llama3-from-scratch—Tutorial on Implementing Llama 3 from ScratchThis project helps people deeply understand how Large Language Models (LLMs) work by building Llama naklecha·Jupyter·5 months ago1.5k
llm-universe—Learn to Develop Large Model ApplicationsThis project is a large model application development tutorial designed specifically for novice devedatawhalechina·Jupyter·6 months ago1.9k
ollama—Tool for Running Various Large Language Models LocallyThis is a tool written in Go designed to install, launch, and manage large language models on a locaollama·Go·8 months ago1.8k
llm-viz—3D Visualization of Large Language Model GPTThis project demonstrates the working principles and reasoning process of large language models simibbycroft·TypeScript·8 months ago1.1k
LLaMA-Factory—Framework for Fine-tuning Large Language ModelsThis is an open-source project that makes fine-tuning large language models easy. It supports variouhiyouga·Python·6 months ago727
langchain—Framework for LLM-based ApplicationsThe LLM refers to large deep learning models that are pre-trained on big data. This project enables langchain-ai·Jupyter·6 months ago1.3k
llm-course—Free Open-source Course on Large Language ModelsThis is a free course on Large Language Models (LLMs), covering basic knowledge for beginners to getmlabonne·Jupyter·9 months ago2.3k
FastChat—Open Platform for Training and Evaluating Large Language ModelsThis platform is designed for training, deploying, and evaluating large language models, allowing yolm-sys·Python·7 months ago592
ml-ferret—Apple's Open-Source Multimodal Language Large ModelFerret, the open-source multimodal LLM model from Apple, is capable of analyzing and recognizing infapple·Python·10 months ago3k
llama3—Official Repository of Meta Llama 3The new generation large model Llama 3, open-sourced by Meta, has released only the 8B and 70B versimeta-llama·Python·6 months ago953
ml-engineering—Machine Learning: Training and Engineering of LLM/VLMThis project is a summary of the author's experience in training open-source BLOOM-176B large-scale stas00·Python·a year ago3k
DeepSpeed—Microsoft Open-Sources the Deep Learning Training Optimization LibraryAs everyone knows, training large language models (LLM) is a 'time-consuming and costly' task. This microsoft·Python·a year ago1.5k