Hugging Face's logo

Diankun
/
Spatial-MLLM-v1.1-Instruct-820K

Video-Text-to-Text
Transformers
Safetensors
spatial-mllm
text-generation
Model card Files
xet
 Community
How to use from the
Use from the
Transformers library
# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("Diankun/Spatial-MLLM-v1.1-Instruct-820K", dtype="auto")
Quick Links

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
63
Safetensors
Model size
6B 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-v1.1-Instruct-820K

Base model

Qwen/Qwen2.5-VL-3B-Instruct
Finetuned
(789)
this model

Collection including Diankun/Spatial-MLLM-v1.1-Instruct-820K

Paper for Diankun/Spatial-MLLM-v1.1-Instruct-820K