config.json

{
  "architectures": [
    "PaliGemmaForConditionalGeneration"
  ],
  "hidden_size": 2048,
  "image_token_index": 256000,
  "model_type": "paligemma",
  "projection_dim": 8,
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "head_dim": 256,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_activation": null,
    "hidden_size": 8,
    "initializer_range": 0.02,
    "intermediate_size": 32,
    "max_position_embeddings": 8192,
    "model_type": "gemma",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_image_tokens": 196,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_theta": 10000.0,
    "use_cache": true,
    "vocab_size": 258522
  },
  "torch_dtype": "float32",
  "transformers_version": "4.56.0.dev0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 8,
    "image_size": 224,
    "intermediate_size": 32,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 4,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "patch_size": 16,
    "projection_dim": 8
  }
}