Downloads · 30 days
79
13% of all-time downloads
Spatial-MLLM-v1.1-Instruct-820K
Diankun/Spatial-MLLM-v1.1-Instruct-820K
Spatial-MLLM-v1.1-Instruct-820K is a video-text-to-text model from Diankun. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
This repository contains the model described in Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence.
All-time downloads
624
Public
Parameters
5.6B
11.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11.2 GB · 100%
At a glance
- Task
- Video-Text-to-Text
- Library
- transformers
- License
- mit
- Model type
- spatial-mllm
- Access
- Public
- Created
- Jan 5, 2026
- Updated
- Jan 17, 2026
- SHA
- 89ac646b
Base models
Model card
From the Hugging Face model README
This repository contains the model described in Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence.
Project page: https://diankun-wu.github.io/Spatial-MLLM/
- Task
- Video-Text-to-Text
- Library
- transformers
- Type
- spatial-mllm
- License
- mit
- Created
- Jan 5, 2026
- Updated
- Jan 17, 2026