OmniRet checkpoint-2220
Copyright 2026 Chuong Huynh and OmniRet contributors.

This distribution contains weights derived from Qwen-Audio.
Tongyi Qianwen is licensed under the Tongyi Qianwen LICENSE AGREEMENT,
Copyright (c) Alibaba Cloud. All Rights Reserved.

The text encoder derives from Alibaba-NLP/gte-Qwen2-1.5B-instruct and the
vision encoder derives from google/siglip-so400m-patch14-384. Those upstream
models are distributed under Apache License 2.0.

The example media comes from chuonghm/ACM and derives from VGG-Sound. ACM
metadata is MIT-licensed; media remains subject to VGG-Sound and source-video
terms. See README.md for source links and citations.