Repository Index

A large collection of system log datasets for AI-driven log analytics [ISSRE'23]

• logs
• unstructured-logs
• log-analysis
• log-parsing

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

• ai
• fairness-ai
• fairness
• fairness-testing

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

• deep-learning
• speech
• speech-recognition
• speech-to-text

A library for debugging/inspecting machine learning classifiers and explaining their predictions

• scikit-learn
• machine-learning
• xgboost
• lightgbm

Go efficient fast multilingual NLP and text segmentation; support English, Chinese, Japanese and others.

• go
• segment
• nlp
• gse

Gaining advanced insights from Git repository history.

• git-analysis
• machine-learning
• tensorflow
• git

Caffe models in TensorFlow

Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

• diffusion-models
• inference
• minimax-h3
• video-generation

LSD-SLAM

The repository host gives no description.

Deep neural network to extract intelligent information from invoice documents.

• invoice
• invoice-management
• invoices
• invoice-insight

Multi-segment MiniMax H3 Director for official ComfyUI MiniMax-H3

Algorithms for explaining machine learning models

• machine-learning
• explanations
• interpretability
• counterfactual

Python library and CLI tool to interface with Google Translate's text-to-speech API

• speech
• python
• tts
• text-to-speech

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

• controllable-generation
• foundation-models
• image-generation
• text-rendering

Machine learning platform for Web developers

• js
• machine-learning
• tensorflow
• pipeline

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

Algorithms for outlier, adversarial and drift detection

• anomaly
• outlier
• concept-drift
• detection

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

• kv-cache
• llm-inference
• local-llm
• quantization

Automatic architecture search and hyperparameter optimization for PyTorch

• automl
• deep-learning
• tabular-data
• pytorch

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

• machine-learning
• python
• statistics
• scikit-learn

The animation engine for agents: blazingly fast math and 3D videos with Manim's Python API, on a Rust GPU core.

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

• cuda
• glm
• glm-5
• llm

Todas as leis do Brasil