DojoAgents: Full-Market AI Copilot for Personal Investment

SAM3 华为昇腾 Ascend NPU 适配与推理加速 | 10x acceleration on Huawei Ascend 910B2

Port of Nvidia LocateAnything-3B on ggml

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Finetune SAM3 with LoRA — optimized for images. A simple setup for training SAM3 on image datasets. Video finetuning is not yet supported but planned for future releases.

基于llama-index框架的 RAG 最佳实践，通过业界领先的PDF结构化文档解析能力、混合检索、small2big、Contextual rag等策略实现了高精度的传统rag模式问答效果，同时支持基于plan and solve agent执行pipline的Deep RAG模式，提供多格式文档支持与数据安全的存储架构。

基于React + FastAPI + LangChain + 通义千问的智能医疗问答系统，支持基于检索增强生成(RAG)的医疗知识问答。

大模型智能体Agent中文教程，博客代码仓库

A pytorch-based implementation of Dirichlet Process Mixture Model (DPMM)

Variational Dirichlet Process Gaussian Mixture Models

Implementation of the first paper on word2vec

The repo for Tsinghua summer course: Interdisciplinary Seminar on Big Models

中国大模型

A PyTorch implementation of T-GCN

[ICLR-2020] Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers.

Feature coded UNSW_NB15 intrusion detection data.

Implemented Variational Autoencoder generative model in Keras for image generation and its latent space visualization on MNIST and CIFAR10 datasets

This is an implementation of the VAE (Variational Autoencoder) for Cifar10

Code examples for using the originpro Python package to interact with Origin software.

Deep learning-based outlier/anomaly detection

Code of the paper 'Neural Transformation Learning for Anomaly Detection' published in ICML 2021

A PyTorch implementation of Model Agnostic Meta-Learning (MAML) that faithfully reproduces the results from the original paper.

A PyTorch implementation of OpenAI's REPTILE algorithm

Online Learning code: TG -> FOBOS -> RDA ->FTRL ->FTPRL -> FTML