| { | |
| "architectures": [ | |
| "Qwen2_5_VisionTransformerPretrainedModel" | |
| ], | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 2048, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.3", | |
| "window_size": 112 | |
| } | |