跳到正文
RadarAI· 蚂蚁 inclusionAI:HuggingFace 新模型·· 5 小时前AI 评分22

蚂蚁 inclusionAI 发布 Duo-1.0-distill-quant:Duo 1.0 的 FP8 量化四步蒸馏权重

AI 导读

蚂蚁 inclusionAI 在 HuggingFace 发布 Duo-1.0-distill-quant,这是全双工音视频交互世界模型 Duo 1.0 的 FP8 量化四步蒸馏 Realization 权重。

正文 · 原文

蚂蚁 inclusionAI:HuggingFace 新模型·2026-11-13 16:09· 3 小时前AI 评分49

inclusionAI/Duo-1.0-distill-quant

AI 导读

蚂蚁 inclusionAI 在 HuggingFace 发布 Duo-1.0-distill-quant,即全双工音视频交互世界模型 Duo 1.0 的 FP8 量化四步蒸馏 Realization 权重。

正文 · 原文

Duo

Duo-1.0-distill-quant

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 FP8-quantized four-step distilled Realization weights for Duo 1.0.

Field Value
Version Duo 1.0
Variant FP8-quantized four-step distilled Realization
Package Realization overlay
Realization format ModelOpt FP8, per-channel scaling
Base dependency inclusionAI/Duo-1.0-causal-base
Default sampler Euler, 4 steps, flow shift 5.0

Usage

Download the complete Duo 1.0 causal-base bundle, then overlay these Realization weights into the same directory:

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

The shared Intent, codecs, speech models, and Realization backbone are supplied by the causal-base bundle. The consuming runtime must support the packaged ModelOpt FP8 format or an equivalent conversion path.

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

来源:RadarAI · aihot.news