| { | |
| "in_dim": 3840, | |
| "out_dim": 512, | |
| "hidden": 1024, | |
| "variant": "radio_summary", | |
| "encoder": "nvidia/C-RADIOv2-H", | |
| "tile": 512, | |
| "pooling": "RADIO summary vector", | |
| "question": "Is there a bone fracture in this X-ray?", | |
| "options": [ | |
| "Yes, there is a fracture.", | |
| "No, there is no fracture." | |
| ], | |
| "positive_option": 0, | |
| "action_tower": { | |
| "encoder": "Qwen/Qwen3-8B (last-token pooling)", | |
| "head": "Contrastive-LM/CLM-v0.1-8B/CLM_v0.1-8B.pt" | |
| } | |
| } |