback (RLHF) training in Large Language Models, focusing on the PPO algorithm and reward modeling.

A PyTorch implementation of Google's Imagen, a state-of-the-art text-to-image neural network, enabling advanced generative AI capabilities.

A command-line tool for generating images from text descriptions using OpenAI's CLIP and Siren neural networks.

A state-of-the-art open-source multilingual text-to-speech system offering exceptionally natural, realistic, and emotionally rich voice generation.

A deep learning framework for real-time voice cloning and text-to-speech synthesis from short audio samples.

A unified, reproducible, and efficient multimodal evaluation toolkit for large language models across text, image, video, and audio tasks.

A PyTorch implementation of BitNet, enabling highly efficient 1-bit transformers for large language models.

An open-source implementation for efficiently fine-tuning Alibaba Cloud's Qwen-VL series of multimodal large language models using HuggingFace and Liger-Kernel.

A modular and scalable PyTorch-based framework for state-of-the-art vision and language multimodal research from Facebook AI Research.

A series of video foundation models and large-scale datasets designed for comprehensive multimodal video understanding and generation.

AutoRound is an advanced quantization toolkit for Large Language Models (LLMs) and Vision-Language Models (VLMs), enabling high-accuracy, ultra-low-bit inference across diverse hardware.

A high-performance, comprehensive face recognition library built on PaddlePaddle and PyTorch.

An open-source PyTorch-based framework for NLP pre-training and fine-tuning, offering modularity, reproducibility, and a comprehensive model zoo for various downstream tasks.

A toolkit for finetuning ChatGLM series models (ChatGLM-6B, ChatGLM2-6B, ChatGLM3-6B) using various methods like Freeze, Lora, P-tuning, and full parameter training for downstream NLP tasks.

An open-source AI model for instant, accurate, and flexible voice cloning, supporting cross-lingual synthesis and granular style control.

A deep learning toolkit for advanced, multi-language Text-to-Speech generation and voice cloning, suitable for research and production.

MetaVoice-1B is an open-source 1.2B parameter foundational model for highly expressive, human-like text-to-speech synthesis with advanced voice cloning capabilities.

TensorFlowTTS is a real-time, state-of-the-art speech synthesis library built on TensorFlow 2, supporting multiple languages and optimized for efficient deployment.

An open-source implementation of Microsoft's VALL-E X, enabling zero-shot multilingual text-to-speech synthesis and voice cloning with emotion control.

VITS is an end-to-end text-to-speech model that generates highly natural-sounding audio with diverse rhythms, outperforming traditional two-stage TTS systems.

A deep learning library for advanced, high-quality, and efficient Text-to-Speech (TTS) synthesis, supporting multiple languages and models.

A modularized multimodal large language model designed for OCR-free document understanding.

The first end-to-end multimodal large language model (MM-LLM) capable of perceiving and generating content in arbitrary combinations of text, image, video, and audio.

A family of powerful multi-modal large language models (MLLMs) designed to advance AI's understanding and generation capabilities across various data types.

A lightweight C++ toolkit for deploying over 100 AI models across various inference engines.

A ComfyUI plugin that integrates Nunchaku, an efficient inference engine for 4-bit quantized neural networks, to accelerate AI model execution.

Official SeedVR2 Video Upscaler for ComfyUI, enabling high-quality video and image upscaling, also runnable as a standalone CLI.

An open-source deep learning tool that enables users to recognize and swap faces in images and videos.

A one-step image-to-image translation framework leveraging Stable Diffusion Turbo for rapid generation across various tasks like sketch-to-image and day-to-night transformations.

SUPIR is an AI-driven project focused on developing practical algorithms for photo-realistic image restoration and upscaling in real-world scenarios.

An open-source, theoretical reconstruction of the Claude Mythos LLM architecture, featuring a Recurrent-Depth Transformer and sparse Mixture of Experts for advanced reasoning.

A meticulously curated list of battle-tested, production-proven open-source AI projects, models, tools, and infrastructure.

A user-friendly template integrating PyTorch Lightning and Hydra to streamline deep learning experimentation and development.

Magika is a fast and highly accurate AI-powered tool for identifying file content types, crucial for security and content routing.

A lightweight and optimized Python library for fast offline large language model inference, offering comparable or better performance than vLLM with a more readable codebase.

A comprehensive, AI-native learning platform to master AI engineering from foundational math to autonomous agent swarms, building and shipping real tools.

A high-performance, no-abstraction toolkit providing recipes for pretraining, finetuning, and deploying over 20 large language models at scale.

MMPreTrain is an OpenMMLab project providing a comprehensive, open-source PyTorch-based toolbox for pre-training and benchmarking various computer vision and multi-modal models.

Fengshenbang-LM is an open-source large model system by IDEA Research Institute, serving as infrastructure for Chinese AIGC and cognitive intelligence.

An open-source large language and vision assistant (LLaVA) that achieves GPT-4V level multimodal capabilities through visual instruction tuning.

A meticulously curated collection of links to free courses and resources covering various Artificial Intelligence (AI) topics, suitable for all learning levels.

A PyTorch library providing advanced foundation architectures to efficiently and effectively scale Transformers for large language models and general-purpose AI.

A comprehensive, curated collection of tutorials and resources for Artificial Intelligence Generated Content (AIGC), encompassing Large Language Models, AI Painting, and related AI fields.