vvl_vit/config.json

{
  "_name_or_path": "vit-large336-custom",
  "architectures": [
    "CLIPVisionModel"
  ],
  "attention_dropout": 0.0,
  "dropout": 0.0,
  "hidden_act": "quick_gelu",
  "hidden_size": 1024,
  "image_size": 336,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-05,
  "model_type": "clip_vision_model",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 24,
  "patch_size": 14,
  "projection_dim": 768,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "image_aspect_ratio": "anyres",
  "image_crop_resolution": 224,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_split_resolution": 224,
  "initializer_range": 0.02,
  "max_length": 4096,
  "max_position_embeddings": 4096,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower__": "openai/clip-vit-large-patch14-336",
  "mm_vision_tower_lr": 2e-06
}