Add model card for Geo-R1

This PR adds an initial model card for the Geo-R1 model, linking it to the paper [Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning](https://huggingface.co/papers/2510.00072).

It includes the `library_name: transformers` metadata, as evidenced by the `config.json` and `tokenizer_config.json` files which indicate compatibility with the `transformers` library. The `pipeline_tag: image-text-to-text` is also added to correctly categorize the model as a vision-language model on the Hub.

README.md

@@ -0,0 +1,12 @@
+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
+
+# Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning
+
+This repository contains the Geo-R1 model, a reasoning-centric post-training framework that unlocks geospatial reasoning in vision-language models, as introduced in the paper:
+
+[**Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning**](https://huggingface.co/papers/2510.00072)
+
+Geo-R1 combines "thinking scaffolding" (supervised fine-tuning on synthetic chain-of-thought exemplars) and an "elevating" stage using GRPO-based reinforcement learning on a weakly-supervised cross-view pairing proxy. This approach enables models to connect visual cues with geographic priors and harness reasoning for accurate prediction, achieving state-of-the-art performance across various geospatial reasoning benchmarks.