Add library name, pipeline tag and link to code

README.md

@@ -1,15 +1,21 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: video-text-to-text
 ---
 
 # 🎥 VideoMolmo: Spatio-Temporal Grounding meets Pointing
 
+This repository contains the model for spatio-temporal grounding, as described in [VideoMolmo: Spatio-Temporal Grounding Meets Pointing](https://huggingface.co/papers/2506.05336).
+
 [**WebPage**] -https://mbzuai-oryx.github.io/VideoMolmo/
 
 [**Paper**] –https://arxiv.org/abs/2506.05336
 
 [**Dataset & Benchmark (VPoS-Bench)**] –https://huggingface.co/datasets/ghazishazan/VPoS/tree/main
 
+Code: https://github.com/mbzuai-oryx/VideoMolmo
+
 ---
 
 ## 🧠 Overview
@@ -62,4 +68,4 @@ We evaluate VideoMolmo on:
 - **MeViS**
 - **Refer-DAVIS17**
 
----
+---