Interpretability and explainability of data and machine learning models
- explainable-ai
- explainable-ml
- trusted-ai
- trusted-ml
47,133 repositories indexed
289–312 of 738 · Most stars
Interpretability and explainability of data and machine learning models
A BERT model for scientific text.
Deep probabilistic analysis of single-cell and spatial omics data
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
TranslatedDSH × Blender direct real-time plugin v2.6.1: 15 model tools let AI drive the GUI Blender; supports dsh-TUI (selection chip / footer status / @ mentions / /blender), activity status pinned on top with one-click pause for the AI, native selection / collections / sub-elements sent directly to DSH, a modeling skill bundled with the package, supports WSL / Windows / macOS.
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
TranslatedMcDonald's MCP party/group meal organizing assistant — a CLI/Skill for party booking and group meal planning based on the Model Context Protocol
Biological foundation modeling from molecular to genome scale
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
A 100-day challenge exploring IoT and embedded systems using ESP32, ESP8266, and Raspberry Pi Pico with MicroPython. Each day covers a new sensor or module with complete code, circuit diagram, and explanation.
A php2shell exploit that requires no modifications to the official version, and does not require display_errors or limit_memory.
Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models
A Django application that provides country choices for use with forms, flag icons static files, and a country field for models.
Modern REST framework for Django with types and async support!
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
Modern(-ish) password hashing for your software and your servers
OpenMMLab Foundational Library for Training Deep Learning Models
Open-source GNSS + inertial navigation, sensor fusion simulator. Motion trajectory generator, sensor models, and navigation
moDel Agnostic Language for Exploration and eXplanation
Translates Django models using a registration approach.
Python DSP module
Python module to get stock data from Yahoo! Finance