LibraTree

/

GeoVista-RL-12k-7B

like 2

This PR significantly enhances the model card for LibraTree/GeoVista-RL-6k-7B by adding crucial metadata and detailed content:

• Metadata: Added pipeline_tag: image-text-to-text and library_name: transformers. The transformers compatibility is evidenced by the config.json and architectures field.
• Description: Provided an introductory description of the GeoVista model and its application to geolocalization tasks.
• Links: Included direct links to the paper (GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization), the official project page, and the GitHub repository.
• Sample Usage: Added a Python code snippet demonstrating basic inference with the transformers library, which is consistent with the model's transformers compatibility and enables the automated "how to use" widget on the Hub.
• Visuals & Benchmarking: Incorporated an illustrative image of the agentic pipeline and a section detailing the GeoBench benchmark, along with its comparison table.
• Citation: Included the BibTeX entry for easy citation.

These additions make the model more discoverable, provide comprehensive information, and offer a clear starting point for users.