Making large AI models cheaper, faster and more accessible

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Minimal reproduction of DeepSeek R1-Zero

Distributed and fault-tolerant realtime computation: stream processing, continuous computation, distributed RPC, and more

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

Harness LLMs with Multi-Agent Programming

Repository for the NaLLM project

Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"

Keras WaveNet implementation

WE HAVE MOVED to Apache Incubator. https://cwiki.apache.org/FLUME/ . Flume is a distributed, reliable, and available service for efficiently collecting, aggregating, and moving large amounts of log…

Graph database implementing the RDF and SPARQL standards. Very fast and scales to more than a trillion triples on a single commodity machine

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

OpenML's Python API for a World of Data and More 💫

Context-Aware Representations for Knowledge Base Relation Extraction

deep learning sex position classifier

The analytics hypervisor, an operating system to manage all your analytics needs and licensed under Apache 2.0 License.

NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT

terashuf shuffles multi-terabyte text files using limited memory

A graph-based distributed in-memory store that leverages efficient graph exploration to provide highly concurrent and low-latency queries over big linked data

A tool for supervised Machine Learning in OWL and Description Logics

This package provides an efficient implementation of locality-sensitve hashing (LSH)

The guts for computing data for OpenAlex. For more, see https://openalex.org/.

You can find the most recent KGQA benchmark numbers from publications here.

RDF-star specification

A highly scalable RDF triple store with full-text and GeoSPARQL support

EMNLP 2020: Message Passing for Hyper-Relational Knowledge Graphs

Deepseek R1 zero tiny version own reproduce on two A100s.

Feature Extractor module for videos using the PySlowFast framework