Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV).…

Simple, safe way to store and distribute tensors

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Tool to create a dataset of semantic segmentation on website screenshots from their DOM

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

A Lightweight Recommendation System

Code for Opponent Modeling in Negotiation Dialogues (Accepted at Findings of NAACL 2022)

Deep Learning - one shot learning for speaker recognition using Filter Banks

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs (ICLR'22)

Extract Keywords from sentence or Replace keywords in sentences.

architectures and pre-trained models for long document classification.

Open-source library for a reinforcement learning research.

Implementation of Hierarchical Text Classification

The most accurate natural language detection library for Go, suitable for short text and mixed-language text

Graph Data Science: an abstraction layer in Python for building knowledge graphs, integrated with popular graph libraries – atop Pandas, NetworkX, RAPIDS, RDFlib, pySHACL, PyVis, morph-kgc, pslpyth…

🛒 Simple recommender with matrix factorization, graph, and NLP. Beating the regular collaborative filtering baseline.

Top2Vec learns jointly embedded topic, document and word vectors.

Python Keyphrase Extraction module

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

Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.

Experimental Finnish language model for SpaCy

A modular active learning framework for Python

Minimal keyword extraction with BERT

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Train transformer language models with reinforcement learning.

🦜🔗 Build context-aware reasoning applications

A lightning-fast search API that fits effortlessly into your apps, websites, and workflow

Perform data science on data that remains in someone else's server