| { | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "drop_path_rate": 0.1, | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 448, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "intern_vit_6b", | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "qk_normalization": false, | |
| "qkv_bias": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.2", | |
| "use_flash_attn": true | |
| } | |