.

README.md

@@ -18,8 +18,49 @@ library_name: transformers
 pipeline_tag: video-text-to-text
 model_name: ViCA-7B
 base_model: lmms-lab/LLaVA-Video-7B-Qwen2
+model-index:
+- name: ViCA-7B
+  results:
+  - task:
+      type: visual-question-answering
+    dataset:
+      name: VSI-Bench
+      type: vsi-bench
+    metrics:
+    - type: score
+      value: 60.56
+      name: Average
+      verified: false
+    - type: MRA
+      value: 68.81
+      name: Object Count
+    - type: MRA
+      value: 57.01
+      name: Absolute Distance
+    - type: MRA
+      value: 79.17
+      name: Object Size
+    - type: MRA
+      value: 75.14
+      name: Room Size
+    - type: accuracy
+      value: 58.45
+      name: Relative Distance
+    - type: accuracy
+      value: 42.56
+      name: Relative Direction
+    - type: accuracy
+      value: 34.54
+      name: Route Plan
+    - type: accuracy
+      value: 68.77
+      name: Appearance Order
 ---
 
+<div align="center">
+  <img src="assets/banner.png" alt="ViCA Banner"/>
+</div>
+
 # ViCA-7B: Visuospatial Cognitive Assistant
 
 ## Overview