---
title: Valley3-8B-Instruct
canonical_url: "https://www.modelscope.cn/models/bytedance-community/Valley3-8B-Instruct"
md_url: "https://www.modelscope.cn/models/bytedance-community/Valley3-8B-Instruct.md"
repository: bytedance-community/Valley3-8B-Instruct
last_updated: 2026-06-05
license: apache-2.0
model_type:
  - valley_omni
architectures:
  - ValleyOmniForConditionalGeneration
parameters: 9.5B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 19
stars: 0
---

# Valley3-8B-Instruct

> Valley3-8B-Instruct - bytedance-community 在 ModelScope 开源的模型。Valley Family: Exploring Scalable Vision-Language Design for Multimodal Understanding and Reasoning

bytedance-community/Valley3-8B-Instruct 是 ModelScope 魔搭社区上的 9.5B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: bytedance-community/Valley3-8B-Instruct
- **License**: apache-2.0
- **Parameters**: 9.5B
- **Downloads**: 19
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/bytedance-community/Valley3-8B-Instruct

---

<div align="center">

# Valley Family: Exploring Scalable Vision-Language Design for Multimodal Understanding and Reasoning

</div align="center">

<p align="center">
    <img src="https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/assets/valley_logo.jpg" width="500"/>
<p>

<p align="center">
        &nbsp&nbsp 🎮️ <a href="https://github.com/bytedance/Valley"> Github Repository </a>&nbsp&nbsp |
        &nbsp&nbsp 🤗 <a href="https://huggingface.co/collections/bytedance-research/valley">Huggingface Model Collection </a>&nbsp&nbsp |
        &nbsp&nbsp 📙 <a href="https://arxiv.org/abs/2605.01278">Technical Report</a>&nbsp&nbsp
</p>

## News
- [2026/05/05] 🔥🔥🔥 We have released the technical report of Valley3! Check out the full paper here: [Valley3 Technical Report](https://arxiv.org/abs/2605.01278).
- [2026/05/01] 🔥🔥🔥 We have released the model weights of [Valley3](https://huggingface.co/collections/bytedance-research/valley), which is an omni foundation model collection for unified e-commerce understanding and reasoning.
- [2025/11/27] 🔥🔥 We have released the technical report of Valley2.5! Check out the full paper here: [Valley2.5 Technical Report](https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/docs/Valley2_5_Tech_Report.pdf).  
- [2025/10/26] 🔥🔥 We have released the weights of [Valley2.5](https://huggingface.co/bytedance-research/Valley2.5), which significantly enhances multimodal understanding and reasoning capabilities. It has achieved 74.3 on the OpenCompass Multi-modal Academic Leaderboard!


## Introduction
Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data, which is developed by ByteDance. Our model:

- Achieved the best results in the inhouse e-commerce and short-video benchmarks, much better then other SOTA opensource models.
- Demonstrated comparatively outstanding performance in the OpenCompass Benchmark.

## Valley3
Valley3 is built upon the Qwen3-VL backbone and extends it with audio transformer for audio encoding. The audio embeddings are aligned to the visual-language backbone via an MLP-based connector, then concatenated with visual and text tokens into a unified input space, enabling omni-modal understanding.

<p align="center">
    <img src="https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/assets/valley3_structure.png" width="1000"/>
<p>

## Environment Setup & Inference Demo

Please refer to the detailed instruction in [Github: Valley3](https://github.com/bytedance/Valley/tree/main/valley3) repository.