Ecosystem & Stack: huggingface

A high-throughput and memory-efficient open-source engine designed for fast, easy, and cost-effective serving of large language models.

A comprehensive guide and collection of recipes for building with the Llama model family, covering inference, fine-tuning, RAG, and end-to-end use cases.

An open-source, cloud-native vector database enabling semantic search at scale by combining vector similarity with structured filtering and integrated AI models.

An open collection of methodologies, tools, and step-by-step instructions for successfully training, fine-tuning, and inferencing large language and multi-modal models.

A comprehensive practical guide and accompanying codebase for building, deploying, and monitoring advanced LLM and RAG applications on AWS, emphasizing LLMOps best practices.

Ludwig is a low-code, declarative deep learning framework designed to simplify the building, training, and deployment of custom AI models, including LLMs and neural networks.

OpenVINO is an open-source toolkit designed to optimize and deploy deep learning models for efficient AI inference across diverse hardware platforms, from edge to cloud.

A free, hands-on course teaching how to build and deploy production-ready LLM and RAG systems, including a personalized 'LLM Twin', using LLMOps best practices.

A Python library for generating and curating high-quality synthetic data for AI model training and structured data extraction.

Provides a collection of Colab notebooks for efficiently fine-tuning large language models using PEFT methods like LoRA and Hugging Face transformers.

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

An efficient toolkit for fine-tuning ChatGLM-6B models using PEFT methods, enabling customization and deployment of large language models.

Nunchaku is a high-performance inference engine that optimizes 4-bit neural networks, especially diffusion models, for speed and efficiency.

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 tool for fast and efficient fine-tuning of diffusion models using Low-rank Adaptation (LoRA), producing small, shareable models.

A modular framework for aligning any-modality large models with human intentions and values using diverse fine-tuning and reinforcement learning methods.

A human preference reward model for evaluating and improving text-to-image generation models.

FinGPT is an open-source initiative providing cost-effective and rapidly adaptable large language models specifically designed for the dynamic financial sector.

A prompt rewriting tool that refines user prompts into clearer, structured versions to enhance the quality of text-to-image generation and image-to-image editing.

An implementation of Google's Dreambooth technique on Stable Diffusion, enabling personalized text-to-image model fine-tuning with limited examples.

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

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

An open-source framework that automates the evaluation and optimization of Retrieval-Augmented Generation (RAG) pipelines using AutoML-style techniques for specific datasets.

A framework for embedding secret cryptographic fingerprints into Large Language Models (LLMs) via fine-tuning to verify ownership and prevent unauthorized use.

A unified platform simplifying instruction-tuning, parameter-efficient methods, and large language model integration for researchers and developers.

A state-of-the-art open-source text-to-speech system leveraging LLMs to generate human-like, emotional, and low-latency speech with zero-shot voice cloning capabilities.

TensorFlowTTS provides real-time, state-of-the-art speech synthesis architectures based on TensorFlow 2, supporting multiple languages and optimized for fast inference and deployment on various devices.

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