config.json

{
  "alpha": 1.0,
  "architectures": [
    "TvpModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "backbone": null,
  "backbone_config": {
    "depths": [
      2,
      2
    ],
    "downsample_in_bottleneck": false,
    "downsample_in_first_stage": false,
    "embedding_size": 64,
    "embeddings_size": 64,
    "hidden_act": "relu",
    "hidden_sizes": [
      64,
      128
    ],
    "layer_type": "bottleneck",
    "model_type": "resnet",
    "num_channels": 3,
    "out_features": [
      "stage2"
    ],
    "out_indices": [
      2
    ],
    "stage_names": [
      "stem",
      "stage1",
      "stage2"
    ]
  },
  "beta": 0.1,
  "distance_loss_weight": 1.0,
  "dtype": "float32",
  "duration_loss_weight": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 32,
  "layer_norm_eps": 1e-12,
  "max_grid_col_position_embeddings": 30,
  "max_grid_row_position_embeddings": 30,
  "max_img_size": 448,
  "max_position_embeddings": 200,
  "model_type": "tvp",
  "num_attention_heads": 4,
  "num_frames": 2,
  "num_hidden_layers": 2,
  "pad_token_id": 0,
  "transformers_version": "5.16.0.dev0",
  "type_vocab_size": 2,
  "visual_prompt_size": 96,
  "visual_prompter_apply": "replace",
  "visual_prompter_type": "framepad",
  "vocab_size": 30522
}