config.json

{
  "architectures": [
    "LongCLIPModel"
  ],
  "dtype": "float32",
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "longclip",
  "projection_dim": 768,
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 768,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "interpolation_keep_length": 20,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 248,
    "model_type": "longclip_text_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "projection_dim": 512,
    "use_position_interpolation": true,
    "vocab_size": 49408
  },
  "transformers_version": "4.57.3",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "longclip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 512
  },
  "auto_map": {
    "AutoModel": "long_clip_hf.LongCLIPModel",
    "AutoConfig": "long_clip_hf.LongCLIPConfig"
  }
}