Repositories list

• CLIP_benchmark

  Public
  CLIP-like model evaluation

  Jupyter Notebook

  •

  MIT License

  •82•662•29•4•Updated Feb 13, 2025Feb 13, 2025

• annotate-collection

  Public
  A repository with data for annotation.

  Python

  •0•1•1•0•Updated Feb 13, 2025Feb 13, 2025

• AIW

  Public
  Alice in Wonderland code base for experiments and raw experiments data

  Python

  •

  Apache License 2.0

  •10•126•2•1•Updated Feb 13, 2025Feb 13, 2025

• Megatron-LM-Open-Sci

  Public
  MegaTron open-sci fork

  Python

  •

  Other

  •2.5k•0•0•0•Updated Feb 11, 2025Feb 11, 2025

• school-bud-e-frontend

  Public
  A frontend that is compatible to the school-bud-e-backend.

  TypeScript

  •

  MIT License

  •9•13•0•0•Updated Feb 7, 2025Feb 7, 2025

• laion.ai

  Public
  HTML

  •

  MIT License

  •45•115•4•3•Updated Jan 30, 2025Jan 30, 2025

• bud-e

  Public
  A general human-ai interaction platform.

  TypeScript

  •

  MIT License

  •9•11•0•0•Updated Jan 18, 2025Jan 18, 2025

• CLAP

  Public
  Contrastive Language-Audio Pretraining

  Python

  •

  Creative Commons Zero v1.0 Universal

  •151•1.5k•55•0•Updated Nov 21, 2024Nov 21, 2024

• emotional-speech-annotations

  Public
  This repository contains prompts & best practices to annotate audio clips with a very high degree of details using Audio-Language-Models

  Apache License 2.0

  •1•32•0•0•Updated Oct 13, 2024Oct 13, 2024

• Desktop-BUD-E_V1.0

  Public
  BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the creation and integration of diverse skills for educational and research applications.

  Python

  •

  Apache License 2.0

  •6•17•0•1•Updated Oct 10, 2024Oct 10, 2024

• Open-Assistant

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

  pythonmachine-learningai+ 6nextjsdiscord-botassistantlanguage-modelchatgptrlhf

  Python

  •

  Apache License 2.0

  •3.3k•37k•226•65•Updated Aug 17, 2024Aug 17, 2024

• Desktop_BUD-E

  Public
  BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the creation and integration of diverse skills for educational and research applications.

  voiceassistantpersonal-assistant+ 9home-assistanttutoringpersonal-assistant-frameworkvoice-assistantsai-assistantvoice-assistant-ailaion+ 2

  Python

  •161•31•0•0•Updated Jul 18, 2024Jul 18, 2024

• snac-to-llama3

  Public
  Jupyter Notebook

  •1•0•0•1•Updated Jul 10, 2024Jul 10, 2024

• riverbed

  Public
  Tools for content datamining and NLP at scale

  Python

  •

  Apache License 2.0

  •6•42•0•0•Updated Jun 20, 2024Jun 20, 2024

• django-htmx-llm-streaming

  Public
  A prototype showing how to stream using Django x htmx.

  JavaScript

  •1•1•0•0•Updated Jun 12, 2024Jun 12, 2024

• Discord-Scrapers

  Public
  Implementation of a discord channel scraper to generate datasets.

  Python

  •

  Apache License 2.0

  •11•74•0•0•Updated Jun 10, 2024Jun 10, 2024

• natural_voice_assistant

  Public
  Python

  •

  MIT License

  •44•477•6•1•Updated May 27, 2024May 27, 2024

• AIW_webpage

  Public
  Alice in Wonderland project and initiative webpage

  Apache License 2.0

  •0•1•0•0•Updated May 23, 2024May 23, 2024

• llm-template

  Public
  A template for procedural template generation using JSON outputs form LLMs.

  TypeScript

  •0•1•0•0•Updated Apr 16, 2024Apr 16, 2024

• audio-dataset

  Public
  Audio Dataset for training CLAP and other models

  Python

  •55•665•33•6•Updated Feb 5, 2024Feb 5, 2024

• Open-Instruction-Generalist

  Public
  Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks

  Python

  •

  Apache License 2.0

  •19•208•5•0•Updated Jan 13, 2024Jan 13, 2024

• scaling-laws-openclip

  Public
  Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

  pytorchtransfer-learningclip+ 9fine-tuningfew-shot-learningpre-trainingzero-shot-retrievalzero-shot-classificationscaling-lawslaion+ 2

  Jupyter Notebook

  •12•158•1•0•Updated Nov 29, 2023Nov 29, 2023

• Text-to-speech

  Public
  Python

  •

  Apache License 2.0

  •5•59•1•0•Updated Nov 4, 2023Nov 4, 2023

• phenaki

  Public
  A phenaki reproduction using pytorch.

  Python

  •22•219•5•3•Updated Oct 23, 2023Oct 23, 2023

• General-GPT

  Public
  computer-visionmultimodal-learninglarge-language-models+ 1nlp

  Jupyter Notebook

  •

  Apache License 2.0

  •12•64•0•0•Updated Oct 4, 2023Oct 4, 2023

• worldsim

  Public
  Apache License 2.0

  •1•11•0•0•Updated Aug 29, 2023Aug 29, 2023

• math_problems-step-by-step_solutions

  Public
  Here we provide and collect many functions to generate math problem and step by step solutions for LLM training

  Python

  •

  Apache License 2.0

  •0•17•0•0•Updated Jun 21, 2023Jun 21, 2023

• OCR-ensemble

  Public
  Jupyter Notebook

  •4•38•0•0•Updated Jun 15, 2023Jun 15, 2023

• lucidrains-projects

  Public
  A summary of all lucidrains repositores and links to training / research approaches by LAION or other communities.

  Jupyter Notebook

  •14•272•0•0•Updated Jun 14, 2023Jun 14, 2023

• CLIP-based-NSFW-Detector

  Public
  Python

  •

  Other

  •30•336•12•1•Updated May 30, 2023May 30, 2023