Hugging Face's logo

Phoebe13
/
Video-MTR

Visual Question Answering
Safetensors
English
qwen2_5_vl
Model card Files
xet
 Community
1

Video-MTR

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding.

This checkpoint extends Qwen2.5-VL-7B-Instruct with a multi-turn frame-retrieval policy trained via PPO, with an 80-frame video input budget.

References

Downloads last month
25
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
Visual Question Answering
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Phoebe13/Video-MTR

Base model

Qwen/Qwen2.5-VL-7B-Instruct
Finetuned
(1084)
this model
Quantizations
2 models

Space using Phoebe13/Video-MTR 1

Paper for Phoebe13/Video-MTR