projector/config.json

{
  "architectures": [
    "CCAMModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_ccam_projector.CCAMConfig",
    "AutoModel": "modeling_ccam_projector.CCAMModel"
  },
  "cross_attention_frequency": 1,
  "encoder_hidden_size": 1152,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1152,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "ccam_projector",
  "num_attention_heads": 18,
  "num_hidden_layers": 1,
  "num_query_tokens": 1024,
  "output_size": 4096,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "query_attn_mask_type": "full",
  "spatial_pos_embed_type": "none",
  "spatial_resolution": [
    1,
    1
  ],
  "temporal_pos_embed_type": "none",
  "temporal_resolution": 16,
  "torch_dtype": "float32",
  "transformers_version": "4.40.2",
  "visual_attn_mask_type": "ccam",
  "vocab_size": 30522
}