TorchDR - PyTorch Dimensionality Reduction

A monolingual and cross-lingual meta-embedding generation and evaluation framework

Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.

Open Source Embeddings Optimisation and Eval Framework for RAG/LLM Applications. Documentations at https://docs.vectorboard.ai/introduction

Interactive quality analysis for two-dimensional embeddings

A scientific benchmark and comparison of the performance of sentiment analysis models in NLP on small to medium datasets

Gold standard resource for evaluation of Danish word embedding models.

Graph (network) embeddings evaluation framework via classification, gram martix construction for links prediction

Repository for the Master Thesis "Encoding semantic information about skills in the domain of human resources" in the University of Koblenz-Landau in cooperation with talentsconnect AG.

Simple function that computes pairwaise cosine distance between several vectors at once, pytorch can only compute beween two vectors at a time, which is time consuming and inneficient when you have multiple vectors.

A framework for word embedding evaluation automation and visualization.

Privacy-first semantic search engine for Mailio’s encrypted email system

This is a repository for a Jupyter based tool to calculate Greedy Matching, Vector Extrema and Average Embedding evaluation metrics for generative AI chatbots

Benchmark for Financial Question Answering

Text classification task to identify and classify malicious prompts for LLM interactions