config.json

{
  "architectures": [
    "TIPSv2Model"
  ],
  "auto_map": {
    "AutoConfig": "configuration_tips.TIPSv2Config",
    "AutoModel": "modeling_tips.TIPSv2Model"
  },
  "model_type": "tipsv2",
  "temperature_init_value": 0.005065968260169029,
  "text_config": {
    "attention_dropout": 0.0,
    "bos_token_id": null,
    "eos_token_id": null,
    "hidden_act": "relu",
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 64,
    "model_type": "tipsv2_text_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "pad_token_id": 0,
    "pooling_epsilon": 1e-08,
    "scale_sqrt_depth": true,
    "vocab_size": 32000
  },
  "transformers_version": "5.10.0.dev0",
  "vision_config": {
    "apply_layernorm": true,
    "attention_probs_dropout_prob": 0.0,
    "drop_path_rate": 0.0,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "image_size": 448,
    "initializer_range": 0.02,
    "interpolate_antialias": true,
    "interpolate_offset": 0.0,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 4,
    "model_type": "tipsv2_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "num_register_tokens": 1,
    "out_features": [
      "stage12"
    ],
    "out_indices": [
      12
    ],
    "patch_size": 14,
    "qkv_bias": true,
    "reshape_hidden_states": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12"
    ],
    "use_swiglu_ffn": false
  }
}