Repo AI đang lênCập nhật hằng ngày từ GitHub

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

Nano vLLM

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

Low-code framework for building custom LLMs, neural networks, and other AI models

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

Implement a reasoning LLM in PyTorch from scratch, step by step

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

An Open-Source Framework for Prompt-Learning.

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

Align Anything: Training All-modality Model with Feedback

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

LLM training code for Databricks foundation models

A curated list of reinforcement learning with human feedback resources (continually updated)

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.

3D ResNets for Action Recognition (CVPR 2018)

Easiest and laziest way for building multi-agent LLMs applications.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

A collection of scientific methods, processes, algorithms, and systems to build stories & models.

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

QualityScaler - image/video AI upscaler app

Training and serving large-scale neural networks with auto parallelization.

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

PyTorch implementation of Super SloMo by Jiang et al.

LLM Finetuning with peft

Images to inference with no labeling (use foundation models to train supervised models).

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

LeetCode for PyTorch — 65 ML/AI interview problems from real interviews at Google, Meta, Anthropic. Jupyter notebooks, an auto-grader, and an MCP AI tutor.

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Run Mixtral-8x7B models in Colab or consumer desktops

Distributed AI Model Training and LLM Fine-Tuning on Kubernetes

Official repository of the xLSTM.

开源社区第一个能下载、能运行的中文 LLaMA2 模型！

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework

Synthetic data curation for post-training and structured data extraction

A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.

AuK: An Open-Source Foundational Model for Speech Generation and Editing

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

This is a background removing tool powered by InSPyReNet (ACCV 2022)

A toolbox for skeleton-based action recognition.

GNES is Generic Neural Elastic Search, a cloud-native semantic search system based on deep neural network.

The official implementation of Self-Play Fine-Tuning (SPIN)

A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.

Neural Network Compression Framework for enhanced OpenVINO™ inference

TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.