| { | |
| "_name_or_path": "unography/blip-large-long-cap-sam-llava", | |
| "architectures": [ | |
| "BlipForConditionalGeneration" | |
| ], | |
| "image_text_hidden_size": 256, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "label_smoothing": 0.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "blip", | |
| "projection_dim": 512, | |
| "text_config": { | |
| "encoder_hidden_size": 1024, | |
| "initializer_factor": 1.0, | |
| "model_type": "blip_text_model", | |
| "num_attention_heads": 12 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.2", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "hidden_size": 1024, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "blip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24 | |
| } | |
| } | |