T

transformers

A command-line tool for running small language models locally using Hugging Face transformers.

Check out the project preview: https://imdb-movie-classifier-76ac6b.gitlab.io/

Run AI in the browser. Easily extendable.

Opus-Translate: German to French Translation Service

Containerized translation service providing German→French translation via CLI and OpenAI-compatible HTTP API. Built with FastAPI and Helsinki-NLP/opus-mt-de-fr transformer model. Features Docker deployment, model caching, health checks, and interactive client for testing. Simple, production-ready translation microservice.

Key Features: • CLI and HTTP server interfaces • OpenAI-compatible /v1/chat/completions endpoint• Docker containerization with multi-stage builds • Automatic model downloading and caching • Interactive test client included • Environment-based configuration

Fork of @xenova/transformers

This research presents a novel ensemble-based approach for detecting deepfake images using a combination of Convolutional Neural Networks (CNNs) and Vision Transformers (ViT). The system achieves 94.87% accuracy by leveraging three complementary architectures: a 12-layer CNN, a lightweight 6-layer CNN, and a hybrid CNN-ViT model. Our approach demonstrates robust performance in distinguishing between real and manipulated facial images.

Projet de correction/ajout de la bi-écriture des notices bibliographiques du Sudoc.

ANTIDOTE's ACTA Module for Finetuning Transformers for Argumentation Mining.

Vamos a contruir un Chatbot Inteligente capaz de interpretar el lenguaje humano y generar respuestas coherentes con tu propia información

This is a demo of my angular application for grammatical error correction with transformers based on multilingual Bart correction. The model is trained in 4 languages:

Italian English Russian German

Master thesis - Deep learning-based pairwise alignment of protein sequences using transformer architecture.

Demo of Semantic Similarity using spaCy vector and transformer models

Repository for all code related to my Master Thesis "Leveraging Natural Language Phrase Grounding in Images for Online Misinformation Detection" at the University of Tübingen in 2022.

✭ MAGNETRON ™ ✭: This is a Google Colab/Jupyter Notebook for developing a BRAIN PROXIA (B) when working with ARTIFICIAL INTELLIGENCE 2.0 ™ (ARTIFICIAL INTELLIGENCE 2.0™ is part of MAGNETRON ™ TECHNOLOGY).

Dense Prediction by Means of Self-attention Layers - research of models for dense prediction (semantic segmentation) - primarily transformers (models in focus: Segmenter, Swin transformer) and comparison with convolutional models (model in focus: pyramidal SwiftNet). Also, research, design and implementation of pyramidal models of transformer-convolutional model (Segmenter-SwiftNet) and transformer-transformer (Segmenter-Segmenter) type. Implementation is in PyTorch deep learning framework. My graduate thesis computer vision project.