| base_model: | |
| - Qwen/Qwen2.5-7B-Instruct | |
| pipeline_tag: image-text-to-text | |
| tags: | |
| - depth-estimation | |
| ## SSR-MIDI-7B | |
| This model repository is for the models in the paper [SSR: Enhancing Depth Perception in Vision-Language | |
| Models via Rationale-Guided Spatial Reasoning](https://arxiv.org/abs/2505.12448). |