| { | |
| "add_special_token": false, | |
| "candidate_resolutions": [ | |
| [ | |
| 384, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 768 | |
| ], | |
| [ | |
| 768, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 1152 | |
| ], | |
| [ | |
| 1152, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 1536 | |
| ], | |
| [ | |
| 1536, | |
| 384 | |
| ], | |
| [ | |
| 768, | |
| 768 | |
| ], | |
| [ | |
| 384, | |
| 1920 | |
| ], | |
| [ | |
| 1920, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 2304 | |
| ], | |
| [ | |
| 2304, | |
| 384 | |
| ], | |
| [ | |
| 768, | |
| 1152 | |
| ], | |
| [ | |
| 1152, | |
| 768 | |
| ], | |
| [ | |
| 384, | |
| 2688 | |
| ], | |
| [ | |
| 2688, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 3072 | |
| ], | |
| [ | |
| 3072, | |
| 384 | |
| ], | |
| [ | |
| 768, | |
| 1536 | |
| ], | |
| [ | |
| 1536, | |
| 768 | |
| ], | |
| [ | |
| 384, | |
| 3456 | |
| ], | |
| [ | |
| 3456, | |
| 384 | |
| ], | |
| [ | |
| 1152, | |
| 1152 | |
| ] | |
| ], | |
| "downsample_ratio": 2, | |
| "ignore_id": -100, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_token": "<image>", | |
| "mask_prompt": false, | |
| "normalize": true, | |
| "pad_token": "<\uff5c\u2581pad\u2581\uff5c>", | |
| "patch_size": 14, | |
| "processor_class": "DeepseekVLV2Processor", | |
| "sft_format": "deepseek" | |
| } | |