tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Foundation Architecture for (M)LLMs

A platform to catch price drops while shopping online, powered by a browser extension, webapp, android app, and more

Package containing the tools necessary for decomposing a speech signal into its modulated components (also known as AM-FM decomposition). Includes the algorithms of the QHM family and the YAAPT pit…

ZIO wrapper around Doobie and Anorm.

NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Official Pytorch Implementation for "DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion" (AAAI 2024)

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

Fast and memory-efficient exact attention

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

Apache Superset is a Data Visualization and Data Exploration Platform

Build Conversational AI in minutes ⚡️

Code to the ICLR 2024 Paper "Lagrangian Flow Networks".

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Official Github repository for the SIGCOMM '24 paper "Accelerating Model Training in Multi-cluster Environments with Consumer-grade GPUs"

High-quality Text-to-Audio Generation with Efficient Diffusion Transformer

Kolmogorov-Arnold Transformer: A PyTorch Implementation with CUDA kernel

Official Implementation of Convolutional Normalization: Improving Robustness and Training for Deep Neural Networks

The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Monotonic Alignment Search

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.

Scaling Diffusion Transformers with Mixture of Experts

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models