Valley Valley Family: Exploring Scalable Vision-Language Design for Multimodal Understanding and Reasoning bytedance-research/Valley3-8B-Instruct 10B • Updated 15 days ago • 27 • 2 bytedance-research/Valley3-32B-Instruct 34B • Updated 15 days ago • 38 • 2 bytedance-research/Valley3-8B-Think 10B • Updated 15 days ago • 27 • 3 bytedance-research/Valley3-32B-Think 34B • Updated 15 days ago • 27 • 1
Vidi Vidi model collection for multimodal video understanding and creation bytedance-research/Vidi-7B 9B • Updated Dec 15, 2025 • 33 • 16 bytedance-research/Vidi1.5-9B 10B • Updated Jan 22 • 35 • 10
Valley Valley Family: Exploring Scalable Vision-Language Design for Multimodal Understanding and Reasoning bytedance-research/Valley3-8B-Instruct 10B • Updated 15 days ago • 27 • 2 bytedance-research/Valley3-32B-Instruct 34B • Updated 15 days ago • 38 • 2 bytedance-research/Valley3-8B-Think 10B • Updated 15 days ago • 27 • 3 bytedance-research/Valley3-32B-Think 34B • Updated 15 days ago • 27 • 1
Vidi Vidi model collection for multimodal video understanding and creation bytedance-research/Vidi-7B 9B • Updated Dec 15, 2025 • 33 • 16 bytedance-research/Vidi1.5-9B 10B • Updated Jan 22 • 35 • 10
