Table of Contents generated with DocToc
关注AI领域值得关注的研究进展，包括视频、LLM及相关应用，以及其他AI相关。
- CogVideo - a THUDM Collection
- genmo/mochi-1-preview · Hugging Face
- rain1011/pyramid-flow-miniflux · Hugging Face
- Lightricks/LTX-Video · Hugging Face
- rhymes-ai/Allegro: Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.
- PKU-YuanGroup/Open-Sora-Plan: This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
- unilm/layoutreader at master · microsoft/unilm
- PaddleNLP/model_zoo/ernie-layout/README_ch.md at develop · PaddlePaddle/PaddleNLP
- AdvancedLiterateMachinery/Applications/DocXChain at main · AlibabaResearch/AdvancedLiterateMachinery
重点关注MicroSoft。
- LLaVA-VL/LLaVA-Interactive-Demo: LLaVA-Interactive-Demo
- yxuansu/PandaGPT: [TLLM'23] PandaGPT: One Model To Instruction-Follow Them All
- microsoft/autogen: Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
- microsoft/semantic-kernel: Integrate cutting-edge LLM technology quickly and easily into your apps
- visual-openllm/visual-openllm: something like visual-chatgpt, 文心一言的开源版
- paradedb/paradedb: PostgreSQL for Search
- facebookresearch/faiss: A library for efficient similarity search and clustering of dense vectors.
- milvus-io/milvus: A cloud-native vector database, storage for next generation AI applications
- alibaba/proxima
- vearch/vearch: A distributed system for embedding-based vector retrieval
- castorini/anserini: Anserini is a Lucene toolkit for reproducible information retrieval research
- google-research/scann at master · google-research/google-research
- terry3041/pyChatGPT: An unofficial Python wrapper for OpenAI's ChatGPT API
- acheong08/EdgeGPT: Reverse engineered API of Microsoft's Bing Chat AI
- acheong08/ChatGPT: Reverse engineered ChatGPT API
- transitive-bullshit/chatgpt-api: Node.js client for the official ChatGPT API. 🔥
- terry3041/pyChatGPT: An unofficial Python wrapper for OpenAI's ChatGPT API
- Sha1rholder/use-ChatGPT-in-GFW: 在中国境内使用 OpenAI 服务的方法
- ninja/README_zh.md at main · gngpp/ninja
- Frameworks for Serving LLMs. A comprehensive guide into LLMs inference and serving
- ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++
- huggingface/text-generation-inference: Large Language Model Text Generation Inference
- onnxruntime/onnxruntime/python/tools/transformers/notebooks/Inference_GPT2_with_OnnxRuntime_on_CPU
- FasterTransformer/docs/gpt_guide.md at main · NVIDIA/FasterTransformer
- OpenNMT/CTranslate2: Fast inference engine for Transformer models
- mlc-ai/mlc-llm: Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
- vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
- sonos/tract: Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
- rustformers/llm: An ecosystem of Rust libraries for working with large language models
- bentoml/OpenLLM: Operating LLMs in production
- huggingface/candle: Minimalist ML framework for Rust
- tairov/llama2.mojo: Inference Llama 2 in one file of pure 🔥
- f/awesome-chatgpt-prompts: This repo includes ChatGPT prompt curation to use ChatGPT better.
- dair-ai/Prompt-Engineering-Guide: 🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
- onnx/onnx: Open standard for machine learning interoperability
- huggingface/safetensors: Simple, safe way to store and distribute tensors
- openai/triton: Development repository for the Triton language and compiler
- microsoft/onnxruntime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
- NVIDIA/TensorRT: NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
- openvinotoolkit/openvino: OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
- triton-inference-server/server: The Triton Inference Server provides an optimized cloud and edge inferencing solution.
- KomputeProject/kompute: General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.
- Adlik/Adlik: Adlik: Toolkit for Accelerating Deep Learning Inference
- tensorflow/serving
- pytorch/serve: Model Serving on PyTorch
- TFX: End-to-End Platform for Deploying Production ML Pipelines
- Kubeflow
- mvitez/thnets: Basic library that can run networks created with Torch
- Serving Trained Model (aka Model API) - FloydHub Documentation
- ahkarami/Deep-Learning-in-Production
- hyperonym/basaran: Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
- holoviz/panel: Panel: The powerful data exploration & web app framework for Python
- rawpython/remi: Python REMote Interface library. Platform independent. In about 100 Kbytes, perfect for your diet.
- PySimpleGUI
- pywebio/PyWebIO: Write interactive web app in script way.
- streamlit/streamlit: Streamlit — A faster way to build and share data apps.
- gradio-app/gradio: Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
- microsoft/hummingbird: Hummingbird compiles trained ML models into tensor computation for faster inference.
- PyTorchLightning/pytorch-lightning: The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
- Deepfakes
- DeepFaceLab
- Music Generation
- AI_Composer
- ChatterBot
- ChatterBot
- GPT2 for Chinese Chitchat
- FaceBook Detectron2: object detection and segmentation.
- Open MMLab Detection Toolbox and Benchmark
- Open MMLab Computer Vision Foundation
- esdalmaijer/PyGaze: eye tracking experiments
- atulapra/Emotion-detection
- Multi-Person Pose Estimation&Tracking System
- facebookresearch/dlrm: recommendation
- Jupyter Tutorial — Jupyter Tutorial 0.8.0
- Dataset Search
- Hugging Face – The AI community building the future.
- Find Open Datasets and Machine Learning Projects | Kaggle
- Machine Learning Datasets | Papers With Code
- Datasets
- 中文NLP数据集
- Dataset list - A list of the biggest machine learning datasets
- awesomedata/awesome-public-datasets: A topic-centric list of HQ open datasets.
- Data Is Plural
- OpenML
- InsaneLife/ChineseNLPCorpus: 中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。
- opencv/cvat: Computer Vision Annotation Tool
- wkentaro/labelme: Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
- generating training data with weak supervision
- make basic image processing operations
- nlplab/brat: textual annotation
- doccano/doccano: Open source annotation tool for machine learning practitioners.
- Overview - CoreNLP
- fast.ai · Making neural nets uncool again
- TensorFlow
- Tensorflow Models
- DeepLearning Papers
- Awesome-Deep-learning-papers
- D2L ZH
- D2L EN
- pytorch/tutorials: PyTorch tutorials.
- Pytorch Examples
- Tutorials | TensorFlow Core
- 简单粗暴 TensorFlow 2 | A Concise Handbook of TensorFlow 2 — 简单粗暴 TensorFlow 2 0.4 beta 文档
- TensorFlow-Examples
- microsoft: NLP Best Practices & Examples
- DeepLearning Projects
- Ttensorflow_practice
- microsoft/nni: AutoML toolkit
- Imbalanced Learning
- Automated Machine Learning tool using genetic programming
- Machine learning evaluation metrics
- Awesome Machine Learning
- autonomio/talos: Hyperparameter Optimization for TensorFlow, Keras and PyTorch
- scikit-optimize: sequential model-based optimization in Python — scikit-optimize 0.8.1 documentation
- fmfn/BayesianOptimization: A Python implementation of global optimization with gaussian processes.
- Ray Tune：Tune: Scalable Hyperparameter Tuning — Ray v2.0.0.dev0
- hyperopt/hyperopt: Distributed Asynchronous Hyperparameter Optimization in Python
- Introduction to the Keras Tuner | TensorFlow Core
- Google Vizier：Vizier 概览 | AI Platform Vizier | Google Cloud
- Amazon Sagemaker：Amazon SageMaker 机器学习模型构建训练部署 - AWS 云服务
- Microsoft NNI：microsoft/nni: An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
- Microsoft Advisor：Optimization advisor overview - Finance & Operations | Dynamics 365 | Microsoft Docs
- maxpumperla/hyperas: Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization （已存档）
- Avsecz/kopt: Hyper-parameter optimization for Keras（一阵没更新了）
- rsteca/sklearn-deap: Use evolutionary algorithms instead of gridsearch in scikit-learn（一阵没更新了）
- HIPS/Spearmint: Spearmint Bayesian optimization codebase（一阵没更新了）
- [1603.06560] Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization