Maschinelles Lernen · GitHub

[NeurlPS-2024] The code of MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models

🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams

Faster versions of published vision models behind one API. With optional custom kernels for even bigger speedup

PyTorch implementation of One-Shot Video Object Segmentation (OSVOS)

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

Locating and editing factual associations in GPT (NeurIPS 2022)

(Linear-chain) Conditional random field in PyTorch.

Natural Intelligence is still a pretty good idea.

ProphitBet is a Machine Learning Soccer Bet prediction application. It analyzes the form of teams, computes match statistics and predicts the outcomes of a match using advanced Machine Learning (ML) methods. Additionally, it provides betting agents based on Deep Reinforcement Learning (DRL), which can learn optimal betting strategies.

Implementation of the paper: Text Segmentation as a Supervised Learning Task

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference.

Awesome Generative Adversarial Networks with tensorflow

A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT.

A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training

Code for finetuning AlexNet in TensorFlow >= 1.2rc0

Language model search engine built on a vector database and an anything key/value store.

• Fast key/value storage with page/column readers and writers
• Practical text analysis utilities for strings, bags of words/chars, and vectors

Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.

An autonomous, AI solver for the LinkedIn Zip puzzle game. It works on deep reinforcement learning, heuristic search and real time browser automation via Playwright