vision_tower/config.json

{
  "_name_or_path": "./vision_tower",
  "architectures": [
    "InternVisionModel"
  ],
  "attention_dropout": 0.0,
  "drop_path_rate": 0.0,
  "dropout": 0.0,
  "hidden_act": "gelu",
  "hidden_size": 3200,
  "image_size": 448,
  "initializer_factor": 0.1,
  "initializer_range": 1e-10,
  "intermediate_size": 12800,
  "layer_norm_eps": 1e-06,
  "model_type": "intern_vit_6b",
  "num_attention_heads": 25,
  "num_channels": 3,
  "num_hidden_layers": 45,
  "patch_size": 14,
  "qk_normalization": true,
  "qkv_bias": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.2",
  "use_bfloat16": true,
  "use_flash_attn": true
}