Deploy latest CoRGI Gradio demo

PROGRESS_LOG.md

@@ -8,6 +8,7 @@
 - Tidied Qwen generation settings to avoid unused temperature flags when running deterministically.
 - Validated ROI extraction on a vision-heavy prompt against the real model and hardened prompts so responses stay in structured JSON without verbose preambles.
 - Added meta-comment pruning so thinking-mode rambles (e.g., redundant “Step 3” reflections) are dropped while preserving genuine reasoning; confirmed with the official demo image that only meaningful steps remain.
+- Authored a metadata-rich `README.md` (with Hugging Face Space front matter) so the deployed Space renders without configuration errors.
 
 ## 2024-10-21
 - Updated default checkpoints to `Qwen/Qwen3-VL-8B-Thinking` and verified CLI/Gradio/test coverage.

README.md

@@ -1,13 +1,42 @@
+---
+title: CoRGI Qwen3-VL Demo
+emoji: 🐶
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+sdk_version: "5.41.1"
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
 # CoRGI Qwen3-VL Demo
 
-This Space hosts the CoRGI reasoning pipeline backed by the Qwen/Qwen3-VL-8B-Thinking model.
+This Space showcases the CoRGI reasoning pipeline powered entirely by **Qwen/Qwen3-VL-8B-Thinking**.  
+Upload an image, ask a visual question, and the app will:
 
-## Run Locally
-```
+1. Generate structured reasoning steps with visual-verification flags.  
+2. Request region-of-interest evidence for steps that require vision.  
+3. Synthesize a grounded final answer.
+
+## Running Locally
+
+```bash
 pip install -r requirements.txt
-python examples/demo_qwen_corgi.py
+python examples/demo_qwen_corgi.py \
+  --model-id Qwen/Qwen3-VL-8B-Thinking \
+  --max-steps 3 \
+  --max-regions 3
 ```
 
-## Notes
-- The demo queues requests sequentially (ZeroGPU/cpu-basic hardware).
-- Configure `CORGI_QWEN_MODEL` to switch to a different checkpoint.
+To launch the Gradio demo locally:
+
+```bash
+python app.py
+```
+
+## Configuration Notes
+
+- The Space queues requests sequentially on `cpu-basic` (ZeroGPU) hardware.  
+- Set the `CORGI_QWEN_MODEL` environment variable to try another Qwen3-VL checkpoint (for example, `Qwen/Qwen3-VL-4B-Instruct`).  
+- `max_steps` and `max_regions` sliders control how many reasoning steps and ROI candidates the model returns.