config.json

{
  "architectures": [
    "Gemma3ForConditionalGeneration"
  ],
  "boi_token_index": 255999,
  "bos_token_id": 2,
  "eoi_token_index": 256000,
  "eos_token_id": 1,
  "hidden_size": 2048,
  "ignore_index": -100,
  "image_token_index": 257152,
  "initializer_range": 0.02,
  "mm_tokens_per_image": 256,
  "model_type": "gemma3",
  "pad_token_id": 0,
  "projection_dim": 2048,
  "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": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 16384,
    "max_position_embeddings": 131072,
    "model_type": "gemma3_text",
    "num_attention_heads": 8,
    "num_hidden_layers": 18,
    "num_image_tokens": 256,
    "num_key_value_heads": 1,
    "query_pre_attn_scalar": 256,
    "rms_norm_eps": 1e-06,
    "rope_local_base_freq": 10000.0,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": 4096,
    "sliding_window_pattern": 6,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 257155
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.3",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 224,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "num_image_tokens": 256,
    "patch_size": 14,
    "projection_dim": 2048,
    "projector_hidden_act": "gelu_fast",
    "torch_dtype": "bfloat16",
    "vision_use_head": false
  },
  "vocab_size": 257216
}