Skip to content
プロジェクトカテゴリ

機械学習 · GitHub

モデルの学習・評価・推論に使うフレームワークを探し、注目度を比較できます。

便利なGitHubプロジェクト

12,805 プロジェクト

asl-ml-immersion

GoogleCloudPlatform

2,616スター

Notebooks, code samples and reference for machine learning and generative ai on Google Cloud for the Advanced Solutions Lab (ASL) bootcamps.

機械学習Jupyter NotebookApache-2.0GitHub
1,119スター
pytorch-original-transformer preview

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

機械学習Jupyter NotebookMITGitHub

gorse

gorse-io

9,926スター
gorse preview

AIを活用したオープンソースのレコメンドシステムエンジンです。従来型およびLLMランカーに対応し、埋め込みを通じてマルチモーダルコンテンツも扱えます。

rockchip-npu-notes

gregordinary

34スター

Hardware reference and research notes for the RK3588 NPU and its regcmd interface

  • Datatypes. The integer types are int4, int8 and int16, and the float types are fp16, bf16 and tf32. Each has a native matmul [HW sweep]. int16's int32 output saturates, so a matmul that needs int64-exact results over full-range int16 operands is computed as four int8 matmuls.
  • On-chip requant. The DPU's output converter performs the requant of an int32 accumulator, with an integer multiplier and a shift. Its BS stage multiplies per output channel, which applies TFLite's per-axis scales on chip [HW sweep]. An int8 convolution therefore writes int8 with no host requant.
機械学習ShellCC-BY-4.0GitHub

awesome-ai

hades217

559スター
awesome-ai preview

A curated list of artificial intelligence resources (Courses, Tools, App, Open Source Project)

smile

haifengl

6,438スター
smile preview

統計的機械知能と学習エンジン

  • LLM - LLaMA-3 inference, tiktoken BPE tokenizer, OpenAI-compatible REST server, SSE chat streaming
  • Deep Learning - LibTorch/GPU backend, EfficientNet-V2 image classification, custom layer API

ATM

HDI-Project

528スター

Auto Tune Models - A multi-tenant, multi-data system for automated machine learning (model selection and tuning).

hedgehog-lab

Hedgehog-Computing

2,387スター

Run, compile and execute JavaScript for Scientific Computing and Data Visualization TOTALLY TOTALLY TOTALLY in your BROWSER! An open source scientific computing environment for JavaScript TOTALLY in your browser, matrix operations with GPU acceleration, TeX support, data visualization and symbolic computation.

機械学習TypeScriptApache-2.0GitHub

ManimML

helblazer811

3,533スター
ManimML preview

ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

305スター
openJev-verdict-2.0 preview

Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

optimus

hi-primus

1,535スター
optimus preview

:truck: Agile Data Preparation Workflows made easy with Pandas, Dask, cuDF, Dask-cuDF, Vaex and PySpark

機械学習PythonApache-2.0GitHub

DataFrame

hosseinmoein

2,997スター
DataFrame preview

C++ DataFrame for statistical, financial, and ML analysis in modern C++

機械学習C++BSD-3-ClauseGitHub

Hyperactive

hyperactive-project

551スター
Hyperactive preview

A unified interface for optimization algorithms and experiments

  • 31 Optimization Algorithms Local, global, population-based, and model-based methods across 3 backends (GFO, Optuna, sklearn). - Experiment Abstraction Clean separation between what to optimize (experiments) and how to optimize (algorithms). - Flexible Search Spaces Discrete, continuous, and mixed parameter types. Define spaces with NumPy arrays or lists.
  • ML Framework Integrations Native support for scikit-learn, sktime, skpro, and PyTorch with minimal code changes. - Multiple Backends GFO algorithms, Optuna samplers, and sklearn search methods through one unified API. - Stable & Tested 5+ years of development, comprehensive test coverage, and active maintenance since 2019.

decisiontree

igrigorik

1,502スター

ID3-based implementation of the ML Decision Tree algorithm

  • ID3 algorithms for continuous and discrete cases, with support for inconsistent datasets.
  • Graphviz component to visualize the learned tree