{
    "architectures": [
      "Gemma3ForConditionalGeneration"
    ],
    "boi_token_index": 255999,
    "eoi_token_index": 256000,
    "eos_token_id": [
      1,
      106
    ],
    "image_token_index": 262144,
    "initializer_range": 0.02,
    "mm_tokens_per_image": 256,
    "model_type": "gemma3",
    "text_config": {
      "attention_bias": false,
      "attention_dropout": 0.0,
      "attn_logit_softcapping": null,
      "cache_implementation": "hybrid",
      "final_logit_softcapping": null,
      "head_dim": 256,
      "hidden_activation": "gelu_pytorch_tanh",
      "hidden_size": 3840,
      "initializer_range": 0.02,
      "intermediate_size": 15360,
      "max_position_embeddings": 131072,
      "model_type": "gemma3_text",
      "num_attention_heads": 16,
      "num_hidden_layers": 48,
      "num_key_value_heads": 8,
      "query_pre_attn_scalar": 256,
      "rms_norm_eps": 1e-06,
      "rope_local_base_freq": 10000,
      "rope_scaling": {
        "factor": 8.0,
        "rope_type": "linear"
      },
      "rope_theta": 1000000,
      "sliding_window": 1024,
      "sliding_window_pattern": 6,
      "torch_dtype": "bfloat16",
      "use_cache": true,
      "vocab_size": 262208
    },
    "torch_dtype": "bfloat16",
    "transformers_version": "4.51.0",
    "vision_config": {
      "attention_dropout": 0.0,
      "hidden_act": "gelu_pytorch_tanh",
      "hidden_size": 1152,
      "image_size": 896,
      "intermediate_size": 4304,
      "layer_norm_eps": 1e-06,
      "model_type": "siglip_vision_model",
      "num_attention_heads": 16,
      "num_channels": 3,
      "num_hidden_layers": 27,
      "patch_size": 14,
      "torch_dtype": "bfloat16",
      "vision_use_head": false
    }
  }