跳到正文
螞蟻 inclusionAI:HuggingFace 新模型·· 10 天前AI 評分54

inclusionAI 提供 Duo-1.0-causal-base 完整模型權重套件

inclusionAI/Duo-1.0-causal-base

AI 導讀

inclusionAI 的 Duo-1.0-causal-base 是支援即時音訊視覺互動的全雙工多模態世界模型,並提供完整模型權重套件。套件包含 Realization 權重與骨幹、意圖模型及 adapter、影片和音訊編解碼器、語音辨識器與強制對齊器。

正文

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.

來源:螞蟻 inclusionAI:HuggingFace 新模型 · huggingface.co