GPD Spatial Reasoning

by hugging-appsco.huggingface.hugging-apps/gpd-spatial-reasoning

  • Remote endpoint
  • 1 tool

Tools

  • gpd_spatial_reasoning_answer Answer a spatial-reasoning question about an image with GPD-4B. GPD (Geometry-Privileged Distillation) is an RGB-only vision-language model fine-tuned from Qwen3-VL-4B-Instruct for single-image 3D spatial reasoning (observer shifts, directional relations, depth/distance estimation). It thinks step by step between <think> and </think> tags and wraps its final answer in <answer> </answer> tags. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

As the server's own listing gives them. We never call a tool.