inclusionAI/Duo-1.0-distill-quant 发布：FP8量化四步蒸馏的实时音视频交互全双工多模态世界模型
inclusionAI/Duo-1.0-distill-quant
inclusionAI 发布 FP8-量化四步蒸馏的 Duo 1.0 Realization 权重，用于其因果基础模型，支持全双工实时音视频交互，需与因果基础模型权重叠加使用。
Duo-1.0-distill-quant
A Reciprocal World Model for Full-Duplex Interaction
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 · Hugging Face 新模型 · huggingface.co