跳到正文
蚂蚁 inclusionAI:HuggingFace 新模型·· 1 天前AI 评分48

蚂蚁 inclusionAI 发布 Duo-1.0-causal-base 全双工交互世界模型权重

inclusionAI/Duo-1.0-causal-base

AI 导读

蚂蚁 inclusionAI 在 HuggingFace 发布 Duo 1.0 的 causal-base 变体权重,Duo 是面向实时音视频交互的全双工多模态世界模型。

正文 · 原文

Duo

Duo-1.0-causal-base

A Reciprocal World Model for Full-Duplex Interaction

arXiv Homepage Models Code

Model Overview

Duo is a full-duplex multimodal world model for real-time audio-visual interaction. This repository contains the Duo 1.0 causal-base model weights.

Field Value
Version Duo 1.0
Variant Causal base
Package Complete model bundle
Realization format PyTorch Distributed Checkpoint (DCP)
Default sampler Euler, 50 steps, flow shift 1.0

Package Contents

The bundle contains the Realization weights and backbone, Intent model and adapter, video and audio codecs, speech recognizer, and forced aligner. Runtime integrations can use realization/complete.json to identify the packaged model family and weight format.

Download

hf download inclusionAI/Duo-1.0-causal-base --local-dir weights

For code, configuration, and runtime-specific integration instructions, see inclusionAI/Duo.

License

These weights were initialized from MiniMax H3 and subsequently trained by the Duo team. See LICENSE and NOTICE for the applicable terms.

来源:蚂蚁 inclusionAI:HuggingFace 新模型 · huggingface.co