-
Ant Group
- Hangzhou,China
Starred repositories
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
OpenMMLab Pose Estimation Toolbox and Benchmark.
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Making large AI models cheaper, faster and more accessible
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)
Code and documentation to train Stanford's Alpaca models, and generate the data.
List of Dirty, Naughty, Obscene, and Otherwise Bad Words
Use ChatGPT to summarize the arXiv papers. 全流程加速科研,利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
Must-read papers on prompt-based tuning for pre-trained language models.
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
Must-read papers on graph neural networks (GNN)
[CVPR2019 Oral] Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation on Python3, Tensorflow, and Keras
PKU-DAIR / GAMLP
Forked from zwt233/GAMLPCode of GAMLP for Open Graph Benchmark. KDD‘22
Graphormer is a general-purpose deep learning backbone for molecular modeling.
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Image augmentation for machine learning experiments.
Graph Attention Networks (https://arxiv.org/abs/1710.10903)
Python 开源项目之「自学编程之路」,保姆级教程:AI实验室、宝藏视频、数据结构、学习指南、机器学习实战、深度学习实战、网络爬虫、大厂面经、程序人生、资源分享。
Top-level Conference Publications on Knowledge Graph
links to conference publications in graph-based deep learning
遥感图像的语义分割,分别使用Deeplab V3+(Xception 和mobilenet V2 backbone)和unet模型,keras+python
electron-ssr原作者删除了这个伟大的项目,故备份了下来,不继续开发,且用且珍惜