Diankun
/

Spatial-MLLM-subset-sft

Video-Text-to-Text

text2text-generation

text-generation-inference

Model card Files Files and versions Community

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/

Code: https://github.com/diankun-wu/Spatial-MLLM

Downloads last month: 2,100

Safetensors

Model size

5.32B params

Tensor type

BF16

·

Inference Providers NEW

Video-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Diankun/Spatial-MLLM-subset-sft

Base model

Qwen/Qwen2.5-VL-3B-Instruct

Finetuned

(298)

this model