docs/SPACE_VLM_REPORT.md

Space VLM Validation Report

• Generated at: 2026-06-09 01:54:43 UTC
• Space URL: https://huggingface.co/spaces/build-small-hackathon/ObjectverseDiary
• Space repo: build-small-hackathon/ObjectverseDiary
• Overall status: PASS
• Vision backend expected: minicpm-v
• Text backend expected: mock

Space Configuration

• Applied configuration:
  • repo_id: build-small-hackathon/ObjectverseDiary
  • hardware: zero-a10g
  • OBJECTVERSE_VISION_BACKEND: minicpm-v
  • VISION_MODEL_ID: openbmb/MiniCPM-V-2_6
  • OBJECTVERSE_TEXT_BACKEND: mock
• Rollback configuration: not applied by this run; live MiniCPM-V configuration remains active.

Vision Runtime Probe

• backend: minicpm-v
• vision_model_id: openbmb/MiniCPM-V-2_6
• torch_import: True
• transformers_import: True
• cuda_available: True
• device_count: 1
• device_name: NVIDIA RTX PRO 6000 Blackwell Server Edition MIG 2g.48gb
• mps_available: False
• minicpm_load_attempted: True
• minicpm_load_ok: True
• Errors: none

Results

Coffee mug

• Status: PASS
• Source: https://commons.wikimedia.org/wiki/File:Striped_coffee_mug.jpg
• Local temporary image: .tmp/space-vlm-assets/mug.jpg
• Object name: Coffee Mug
• Visible features: Striped pattern, Handle, Matte finish
• Likely context: On a table or countertop in a home or café setting.
• Confidence: 0.90
• Runtime vision: minicpm-v object understanding
• Runtime text: mock persona and diary generation
• Fallbacks: mock-text-runtime

Computer keyboard

• Status: PASS
• Source: https://commons.wikimedia.org/wiki/File:Computer_keyboard.jpg
• Local temporary image: .tmp/space-vlm-assets/keyboard.jpg
• Object name: computer keyboard
• Visible features: QWERTY layout, function keys (F1-F12), numeric keypad
• Likely context: office or home workspace
• Confidence: 0.80
• Runtime vision: minicpm-v object understanding
• Runtime text: mock persona and diary generation
• Fallbacks: mock-text-runtime

Running shoe

• Status: PASS
• Source: https://commons.wikimedia.org/wiki/File:Running_shoes.jpg
• Local temporary image: .tmp/space-vlm-assets/shoe.jpg
• Object name: Running Shoe
• Visible features: Purple and pink mesh upper with reflective silver lines, Bright yellow laces, Green and white midsole
• Likely context: Outdoor sports or athletic activities
• Confidence: 0.90
• Runtime vision: minicpm-v object understanding
• Runtime text: mock persona and diary generation
• Fallbacks: mock-text-runtime

Notes

• Test images are temporary public Wikimedia Commons assets and are not committed.
• No tokens, secrets, or private file paths should be recorded in this report.
• If live validation fails, run the documented rollback command to switch OBJECTVERSE_VISION_BACKEND back to mock.